diff --git a/en/go/resources/realtime/index.md b/en/go/resources/realtime/index.md new file mode 100644 index 0000000..2a4d208 --- /dev/null +++ b/en/go/resources/realtime/index.md @@ -0,0 +1,24758 @@ +# Realtime + +## Domain Types + +### Audio Transcription + +- `type AudioTranscription struct{…}` + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + +### Conversation Created Event + +- `type ConversationCreatedEvent struct{…}` + + Returned when a conversation is created. Emitted right after session creation. + + - `Conversation ConversationCreatedEventConversation` + + The conversation resource. + + - `ID string` + + The unique ID of the conversation. + + - `Object string` + + The object type, must be `realtime.conversation`. + + - `const ConversationCreatedEventConversationObjectRealtimeConversation ConversationCreatedEventConversationObject = "realtime.conversation"` + + - `EventID string` + + The unique ID of the server event. + + - `Type ConversationCreated` + + The event type, must be `conversation.created`. + + - `const ConversationCreatedConversationCreated ConversationCreated = "conversation.created"` + +### Conversation Item + +- `type ConversationItemUnion interface{…}` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + +### Conversation Item Added + +- `type ConversationItemAdded struct{…}` + + Sent by the server when an Item is added to the default Conversation. This can happen in several cases: + + - When the client sends a `conversation.item.create` event. + - When the input audio buffer is committed. In this case the item will be a user message containing the audio from the buffer. + - When the model is generating a Response. In this case the `conversation.item.added` event will be sent when the model starts generating a specific Item, and thus it will not yet have any content (and `status` will be `in_progress`). + + The event will include the full content of the Item (except when model is generating a Response) except for audio data, which can be retrieved separately with a `conversation.item.retrieve` event if necessary. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Type ConversationItemAdded` + + The event type, must be `conversation.item.added`. + + - `const ConversationItemAddedConversationItemAdded ConversationItemAdded = "conversation.item.added"` + + - `PreviousItemID string` + + The ID of the item that precedes this one, if any. This is used to + maintain ordering when items are inserted. + +### Conversation Item Create Event + +- `type ConversationItemCreateEvent struct{…}` + + Add a new Item to the Conversation's context, including messages, function + calls, and function call responses. This event can be used both to populate a + "history" of the conversation and to add new items mid-stream, but has the + current limitation that it cannot populate assistant audio messages. + + If successful, the server will respond with a `conversation.item.created` + event, otherwise an `error` event will be sent. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Type ConversationItemCreate` + + The event type, must be `conversation.item.create`. + + - `const ConversationItemCreateConversationItemCreate ConversationItemCreate = "conversation.item.create"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `PreviousItemID string` + + The ID of the preceding item after which the new item will be inserted. If not set, the new item will be appended to the end of the conversation. + + If set to `root`, the new item will be added to the beginning of the conversation. + + If set to an existing ID, it allows an item to be inserted mid-conversation. If the ID cannot be found, an error will be returned and the item will not be added. + +### Conversation Item Created Event + +- `type ConversationItemCreatedEvent struct{…}` + + Returned when a conversation item is created. There are several scenarios that produce this event: + + - The server is generating a Response, which if successful will produce + either one or two Items, which will be of type `message` + (role `assistant`) or type `function_call`. + - The input audio buffer has been committed, either by the client or the + server (in `server_vad` mode). The server will take the content of the + input audio buffer and add it to a new user message Item. + - The client has sent a `conversation.item.create` event to add a new Item + to the Conversation. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Type ConversationItemCreated` + + The event type, must be `conversation.item.created`. + + - `const ConversationItemCreatedConversationItemCreated ConversationItemCreated = "conversation.item.created"` + + - `PreviousItemID string` + + The ID of the preceding item in the Conversation context, allows the + client to understand the order of the conversation. Can be `null` if the + item has no predecessor. + +### Conversation Item Delete Event + +- `type ConversationItemDeleteEvent struct{…}` + + Send this event when you want to remove any item from the conversation + history. The server will respond with a `conversation.item.deleted` event, + unless the item does not exist in the conversation history, in which case the + server will respond with an error. + + - `ItemID string` + + The ID of the item to delete. + + - `Type ConversationItemDelete` + + The event type, must be `conversation.item.delete`. + + - `const ConversationItemDeleteConversationItemDelete ConversationItemDelete = "conversation.item.delete"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Conversation Item Deleted Event + +- `type ConversationItemDeletedEvent struct{…}` + + Returned when an item in the conversation is deleted by the client with a + `conversation.item.delete` event. This event is used to synchronize the + server's understanding of the conversation history with the client's view. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item that was deleted. + + - `Type ConversationItemDeleted` + + The event type, must be `conversation.item.deleted`. + + - `const ConversationItemDeletedConversationItemDeleted ConversationItemDeleted = "conversation.item.deleted"` + +### Conversation Item Done + +- `type ConversationItemDone struct{…}` + + Returned when a conversation item is finalized. + + The event will include the full content of the Item except for audio data, which can be retrieved separately with a `conversation.item.retrieve` event if needed. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Type ConversationItemDone` + + The event type, must be `conversation.item.done`. + + - `const ConversationItemDoneConversationItemDone ConversationItemDone = "conversation.item.done"` + + - `PreviousItemID string` + + The ID of the item that precedes this one, if any. This is used to + maintain ordering when items are inserted. + +### Conversation Item Input Audio Transcription Completed Event + +- `type ConversationItemInputAudioTranscriptionCompletedEvent struct{…}` + + This event is the output of audio transcription for user audio written to the + user audio buffer. Transcription begins when the input audio buffer is + committed by the client or server (when VAD is enabled). Transcription runs + asynchronously with Response creation, so this event may come before or after + the Response events. + + Realtime API models accept audio natively, and thus input transcription is a + separate process run on a separate ASR (Automatic Speech Recognition) model. + The transcript may diverge somewhat from the model's interpretation, and + should be treated as a rough guide. + + - `ContentIndex int64` + + The index of the content part containing the audio. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item containing the audio that is being transcribed. + + - `Transcript string` + + The transcribed text. + + - `Type ConversationItemInputAudioTranscriptionCompleted` + + The event type, must be + `conversation.item.input_audio_transcription.completed`. + + - `const ConversationItemInputAudioTranscriptionCompletedConversationItemInputAudioTranscriptionCompleted ConversationItemInputAudioTranscriptionCompleted = "conversation.item.input_audio_transcription.completed"` + + - `Usage ConversationItemInputAudioTranscriptionCompletedEventUsageUnion` + + Usage statistics for the transcription, this is billed according to the ASR model's pricing rather than the realtime model's pricing. + + - `ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokens` + + - `InputTokens int64` + + Number of input tokens billed for this request. + + - `OutputTokens int64` + + Number of output tokens generated. + + - `TotalTokens int64` + + Total number of tokens used (input + output). + + - `Type Tokens` + + The type of the usage object. Always `tokens` for this variant. + + - `const TokensTokens Tokens = "tokens"` + + - `InputTokenDetails ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokensInputTokenDetails` + + Details about the input tokens billed for this request. + + - `AudioTokens int64` + + Number of audio tokens billed for this request. + + - `TextTokens int64` + + Number of text tokens billed for this request. + + - `ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageDuration` + + - `Seconds float64` + + Duration of the input audio in seconds. + + - `Type Duration` + + The type of the usage object. Always `duration` for this variant. + + - `const DurationDuration Duration = "duration"` + + - `Logprobs []LogProbProperties` + + The log probabilities of the transcription. + + - `Token string` + + The token that was used to generate the log probability. + + - `Bytes []int64` + + The bytes that were used to generate the log probability. + + - `Logprob float64` + + The log probability of the token. + +### Conversation Item Input Audio Transcription Delta Event + +- `type ConversationItemInputAudioTranscriptionDeltaEvent struct{…}` + + Returned when the text value of an input audio transcription content part is updated with incremental transcription results. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item containing the audio that is being transcribed. + + - `Type ConversationItemInputAudioTranscriptionDelta` + + The event type, must be `conversation.item.input_audio_transcription.delta`. + + - `const ConversationItemInputAudioTranscriptionDeltaConversationItemInputAudioTranscriptionDelta ConversationItemInputAudioTranscriptionDelta = "conversation.item.input_audio_transcription.delta"` + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + The text delta. + + - `Logprobs []LogProbProperties` + + The log probabilities of the transcription. These can be enabled by configurating the session with `"include": ["item.input_audio_transcription.logprobs"]`. Each entry in the array corresponds a log probability of which token would be selected for this chunk of transcription. This can help to identify if it was possible there were multiple valid options for a given chunk of transcription. + + - `Token string` + + The token that was used to generate the log probability. + + - `Bytes []int64` + + The bytes that were used to generate the log probability. + + - `Logprob float64` + + The log probability of the token. + +### Conversation Item Input Audio Transcription Failed Event + +- `type ConversationItemInputAudioTranscriptionFailedEvent struct{…}` + + Returned when input audio transcription is configured, and a transcription + request for a user message failed. These events are separate from other + `error` events so that the client can identify the related Item. + + - `ContentIndex int64` + + The index of the content part containing the audio. + + - `Error ConversationItemInputAudioTranscriptionFailedEventError` + + Details of the transcription error. + + - `Code string` + + Error code, if any. + + - `Message string` + + A human-readable error message. + + - `Param string` + + Parameter related to the error, if any. + + - `Type string` + + The type of error. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item. + + - `Type ConversationItemInputAudioTranscriptionFailed` + + The event type, must be + `conversation.item.input_audio_transcription.failed`. + + - `const ConversationItemInputAudioTranscriptionFailedConversationItemInputAudioTranscriptionFailed ConversationItemInputAudioTranscriptionFailed = "conversation.item.input_audio_transcription.failed"` + +### Conversation Item Input Audio Transcription Segment + +- `type ConversationItemInputAudioTranscriptionSegment struct{…}` + + Returned when an input audio transcription segment is identified for an item. + + - `ID string` + + The segment identifier. + + - `ContentIndex int64` + + The index of the input audio content part within the item. + + - `End float64` + + End time of the segment in seconds. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item containing the input audio content. + + - `Speaker string` + + The detected speaker label for this segment. + + - `Start float64` + + Start time of the segment in seconds. + + - `Text string` + + The text for this segment. + + - `Type ConversationItemInputAudioTranscriptionSegment` + + The event type, must be `conversation.item.input_audio_transcription.segment`. + + - `const ConversationItemInputAudioTranscriptionSegmentConversationItemInputAudioTranscriptionSegment ConversationItemInputAudioTranscriptionSegment = "conversation.item.input_audio_transcription.segment"` + +### Conversation Item Retrieve Event + +- `type ConversationItemRetrieveEvent struct{…}` + + Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. + The server will respond with a `conversation.item.retrieved` event, + unless the item does not exist in the conversation history, in which case the + server will respond with an error. + + - `ItemID string` + + The ID of the item to retrieve. + + - `Type ConversationItemRetrieve` + + The event type, must be `conversation.item.retrieve`. + + - `const ConversationItemRetrieveConversationItemRetrieve ConversationItemRetrieve = "conversation.item.retrieve"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Conversation Item Truncate Event + +- `type ConversationItemTruncateEvent struct{…}` + + Send this event to truncate a previous assistant message’s audio. The server + will produce audio faster than realtime, so this event is useful when the user + interrupts to truncate audio that has already been sent to the client but not + yet played. This will synchronize the server's understanding of the audio with + the client's playback. + + Truncating audio will delete the server-side text transcript to ensure there + is not text in the context that hasn't been heard by the user. + + If successful, the server will respond with a `conversation.item.truncated` + event. + + - `AudioEndMs int64` + + Inclusive duration up to which audio is truncated, in milliseconds. If + the audio_end_ms is greater than the actual audio duration, the server + will respond with an error. + + - `ContentIndex int64` + + The index of the content part to truncate. Set this to `0`. + + - `ItemID string` + + The ID of the assistant message item to truncate. Only assistant message + items can be truncated. + + - `Type ConversationItemTruncate` + + The event type, must be `conversation.item.truncate`. + + - `const ConversationItemTruncateConversationItemTruncate ConversationItemTruncate = "conversation.item.truncate"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Conversation Item Truncated Event + +- `type ConversationItemTruncatedEvent struct{…}` + + Returned when an earlier assistant audio message item is truncated by the + client with a `conversation.item.truncate` event. This event is used to + synchronize the server's understanding of the audio with the client's playback. + + This action will truncate the audio and remove the server-side text transcript + to ensure there is no text in the context that hasn't been heard by the user. + + - `AudioEndMs int64` + + The duration up to which the audio was truncated, in milliseconds. + + - `ContentIndex int64` + + The index of the content part that was truncated. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the assistant message item that was truncated. + + - `Type ConversationItemTruncated` + + The event type, must be `conversation.item.truncated`. + + - `const ConversationItemTruncatedConversationItemTruncated ConversationItemTruncated = "conversation.item.truncated"` + +### Conversation Item With Reference + +- `type ConversationItemWithReference struct{…}` + + The item to add to the conversation. + + - `ID string` + + For an item of type (`message` | `function_call` | `function_call_output`) + this field allows the client to assign the unique ID of the item. It is + not required because the server will generate one if not provided. + + For an item of type `item_reference`, this field is required and is a + reference to any item that has previously existed in the conversation. + + - `Arguments string` + + The arguments of the function call (for `function_call` items). + + - `CallID string` + + The ID of the function call (for `function_call` and + `function_call_output` items). If passed on a `function_call_output` + item, the server will check that a `function_call` item with the same + ID exists in the conversation history. + + - `Content []ConversationItemWithReferenceContent` + + The content of the message, applicable for `message` items. + + - Message items of role `system` support only `input_text` content + - Message items of role `user` support `input_text` and `input_audio` + content + - Message items of role `assistant` support `text` content. + + - `ID string` + + ID of a previous conversation item to reference (for `item_reference` + content types in `response.create` events). These can reference both + client and server created items. + + - `Audio string` + + Base64-encoded audio bytes, used for `input_audio` content type. + + - `Text string` + + The text content, used for `input_text` and `text` content types. + + - `Transcript string` + + The transcript of the audio, used for `input_audio` content type. + + - `Type string` + + The content type (`input_text`, `input_audio`, `item_reference`, `text`). + + - `const ConversationItemWithReferenceContentTypeInputText ConversationItemWithReferenceContentType = "input_text"` + + - `const ConversationItemWithReferenceContentTypeInputAudio ConversationItemWithReferenceContentType = "input_audio"` + + - `const ConversationItemWithReferenceContentTypeItemReference ConversationItemWithReferenceContentType = "item_reference"` + + - `const ConversationItemWithReferenceContentTypeText ConversationItemWithReferenceContentType = "text"` + + - `Name string` + + The name of the function being called (for `function_call` items). + + - `Object ConversationItemWithReferenceObject` + + Identifier for the API object being returned - always `realtime.item`. + + - `const ConversationItemWithReferenceObjectRealtimeItem ConversationItemWithReferenceObject = "realtime.item"` + + - `Output string` + + The output of the function call (for `function_call_output` items). + + - `Role ConversationItemWithReferenceRole` + + The role of the message sender (`user`, `assistant`, `system`), only + applicable for `message` items. + + - `const ConversationItemWithReferenceRoleUser ConversationItemWithReferenceRole = "user"` + + - `const ConversationItemWithReferenceRoleAssistant ConversationItemWithReferenceRole = "assistant"` + + - `const ConversationItemWithReferenceRoleSystem ConversationItemWithReferenceRole = "system"` + + - `Status ConversationItemWithReferenceStatus` + + The status of the item (`completed`, `incomplete`, `in_progress`). These have no effect + on the conversation, but are accepted for consistency with the + `conversation.item.created` event. + + - `const ConversationItemWithReferenceStatusCompleted ConversationItemWithReferenceStatus = "completed"` + + - `const ConversationItemWithReferenceStatusIncomplete ConversationItemWithReferenceStatus = "incomplete"` + + - `const ConversationItemWithReferenceStatusInProgress ConversationItemWithReferenceStatus = "in_progress"` + + - `Type ConversationItemWithReferenceType` + + The type of the item (`message`, `function_call`, `function_call_output`, `item_reference`). + + - `const ConversationItemWithReferenceTypeMessage ConversationItemWithReferenceType = "message"` + + - `const ConversationItemWithReferenceTypeFunctionCall ConversationItemWithReferenceType = "function_call"` + + - `const ConversationItemWithReferenceTypeFunctionCallOutput ConversationItemWithReferenceType = "function_call_output"` + + - `const ConversationItemWithReferenceTypeItemReference ConversationItemWithReferenceType = "item_reference"` + +### Input Audio Buffer Append Event + +- `type InputAudioBufferAppendEvent struct{…}` + + Send this event to append audio bytes to the input audio buffer. The audio + buffer is temporary storage you can write to and later commit. A "commit" will create a new + user message item in the conversation history from the buffer content and clear the buffer. + Input audio transcription (if enabled) will be generated when the buffer is committed. + + If VAD is enabled the audio buffer is used to detect speech and the server will decide + when to commit. When Server VAD is disabled, you must commit the audio buffer + manually. Input audio noise reduction operates on writes to the audio buffer. + + The client may choose how much audio to place in each event up to a maximum + of 15 MiB, for example streaming smaller chunks from the client may allow the + VAD to be more responsive. Unlike most other client events, the server will + not send a confirmation response to this event. + + - `Audio string` + + Base64-encoded audio bytes. This must be in the format specified by the + `input_audio_format` field in the session configuration. + + - `Type InputAudioBufferAppend` + + The event type, must be `input_audio_buffer.append`. + + - `const InputAudioBufferAppendInputAudioBufferAppend InputAudioBufferAppend = "input_audio_buffer.append"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Input Audio Buffer Clear Event + +- `type InputAudioBufferClearEvent struct{…}` + + Send this event to clear the audio bytes in the buffer. The server will + respond with an `input_audio_buffer.cleared` event. + + - `Type InputAudioBufferClear` + + The event type, must be `input_audio_buffer.clear`. + + - `const InputAudioBufferClearInputAudioBufferClear InputAudioBufferClear = "input_audio_buffer.clear"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Input Audio Buffer Cleared Event + +- `type InputAudioBufferClearedEvent struct{…}` + + Returned when the input audio buffer is cleared by the client with a + `input_audio_buffer.clear` event. + + - `EventID string` + + The unique ID of the server event. + + - `Type InputAudioBufferCleared` + + The event type, must be `input_audio_buffer.cleared`. + + - `const InputAudioBufferClearedInputAudioBufferCleared InputAudioBufferCleared = "input_audio_buffer.cleared"` + +### Input Audio Buffer Commit Event + +- `type InputAudioBufferCommitEvent struct{…}` + + Send this event to commit the user input audio buffer, which will create a new user message item in the conversation. This event will produce an error if the input audio buffer is empty. When in Server VAD mode, the client does not need to send this event, the server will commit the audio buffer automatically. + + Committing the input audio buffer will trigger input audio transcription (if enabled in session configuration), but it will not create a response from the model. The server will respond with an `input_audio_buffer.committed` event. + + - `Type InputAudioBufferCommit` + + The event type, must be `input_audio_buffer.commit`. + + - `const InputAudioBufferCommitInputAudioBufferCommit InputAudioBufferCommit = "input_audio_buffer.commit"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Input Audio Buffer Committed Event + +- `type InputAudioBufferCommittedEvent struct{…}` + + Returned when an input audio buffer is committed, either by the client or + automatically in server VAD mode. The `item_id` property is the ID of the user + message item that will be created, thus a `conversation.item.created` event + will also be sent to the client. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item that will be created. + + - `Type InputAudioBufferCommitted` + + The event type, must be `input_audio_buffer.committed`. + + - `const InputAudioBufferCommittedInputAudioBufferCommitted InputAudioBufferCommitted = "input_audio_buffer.committed"` + + - `PreviousItemID string` + + The ID of the preceding item after which the new item will be inserted. + Can be `null` if the item has no predecessor. + +### Input Audio Buffer Dtmf Event Received Event + +- `type InputAudioBufferDtmfEventReceivedEvent struct{…}` + + **SIP Only:** Returned when an DTMF event is received. A DTMF event is a message that + represents a telephone keypad press (0–9, *, #, A–D). The `event` property + is the keypad that the user press. The `received_at` is the UTC Unix Timestamp + that the server received the event. + + - `Event string` + + The telephone keypad that was pressed by the user. + + - `ReceivedAt int64` + + UTC Unix Timestamp when DTMF Event was received by server. + + - `Type InputAudioBufferDtmfEventReceived` + + The event type, must be `input_audio_buffer.dtmf_event_received`. + + - `const InputAudioBufferDtmfEventReceivedInputAudioBufferDtmfEventReceived InputAudioBufferDtmfEventReceived = "input_audio_buffer.dtmf_event_received"` + +### Input Audio Buffer Speech Started Event + +- `type InputAudioBufferSpeechStartedEvent struct{…}` + + Sent by the server when in `server_vad` mode to indicate that speech has been + detected in the audio buffer. This can happen any time audio is added to the + buffer (unless speech is already detected). The client may want to use this + event to interrupt audio playback or provide visual feedback to the user. + + The client should expect to receive a `input_audio_buffer.speech_stopped` event + when speech stops. The `item_id` property is the ID of the user message item + that will be created when speech stops and will also be included in the + `input_audio_buffer.speech_stopped` event (unless the client manually commits + the audio buffer during VAD activation). + + - `AudioStartMs int64` + + Milliseconds from the start of all audio written to the buffer during the + session when speech was first detected. This will correspond to the + beginning of audio sent to the model, and thus includes the + `prefix_padding_ms` configured in the Session. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item that will be created when speech stops. + + - `Type InputAudioBufferSpeechStarted` + + The event type, must be `input_audio_buffer.speech_started`. + + - `const InputAudioBufferSpeechStartedInputAudioBufferSpeechStarted InputAudioBufferSpeechStarted = "input_audio_buffer.speech_started"` + +### Input Audio Buffer Speech Stopped Event + +- `type InputAudioBufferSpeechStoppedEvent struct{…}` + + Returned in `server_vad` mode when the server detects the end of speech in + the audio buffer. The server will also send an `conversation.item.created` + event with the user message item that is created from the audio buffer. + + - `AudioEndMs int64` + + Milliseconds since the session started when speech stopped. This will + correspond to the end of audio sent to the model, and thus includes the + `min_silence_duration_ms` configured in the Session. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item that will be created. + + - `Type InputAudioBufferSpeechStopped` + + The event type, must be `input_audio_buffer.speech_stopped`. + + - `const InputAudioBufferSpeechStoppedInputAudioBufferSpeechStopped InputAudioBufferSpeechStopped = "input_audio_buffer.speech_stopped"` + +### Input Audio Buffer Timeout Triggered + +- `type InputAudioBufferTimeoutTriggered struct{…}` + + Returned when the Server VAD timeout is triggered for the input audio buffer. This is configured + with `idle_timeout_ms` in the `turn_detection` settings of the session, and it indicates that + there hasn't been any speech detected for the configured duration. + + The `audio_start_ms` and `audio_end_ms` fields indicate the segment of audio after the last + model response up to the triggering time, as an offset from the beginning of audio written + to the input audio buffer. This means it demarcates the segment of audio that was silent and + the difference between the start and end values will roughly match the configured timeout. + + The empty audio will be committed to the conversation as an `input_audio` item (there will be a + `input_audio_buffer.committed` event) and a model response will be generated. There may be speech + that didn't trigger VAD but is still detected by the model, so the model may respond with + something relevant to the conversation or a prompt to continue speaking. + + - `AudioEndMs int64` + + Millisecond offset of audio written to the input audio buffer at the time the timeout was triggered. + + - `AudioStartMs int64` + + Millisecond offset of audio written to the input audio buffer that was after the playback time of the last model response. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item associated with this segment. + + - `Type InputAudioBufferTimeoutTriggered` + + The event type, must be `input_audio_buffer.timeout_triggered`. + + - `const InputAudioBufferTimeoutTriggeredInputAudioBufferTimeoutTriggered InputAudioBufferTimeoutTriggered = "input_audio_buffer.timeout_triggered"` + +### Log Prob Properties + +- `type LogProbProperties struct{…}` + + A log probability object. + + - `Token string` + + The token that was used to generate the log probability. + + - `Bytes []int64` + + The bytes that were used to generate the log probability. + + - `Logprob float64` + + The log probability of the token. + +### Mcp List Tools Completed + +- `type McpListToolsCompleted struct{…}` + + Returned when listing MCP tools has completed for an item. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP list tools item. + + - `Type McpListToolsCompleted` + + The event type, must be `mcp_list_tools.completed`. + + - `const McpListToolsCompletedMcpListToolsCompleted McpListToolsCompleted = "mcp_list_tools.completed"` + +### Mcp List Tools Failed + +- `type McpListToolsFailed struct{…}` + + Returned when listing MCP tools has failed for an item. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP list tools item. + + - `Type McpListToolsFailed` + + The event type, must be `mcp_list_tools.failed`. + + - `const McpListToolsFailedMcpListToolsFailed McpListToolsFailed = "mcp_list_tools.failed"` + +### Mcp List Tools In Progress + +- `type McpListToolsInProgress struct{…}` + + Returned when listing MCP tools is in progress for an item. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP list tools item. + + - `Type McpListToolsInProgress` + + The event type, must be `mcp_list_tools.in_progress`. + + - `const McpListToolsInProgressMcpListToolsInProgress McpListToolsInProgress = "mcp_list_tools.in_progress"` + +### Noise Reduction Type + +- `type NoiseReductionType string` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + +### Output Audio Buffer Clear Event + +- `type OutputAudioBufferClearEvent struct{…}` + + **WebRTC/SIP Only:** Emit to cut off the current audio response. This will trigger the server to + stop generating audio and emit a `output_audio_buffer.cleared` event. This + event should be preceded by a `response.cancel` client event to stop the + generation of the current response. + [Learn more](https://platform.openai.com/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + + - `Type OutputAudioBufferClear` + + The event type, must be `output_audio_buffer.clear`. + + - `const OutputAudioBufferClearOutputAudioBufferClear OutputAudioBufferClear = "output_audio_buffer.clear"` + + - `EventID string` + + The unique ID of the client event used for error handling. + +### Rate Limits Updated Event + +- `type RateLimitsUpdatedEvent struct{…}` + + Emitted at the beginning of a Response to indicate the updated rate limits. + When a Response is created some tokens will be "reserved" for the output + tokens, the rate limits shown here reflect that reservation, which is then + adjusted accordingly once the Response is completed. + + - `EventID string` + + The unique ID of the server event. + + - `RateLimits []RateLimitsUpdatedEventRateLimit` + + List of rate limit information. + + - `Limit int64` + + The maximum allowed value for the rate limit. + + - `Name string` + + The name of the rate limit (`requests`, `tokens`). + + - `const RateLimitsUpdatedEventRateLimitNameRequests RateLimitsUpdatedEventRateLimitName = "requests"` + + - `const RateLimitsUpdatedEventRateLimitNameTokens RateLimitsUpdatedEventRateLimitName = "tokens"` + + - `Remaining int64` + + The remaining value before the limit is reached. + + - `ResetSeconds float64` + + Seconds until the rate limit resets. + + - `Type RateLimitsUpdated` + + The event type, must be `rate_limits.updated`. + + - `const RateLimitsUpdatedRateLimitsUpdated RateLimitsUpdated = "rate_limits.updated"` + +### Realtime Audio Config + +- `type RealtimeAudioConfig struct{…}` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + +### Realtime Audio Config Input + +- `type RealtimeAudioConfigInput struct{…}` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + +### Realtime Audio Config Output + +- `type RealtimeAudioConfigOutput struct{…}` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + +### Realtime Audio Formats + +- `type RealtimeAudioFormatsUnion interface{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + +### Realtime Audio Input Turn Detection + +- `type RealtimeAudioInputTurnDetectionUnion interface{…}` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + +### Realtime Client Event + +- `type RealtimeClientEventUnion interface{…}` + + A realtime client event. + + - `type ConversationItemCreateEvent struct{…}` + + Add a new Item to the Conversation's context, including messages, function + calls, and function call responses. This event can be used both to populate a + "history" of the conversation and to add new items mid-stream, but has the + current limitation that it cannot populate assistant audio messages. + + If successful, the server will respond with a `conversation.item.created` + event, otherwise an `error` event will be sent. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Type ConversationItemCreate` + + The event type, must be `conversation.item.create`. + + - `const ConversationItemCreateConversationItemCreate ConversationItemCreate = "conversation.item.create"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `PreviousItemID string` + + The ID of the preceding item after which the new item will be inserted. If not set, the new item will be appended to the end of the conversation. + + If set to `root`, the new item will be added to the beginning of the conversation. + + If set to an existing ID, it allows an item to be inserted mid-conversation. If the ID cannot be found, an error will be returned and the item will not be added. + + - `type ConversationItemDeleteEvent struct{…}` + + Send this event when you want to remove any item from the conversation + history. The server will respond with a `conversation.item.deleted` event, + unless the item does not exist in the conversation history, in which case the + server will respond with an error. + + - `ItemID string` + + The ID of the item to delete. + + - `Type ConversationItemDelete` + + The event type, must be `conversation.item.delete`. + + - `const ConversationItemDeleteConversationItemDelete ConversationItemDelete = "conversation.item.delete"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type ConversationItemRetrieveEvent struct{…}` + + Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. + The server will respond with a `conversation.item.retrieved` event, + unless the item does not exist in the conversation history, in which case the + server will respond with an error. + + - `ItemID string` + + The ID of the item to retrieve. + + - `Type ConversationItemRetrieve` + + The event type, must be `conversation.item.retrieve`. + + - `const ConversationItemRetrieveConversationItemRetrieve ConversationItemRetrieve = "conversation.item.retrieve"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type ConversationItemTruncateEvent struct{…}` + + Send this event to truncate a previous assistant message’s audio. The server + will produce audio faster than realtime, so this event is useful when the user + interrupts to truncate audio that has already been sent to the client but not + yet played. This will synchronize the server's understanding of the audio with + the client's playback. + + Truncating audio will delete the server-side text transcript to ensure there + is not text in the context that hasn't been heard by the user. + + If successful, the server will respond with a `conversation.item.truncated` + event. + + - `AudioEndMs int64` + + Inclusive duration up to which audio is truncated, in milliseconds. If + the audio_end_ms is greater than the actual audio duration, the server + will respond with an error. + + - `ContentIndex int64` + + The index of the content part to truncate. Set this to `0`. + + - `ItemID string` + + The ID of the assistant message item to truncate. Only assistant message + items can be truncated. + + - `Type ConversationItemTruncate` + + The event type, must be `conversation.item.truncate`. + + - `const ConversationItemTruncateConversationItemTruncate ConversationItemTruncate = "conversation.item.truncate"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type InputAudioBufferAppendEvent struct{…}` + + Send this event to append audio bytes to the input audio buffer. The audio + buffer is temporary storage you can write to and later commit. A "commit" will create a new + user message item in the conversation history from the buffer content and clear the buffer. + Input audio transcription (if enabled) will be generated when the buffer is committed. + + If VAD is enabled the audio buffer is used to detect speech and the server will decide + when to commit. When Server VAD is disabled, you must commit the audio buffer + manually. Input audio noise reduction operates on writes to the audio buffer. + + The client may choose how much audio to place in each event up to a maximum + of 15 MiB, for example streaming smaller chunks from the client may allow the + VAD to be more responsive. Unlike most other client events, the server will + not send a confirmation response to this event. + + - `Audio string` + + Base64-encoded audio bytes. This must be in the format specified by the + `input_audio_format` field in the session configuration. + + - `Type InputAudioBufferAppend` + + The event type, must be `input_audio_buffer.append`. + + - `const InputAudioBufferAppendInputAudioBufferAppend InputAudioBufferAppend = "input_audio_buffer.append"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type InputAudioBufferClearEvent struct{…}` + + Send this event to clear the audio bytes in the buffer. The server will + respond with an `input_audio_buffer.cleared` event. + + - `Type InputAudioBufferClear` + + The event type, must be `input_audio_buffer.clear`. + + - `const InputAudioBufferClearInputAudioBufferClear InputAudioBufferClear = "input_audio_buffer.clear"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type OutputAudioBufferClearEvent struct{…}` + + **WebRTC/SIP Only:** Emit to cut off the current audio response. This will trigger the server to + stop generating audio and emit a `output_audio_buffer.cleared` event. This + event should be preceded by a `response.cancel` client event to stop the + generation of the current response. + [Learn more](https://platform.openai.com/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + + - `Type OutputAudioBufferClear` + + The event type, must be `output_audio_buffer.clear`. + + - `const OutputAudioBufferClearOutputAudioBufferClear OutputAudioBufferClear = "output_audio_buffer.clear"` + + - `EventID string` + + The unique ID of the client event used for error handling. + + - `type InputAudioBufferCommitEvent struct{…}` + + Send this event to commit the user input audio buffer, which will create a new user message item in the conversation. This event will produce an error if the input audio buffer is empty. When in Server VAD mode, the client does not need to send this event, the server will commit the audio buffer automatically. + + Committing the input audio buffer will trigger input audio transcription (if enabled in session configuration), but it will not create a response from the model. The server will respond with an `input_audio_buffer.committed` event. + + - `Type InputAudioBufferCommit` + + The event type, must be `input_audio_buffer.commit`. + + - `const InputAudioBufferCommitInputAudioBufferCommit InputAudioBufferCommit = "input_audio_buffer.commit"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type ResponseCancelEvent struct{…}` + + Send this event to cancel an in-progress response. The server will respond + with a `response.done` event with a status of `response.status=cancelled`. If + there is no response to cancel, the server will respond with an error. It's safe + to call `response.cancel` even if no response is in progress, an error will be + returned the session will remain unaffected. + + - `Type ResponseCancel` + + The event type, must be `response.cancel`. + + - `const ResponseCancelResponseCancel ResponseCancel = "response.cancel"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `ResponseID string` + + A specific response ID to cancel - if not provided, will cancel an + in-progress response in the default conversation. + + - `type ResponseCreateEvent struct{…}` + + This event instructs the server to create a Response, which means triggering + model inference. When in Server VAD mode, the server will create Responses + automatically. + + A Response will include at least one Item, and may have two, in which case + the second will be a function call. These Items will be appended to the + conversation history by default. + + The server will respond with a `response.created` event, events for Items + and content created, and finally a `response.done` event to indicate the + Response is complete. + + The `response.create` event includes inference configuration like + `instructions` and `tools`. If these are set, they will override the Session's + configuration for this Response only. + + Responses can be created out-of-band of the default Conversation, meaning that they can + have arbitrary input, and it's possible to disable writing the output to the Conversation. + Only one Response can write to the default Conversation at a time, but otherwise multiple + Responses can be created in parallel. The `metadata` field is a good way to disambiguate + multiple simultaneous Responses. + + Clients can set `conversation` to `none` to create a Response that does not write to the default + Conversation. Arbitrary input can be provided with the `input` field, which is an array accepting + raw Items and references to existing Items. + + - `Type ResponseCreate` + + The event type, must be `response.create`. + + - `const ResponseCreateResponseCreate ResponseCreate = "response.create"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `Response RealtimeResponseCreateParamsResp` + + Create a new Realtime response with these parameters + + - `Audio RealtimeResponseCreateAudioOutput` + + Configuration for audio input and output. + + - `Output RealtimeResponseCreateAudioOutputOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice RealtimeResponseCreateAudioOutputOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Alloy RealtimeResponseCreateAudioOutputOutputVoiceString2 = "alloy"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ash RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ash"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ballad RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ballad"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Coral RealtimeResponseCreateAudioOutputOutputVoiceString2 = "coral"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Echo RealtimeResponseCreateAudioOutputOutputVoiceString2 = "echo"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Sage RealtimeResponseCreateAudioOutputOutputVoiceString2 = "sage"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Shimmer RealtimeResponseCreateAudioOutputOutputVoiceString2 = "shimmer"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Verse RealtimeResponseCreateAudioOutputOutputVoiceString2 = "verse"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Marin RealtimeResponseCreateAudioOutputOutputVoiceString2 = "marin"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Cedar RealtimeResponseCreateAudioOutputOutputVoiceString2 = "cedar"` + + - `RealtimeResponseCreateAudioOutputOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Conversation RealtimeResponseCreateParamsConversation` + + Controls which conversation the response is added to. Currently supports + `auto` and `none`, with `auto` as the default value. The `auto` value + means that the contents of the response will be added to the default + conversation. Set this to `none` to create an out-of-band response which + will not add items to default conversation. + + - `string` + + - `RealtimeResponseCreateParamsConversation` + + - `const RealtimeResponseCreateParamsConversationAuto RealtimeResponseCreateParamsConversation = "auto"` + + - `const RealtimeResponseCreateParamsConversationNone RealtimeResponseCreateParamsConversation = "none"` + + - `Input []ConversationItemUnion` + + Input items to include in the prompt for the model. Using this field + creates a new context for this Response instead of using the default + conversation. An empty array `[]` will clear the context for this Response. + Note that this can include references to items that previously appeared in the session + using their id. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeResponseCreateParamsMaxOutputTokensUnionResp` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Metadata Metadata` + + Set of 16 key-value pairs that can be attached to an object. This can be + useful for storing additional information about the object in a structured + format, and querying for objects via API or the dashboard. + + Keys are strings with a maximum length of 64 characters. Values are strings + with a maximum length of 512 characters. + + - `OutputModalities []string` + + The set of modalities the model used to respond, currently the only possible values are + `[\"audio\"]`, `[\"text\"]`. Audio output always include a text transcript. Setting the + output to mode `text` will disable audio output from the model. + + - `const RealtimeResponseCreateParamsOutputModalityText RealtimeResponseCreateParamsOutputModality = "text"` + + - `const RealtimeResponseCreateParamsOutputModalityAudio RealtimeResponseCreateParamsOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeResponseCreateParamsToolChoiceUnionResp` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools []RealtimeResponseCreateParamsToolUnionResp` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `type RealtimeResponseCreateMcpTool struct{…}` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeResponseCreateMcpToolAllowedToolsUnion` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeResponseCreateMcpToolAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID RealtimeResponseCreateMcpToolConnectorID` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorDropbox RealtimeResponseCreateMcpToolConnectorID = "connector_dropbox"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGmail RealtimeResponseCreateMcpToolConnectorID = "connector_gmail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGooglecalendar RealtimeResponseCreateMcpToolConnectorID = "connector_googlecalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGoogledrive RealtimeResponseCreateMcpToolConnectorID = "connector_googledrive"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorMicrosoftteams RealtimeResponseCreateMcpToolConnectorID = "connector_microsoftteams"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookcalendar RealtimeResponseCreateMcpToolConnectorID = "connector_outlookcalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookemail RealtimeResponseCreateMcpToolConnectorID = "connector_outlookemail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorSharepoint RealtimeResponseCreateMcpToolConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeResponseCreateMcpToolRequireApprovalUnion` + + Specify which of the MCP server's tools require approval. + + - `RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `type SessionUpdateEvent struct{…}` + + Send this event to update the session’s configuration. + The client may send this event at any time to update any field + except for `voice` and `model`. `voice` can be updated only if there have been no other audio outputs yet. + + When the server receives a `session.update`, it will respond + with a `session.updated` event showing the full, effective configuration. + Only the fields that are present in the `session.update` are updated. To clear a field like + `instructions`, pass an empty string. To clear a field like `tools`, pass an empty array. + To clear a field like `turn_detection`, pass `null`. + + - `Session SessionUpdateEventSessionUnion` + + Update the Realtime session. Choose either a realtime + session or a transcription session. + + - `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeAudioConfig` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateRequestModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionCreateRequestModel` + + - `const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime1_5 RealtimeSessionCreateRequestModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2 RealtimeSessionCreateRequestModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateRequestModelGPTAudio1_5 RealtimeSessionCreateRequestModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"` + + - `const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `ToolChoice RealtimeToolChoiceConfigUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `Tools RealtimeToolsConfig` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeTracingConfigUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + + - `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type Transcription` + + The type of session to create. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionAudio` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Type SessionUpdate` + + The event type, must be `session.update`. + + - `const SessionUpdateSessionUpdate SessionUpdate = "session.update"` + + - `EventID string` + + Optional client-generated ID used to identify this event. This is an arbitrary string that a client may assign. It will be passed back if there is an error with the event, but the corresponding `session.updated` event will not include it. + +### Realtime Conversation Item Assistant Message + +- `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + +### Realtime Conversation Item Function Call + +- `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + +### Realtime Conversation Item Function Call Output + +- `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + +### Realtime Conversation Item System Message + +- `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + +### Realtime Conversation Item User Message + +- `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + +### Realtime Error + +- `type RealtimeError struct{…}` + + Details of the error. + + - `Message string` + + A human-readable error message. + + - `Type string` + + The type of error (e.g., "invalid_request_error", "server_error"). + + - `Code string` + + Error code, if any. + + - `EventID string` + + The event_id of the client event that caused the error, if applicable. + + - `Param string` + + Parameter related to the error, if any. + +### Realtime Error Event + +- `type RealtimeErrorEvent struct{…}` + + Returned when an error occurs, which could be a client problem or a server + problem. Most errors are recoverable and the session will stay open, we + recommend to implementors to monitor and log error messages by default. + + - `Error RealtimeError` + + Details of the error. + + - `Message string` + + A human-readable error message. + + - `Type string` + + The type of error (e.g., "invalid_request_error", "server_error"). + + - `Code string` + + Error code, if any. + + - `EventID string` + + The event_id of the client event that caused the error, if applicable. + + - `Param string` + + Parameter related to the error, if any. + + - `EventID string` + + The unique ID of the server event. + + - `Type Error` + + The event type, must be `error`. + + - `const ErrorError Error = "error"` + +### Realtime Function Tool + +- `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + +### Realtime Mcp Approval Request + +- `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + +### Realtime Mcp Approval Response + +- `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + +### Realtime Mcp List Tools + +- `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + +### Realtime Mcp Protocol Error + +- `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + +### Realtime Mcp Tool Call + +- `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + +### Realtime Mcp Tool Execution Error + +- `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + +### Realtime Mcphttp Error + +- `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + +### Realtime Reasoning + +- `type RealtimeReasoning struct{…}` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + +### Realtime Reasoning Effort + +- `type RealtimeReasoningEffort string` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + +### Realtime Response + +- `type RealtimeResponse struct{…}` + + The response resource. + + - `ID string` + + The unique ID of the response, will look like `resp_1234`. + + - `Audio RealtimeResponseAudio` + + Configuration for audio output. + + - `Output RealtimeResponseAudioOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice string` + + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, + `shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for + best quality. + + - `string` + + - `string` + + - `const RealtimeResponseAudioOutputVoiceAlloy RealtimeResponseAudioOutputVoice = "alloy"` + + - `const RealtimeResponseAudioOutputVoiceAsh RealtimeResponseAudioOutputVoice = "ash"` + + - `const RealtimeResponseAudioOutputVoiceBallad RealtimeResponseAudioOutputVoice = "ballad"` + + - `const RealtimeResponseAudioOutputVoiceCoral RealtimeResponseAudioOutputVoice = "coral"` + + - `const RealtimeResponseAudioOutputVoiceEcho RealtimeResponseAudioOutputVoice = "echo"` + + - `const RealtimeResponseAudioOutputVoiceSage RealtimeResponseAudioOutputVoice = "sage"` + + - `const RealtimeResponseAudioOutputVoiceShimmer RealtimeResponseAudioOutputVoice = "shimmer"` + + - `const RealtimeResponseAudioOutputVoiceVerse RealtimeResponseAudioOutputVoice = "verse"` + + - `const RealtimeResponseAudioOutputVoiceMarin RealtimeResponseAudioOutputVoice = "marin"` + + - `const RealtimeResponseAudioOutputVoiceCedar RealtimeResponseAudioOutputVoice = "cedar"` + + - `ConversationID string` + + Which conversation the response is added to, determined by the `conversation` + field in the `response.create` event. If `auto`, the response will be added to + the default conversation and the value of `conversation_id` will be an id like + `conv_1234`. If `none`, the response will not be added to any conversation and + the value of `conversation_id` will be `null`. If responses are being triggered + automatically by VAD the response will be added to the default conversation + + - `MaxOutputTokens RealtimeResponseMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls, that was used in this response. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Metadata Metadata` + + Set of 16 key-value pairs that can be attached to an object. This can be + useful for storing additional information about the object in a structured + format, and querying for objects via API or the dashboard. + + Keys are strings with a maximum length of 64 characters. Values are strings + with a maximum length of 512 characters. + + - `Object RealtimeResponseObject` + + The object type, must be `realtime.response`. + + - `const RealtimeResponseObjectRealtimeResponse RealtimeResponseObject = "realtime.response"` + + - `Output []ConversationItemUnion` + + The list of output items generated by the response. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `OutputModalities []string` + + The set of modalities the model used to respond, currently the only possible values are + `[\"audio\"]`, `[\"text\"]`. Audio output always include a text transcript. Setting the + output to mode `text` will disable audio output from the model. + + - `const RealtimeResponseOutputModalityText RealtimeResponseOutputModality = "text"` + + - `const RealtimeResponseOutputModalityAudio RealtimeResponseOutputModality = "audio"` + + - `Status RealtimeResponseStatus` + + The final status of the response (`completed`, `cancelled`, `failed`, or + `incomplete`, `in_progress`). + + - `const RealtimeResponseStatusCompleted RealtimeResponseStatus = "completed"` + + - `const RealtimeResponseStatusCancelled RealtimeResponseStatus = "cancelled"` + + - `const RealtimeResponseStatusFailed RealtimeResponseStatus = "failed"` + + - `const RealtimeResponseStatusIncomplete RealtimeResponseStatus = "incomplete"` + + - `const RealtimeResponseStatusInProgress RealtimeResponseStatus = "in_progress"` + + - `StatusDetails RealtimeResponseStatus` + + Additional details about the status. + + - `Error RealtimeResponseStatusError` + + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + + - `Code string` + + Error code, if any. + + - `Type string` + + The type of error. + + - `Reason RealtimeResponseStatusReason` + + The reason the Response did not complete. For a `cancelled` Response, one of `turn_detected` (the server VAD detected a new start of speech) or `client_cancelled` (the client sent a cancel event). For an `incomplete` Response, one of `max_output_tokens` or `content_filter` (the server-side safety filter activated and cut off the response). + + - `const RealtimeResponseStatusReasonTurnDetected RealtimeResponseStatusReason = "turn_detected"` + + - `const RealtimeResponseStatusReasonClientCancelled RealtimeResponseStatusReason = "client_cancelled"` + + - `const RealtimeResponseStatusReasonMaxOutputTokens RealtimeResponseStatusReason = "max_output_tokens"` + + - `const RealtimeResponseStatusReasonContentFilter RealtimeResponseStatusReason = "content_filter"` + + - `Type RealtimeResponseStatusType` + + The type of error that caused the response to fail, corresponding + with the `status` field (`completed`, `cancelled`, `incomplete`, + `failed`). + + - `const RealtimeResponseStatusTypeCompleted RealtimeResponseStatusType = "completed"` + + - `const RealtimeResponseStatusTypeCancelled RealtimeResponseStatusType = "cancelled"` + + - `const RealtimeResponseStatusTypeIncomplete RealtimeResponseStatusType = "incomplete"` + + - `const RealtimeResponseStatusTypeFailed RealtimeResponseStatusType = "failed"` + + - `Usage RealtimeResponseUsage` + + Usage statistics for the Response, this will correspond to billing. A + Realtime API session will maintain a conversation context and append new + Items to the Conversation, thus output from previous turns (text and + audio tokens) will become the input for later turns. + + - `InputTokenDetails RealtimeResponseUsageInputTokenDetails` + + Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens. + + - `AudioTokens int64` + + The number of audio tokens used as input for the Response. + + - `CachedTokens int64` + + The number of cached tokens used as input for the Response. + + - `CachedTokensDetails RealtimeResponseUsageInputTokenDetailsCachedTokensDetails` + + Details about the cached tokens used as input for the Response. + + - `AudioTokens int64` + + The number of cached audio tokens used as input for the Response. + + - `ImageTokens int64` + + The number of cached image tokens used as input for the Response. + + - `TextTokens int64` + + The number of cached text tokens used as input for the Response. + + - `ImageTokens int64` + + The number of image tokens used as input for the Response. + + - `TextTokens int64` + + The number of text tokens used as input for the Response. + + - `InputTokens int64` + + The number of input tokens used in the Response, including text and + audio tokens. + + - `OutputTokenDetails RealtimeResponseUsageOutputTokenDetails` + + Details about the output tokens used in the Response. + + - `AudioTokens int64` + + The number of audio tokens used in the Response. + + - `TextTokens int64` + + The number of text tokens used in the Response. + + - `OutputTokens int64` + + The number of output tokens sent in the Response, including text and + audio tokens. + + - `TotalTokens int64` + + The total number of tokens in the Response including input and output + text and audio tokens. + +### Realtime Response Create Audio Output + +- `type RealtimeResponseCreateAudioOutput struct{…}` + + Configuration for audio input and output. + + - `Output RealtimeResponseCreateAudioOutputOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice RealtimeResponseCreateAudioOutputOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Alloy RealtimeResponseCreateAudioOutputOutputVoiceString2 = "alloy"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ash RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ash"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ballad RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ballad"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Coral RealtimeResponseCreateAudioOutputOutputVoiceString2 = "coral"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Echo RealtimeResponseCreateAudioOutputOutputVoiceString2 = "echo"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Sage RealtimeResponseCreateAudioOutputOutputVoiceString2 = "sage"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Shimmer RealtimeResponseCreateAudioOutputOutputVoiceString2 = "shimmer"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Verse RealtimeResponseCreateAudioOutputOutputVoiceString2 = "verse"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Marin RealtimeResponseCreateAudioOutputOutputVoiceString2 = "marin"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Cedar RealtimeResponseCreateAudioOutputOutputVoiceString2 = "cedar"` + + - `RealtimeResponseCreateAudioOutputOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + +### Realtime Response Create Mcp Tool + +- `type RealtimeResponseCreateMcpTool struct{…}` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeResponseCreateMcpToolAllowedToolsUnion` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeResponseCreateMcpToolAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID RealtimeResponseCreateMcpToolConnectorID` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorDropbox RealtimeResponseCreateMcpToolConnectorID = "connector_dropbox"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGmail RealtimeResponseCreateMcpToolConnectorID = "connector_gmail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGooglecalendar RealtimeResponseCreateMcpToolConnectorID = "connector_googlecalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGoogledrive RealtimeResponseCreateMcpToolConnectorID = "connector_googledrive"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorMicrosoftteams RealtimeResponseCreateMcpToolConnectorID = "connector_microsoftteams"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookcalendar RealtimeResponseCreateMcpToolConnectorID = "connector_outlookcalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookemail RealtimeResponseCreateMcpToolConnectorID = "connector_outlookemail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorSharepoint RealtimeResponseCreateMcpToolConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeResponseCreateMcpToolRequireApprovalUnion` + + Specify which of the MCP server's tools require approval. + + - `RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + +### Realtime Response Create Params + +- `type RealtimeResponseCreateParamsResp struct{…}` + + Create a new Realtime response with these parameters + + - `Audio RealtimeResponseCreateAudioOutput` + + Configuration for audio input and output. + + - `Output RealtimeResponseCreateAudioOutputOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice RealtimeResponseCreateAudioOutputOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Alloy RealtimeResponseCreateAudioOutputOutputVoiceString2 = "alloy"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ash RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ash"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ballad RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ballad"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Coral RealtimeResponseCreateAudioOutputOutputVoiceString2 = "coral"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Echo RealtimeResponseCreateAudioOutputOutputVoiceString2 = "echo"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Sage RealtimeResponseCreateAudioOutputOutputVoiceString2 = "sage"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Shimmer RealtimeResponseCreateAudioOutputOutputVoiceString2 = "shimmer"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Verse RealtimeResponseCreateAudioOutputOutputVoiceString2 = "verse"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Marin RealtimeResponseCreateAudioOutputOutputVoiceString2 = "marin"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Cedar RealtimeResponseCreateAudioOutputOutputVoiceString2 = "cedar"` + + - `RealtimeResponseCreateAudioOutputOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Conversation RealtimeResponseCreateParamsConversation` + + Controls which conversation the response is added to. Currently supports + `auto` and `none`, with `auto` as the default value. The `auto` value + means that the contents of the response will be added to the default + conversation. Set this to `none` to create an out-of-band response which + will not add items to default conversation. + + - `string` + + - `RealtimeResponseCreateParamsConversation` + + - `const RealtimeResponseCreateParamsConversationAuto RealtimeResponseCreateParamsConversation = "auto"` + + - `const RealtimeResponseCreateParamsConversationNone RealtimeResponseCreateParamsConversation = "none"` + + - `Input []ConversationItemUnion` + + Input items to include in the prompt for the model. Using this field + creates a new context for this Response instead of using the default + conversation. An empty array `[]` will clear the context for this Response. + Note that this can include references to items that previously appeared in the session + using their id. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeResponseCreateParamsMaxOutputTokensUnionResp` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Metadata Metadata` + + Set of 16 key-value pairs that can be attached to an object. This can be + useful for storing additional information about the object in a structured + format, and querying for objects via API or the dashboard. + + Keys are strings with a maximum length of 64 characters. Values are strings + with a maximum length of 512 characters. + + - `OutputModalities []string` + + The set of modalities the model used to respond, currently the only possible values are + `[\"audio\"]`, `[\"text\"]`. Audio output always include a text transcript. Setting the + output to mode `text` will disable audio output from the model. + + - `const RealtimeResponseCreateParamsOutputModalityText RealtimeResponseCreateParamsOutputModality = "text"` + + - `const RealtimeResponseCreateParamsOutputModalityAudio RealtimeResponseCreateParamsOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeResponseCreateParamsToolChoiceUnionResp` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools []RealtimeResponseCreateParamsToolUnionResp` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `type RealtimeResponseCreateMcpTool struct{…}` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeResponseCreateMcpToolAllowedToolsUnion` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeResponseCreateMcpToolAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID RealtimeResponseCreateMcpToolConnectorID` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorDropbox RealtimeResponseCreateMcpToolConnectorID = "connector_dropbox"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGmail RealtimeResponseCreateMcpToolConnectorID = "connector_gmail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGooglecalendar RealtimeResponseCreateMcpToolConnectorID = "connector_googlecalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGoogledrive RealtimeResponseCreateMcpToolConnectorID = "connector_googledrive"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorMicrosoftteams RealtimeResponseCreateMcpToolConnectorID = "connector_microsoftteams"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookcalendar RealtimeResponseCreateMcpToolConnectorID = "connector_outlookcalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookemail RealtimeResponseCreateMcpToolConnectorID = "connector_outlookemail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorSharepoint RealtimeResponseCreateMcpToolConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeResponseCreateMcpToolRequireApprovalUnion` + + Specify which of the MCP server's tools require approval. + + - `RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + +### Realtime Response Status + +- `type RealtimeResponseStatus struct{…}` + + Additional details about the status. + + - `Error RealtimeResponseStatusError` + + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + + - `Code string` + + Error code, if any. + + - `Type string` + + The type of error. + + - `Reason RealtimeResponseStatusReason` + + The reason the Response did not complete. For a `cancelled` Response, one of `turn_detected` (the server VAD detected a new start of speech) or `client_cancelled` (the client sent a cancel event). For an `incomplete` Response, one of `max_output_tokens` or `content_filter` (the server-side safety filter activated and cut off the response). + + - `const RealtimeResponseStatusReasonTurnDetected RealtimeResponseStatusReason = "turn_detected"` + + - `const RealtimeResponseStatusReasonClientCancelled RealtimeResponseStatusReason = "client_cancelled"` + + - `const RealtimeResponseStatusReasonMaxOutputTokens RealtimeResponseStatusReason = "max_output_tokens"` + + - `const RealtimeResponseStatusReasonContentFilter RealtimeResponseStatusReason = "content_filter"` + + - `Type RealtimeResponseStatusType` + + The type of error that caused the response to fail, corresponding + with the `status` field (`completed`, `cancelled`, `incomplete`, + `failed`). + + - `const RealtimeResponseStatusTypeCompleted RealtimeResponseStatusType = "completed"` + + - `const RealtimeResponseStatusTypeCancelled RealtimeResponseStatusType = "cancelled"` + + - `const RealtimeResponseStatusTypeIncomplete RealtimeResponseStatusType = "incomplete"` + + - `const RealtimeResponseStatusTypeFailed RealtimeResponseStatusType = "failed"` + +### Realtime Response Usage + +- `type RealtimeResponseUsage struct{…}` + + Usage statistics for the Response, this will correspond to billing. A + Realtime API session will maintain a conversation context and append new + Items to the Conversation, thus output from previous turns (text and + audio tokens) will become the input for later turns. + + - `InputTokenDetails RealtimeResponseUsageInputTokenDetails` + + Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens. + + - `AudioTokens int64` + + The number of audio tokens used as input for the Response. + + - `CachedTokens int64` + + The number of cached tokens used as input for the Response. + + - `CachedTokensDetails RealtimeResponseUsageInputTokenDetailsCachedTokensDetails` + + Details about the cached tokens used as input for the Response. + + - `AudioTokens int64` + + The number of cached audio tokens used as input for the Response. + + - `ImageTokens int64` + + The number of cached image tokens used as input for the Response. + + - `TextTokens int64` + + The number of cached text tokens used as input for the Response. + + - `ImageTokens int64` + + The number of image tokens used as input for the Response. + + - `TextTokens int64` + + The number of text tokens used as input for the Response. + + - `InputTokens int64` + + The number of input tokens used in the Response, including text and + audio tokens. + + - `OutputTokenDetails RealtimeResponseUsageOutputTokenDetails` + + Details about the output tokens used in the Response. + + - `AudioTokens int64` + + The number of audio tokens used in the Response. + + - `TextTokens int64` + + The number of text tokens used in the Response. + + - `OutputTokens int64` + + The number of output tokens sent in the Response, including text and + audio tokens. + + - `TotalTokens int64` + + The total number of tokens in the Response including input and output + text and audio tokens. + +### Realtime Response Usage Input Token Details + +- `type RealtimeResponseUsageInputTokenDetails struct{…}` + + Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens. + + - `AudioTokens int64` + + The number of audio tokens used as input for the Response. + + - `CachedTokens int64` + + The number of cached tokens used as input for the Response. + + - `CachedTokensDetails RealtimeResponseUsageInputTokenDetailsCachedTokensDetails` + + Details about the cached tokens used as input for the Response. + + - `AudioTokens int64` + + The number of cached audio tokens used as input for the Response. + + - `ImageTokens int64` + + The number of cached image tokens used as input for the Response. + + - `TextTokens int64` + + The number of cached text tokens used as input for the Response. + + - `ImageTokens int64` + + The number of image tokens used as input for the Response. + + - `TextTokens int64` + + The number of text tokens used as input for the Response. + +### Realtime Response Usage Output Token Details + +- `type RealtimeResponseUsageOutputTokenDetails struct{…}` + + Details about the output tokens used in the Response. + + - `AudioTokens int64` + + The number of audio tokens used in the Response. + + - `TextTokens int64` + + The number of text tokens used in the Response. + +### Realtime Server Event + +- `type RealtimeServerEventUnion interface{…}` + + A realtime server event. + + - `type ConversationCreatedEvent struct{…}` + + Returned when a conversation is created. Emitted right after session creation. + + - `Conversation ConversationCreatedEventConversation` + + The conversation resource. + + - `ID string` + + The unique ID of the conversation. + + - `Object string` + + The object type, must be `realtime.conversation`. + + - `const ConversationCreatedEventConversationObjectRealtimeConversation ConversationCreatedEventConversationObject = "realtime.conversation"` + + - `EventID string` + + The unique ID of the server event. + + - `Type ConversationCreated` + + The event type, must be `conversation.created`. + + - `const ConversationCreatedConversationCreated ConversationCreated = "conversation.created"` + + - `type ConversationItemCreatedEvent struct{…}` + + Returned when a conversation item is created. There are several scenarios that produce this event: + + - The server is generating a Response, which if successful will produce + either one or two Items, which will be of type `message` + (role `assistant`) or type `function_call`. + - The input audio buffer has been committed, either by the client or the + server (in `server_vad` mode). The server will take the content of the + input audio buffer and add it to a new user message Item. + - The client has sent a `conversation.item.create` event to add a new Item + to the Conversation. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Type ConversationItemCreated` + + The event type, must be `conversation.item.created`. + + - `const ConversationItemCreatedConversationItemCreated ConversationItemCreated = "conversation.item.created"` + + - `PreviousItemID string` + + The ID of the preceding item in the Conversation context, allows the + client to understand the order of the conversation. Can be `null` if the + item has no predecessor. + + - `type ConversationItemDeletedEvent struct{…}` + + Returned when an item in the conversation is deleted by the client with a + `conversation.item.delete` event. This event is used to synchronize the + server's understanding of the conversation history with the client's view. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item that was deleted. + + - `Type ConversationItemDeleted` + + The event type, must be `conversation.item.deleted`. + + - `const ConversationItemDeletedConversationItemDeleted ConversationItemDeleted = "conversation.item.deleted"` + + - `type ConversationItemInputAudioTranscriptionCompletedEvent struct{…}` + + This event is the output of audio transcription for user audio written to the + user audio buffer. Transcription begins when the input audio buffer is + committed by the client or server (when VAD is enabled). Transcription runs + asynchronously with Response creation, so this event may come before or after + the Response events. + + Realtime API models accept audio natively, and thus input transcription is a + separate process run on a separate ASR (Automatic Speech Recognition) model. + The transcript may diverge somewhat from the model's interpretation, and + should be treated as a rough guide. + + - `ContentIndex int64` + + The index of the content part containing the audio. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item containing the audio that is being transcribed. + + - `Transcript string` + + The transcribed text. + + - `Type ConversationItemInputAudioTranscriptionCompleted` + + The event type, must be + `conversation.item.input_audio_transcription.completed`. + + - `const ConversationItemInputAudioTranscriptionCompletedConversationItemInputAudioTranscriptionCompleted ConversationItemInputAudioTranscriptionCompleted = "conversation.item.input_audio_transcription.completed"` + + - `Usage ConversationItemInputAudioTranscriptionCompletedEventUsageUnion` + + Usage statistics for the transcription, this is billed according to the ASR model's pricing rather than the realtime model's pricing. + + - `ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokens` + + - `InputTokens int64` + + Number of input tokens billed for this request. + + - `OutputTokens int64` + + Number of output tokens generated. + + - `TotalTokens int64` + + Total number of tokens used (input + output). + + - `Type Tokens` + + The type of the usage object. Always `tokens` for this variant. + + - `const TokensTokens Tokens = "tokens"` + + - `InputTokenDetails ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageTokensInputTokenDetails` + + Details about the input tokens billed for this request. + + - `AudioTokens int64` + + Number of audio tokens billed for this request. + + - `TextTokens int64` + + Number of text tokens billed for this request. + + - `ConversationItemInputAudioTranscriptionCompletedEventUsageTranscriptTextUsageDuration` + + - `Seconds float64` + + Duration of the input audio in seconds. + + - `Type Duration` + + The type of the usage object. Always `duration` for this variant. + + - `const DurationDuration Duration = "duration"` + + - `Logprobs []LogProbProperties` + + The log probabilities of the transcription. + + - `Token string` + + The token that was used to generate the log probability. + + - `Bytes []int64` + + The bytes that were used to generate the log probability. + + - `Logprob float64` + + The log probability of the token. + + - `type ConversationItemInputAudioTranscriptionDeltaEvent struct{…}` + + Returned when the text value of an input audio transcription content part is updated with incremental transcription results. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item containing the audio that is being transcribed. + + - `Type ConversationItemInputAudioTranscriptionDelta` + + The event type, must be `conversation.item.input_audio_transcription.delta`. + + - `const ConversationItemInputAudioTranscriptionDeltaConversationItemInputAudioTranscriptionDelta ConversationItemInputAudioTranscriptionDelta = "conversation.item.input_audio_transcription.delta"` + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + The text delta. + + - `Logprobs []LogProbProperties` + + The log probabilities of the transcription. These can be enabled by configurating the session with `"include": ["item.input_audio_transcription.logprobs"]`. Each entry in the array corresponds a log probability of which token would be selected for this chunk of transcription. This can help to identify if it was possible there were multiple valid options for a given chunk of transcription. + + - `Token string` + + The token that was used to generate the log probability. + + - `Bytes []int64` + + The bytes that were used to generate the log probability. + + - `Logprob float64` + + The log probability of the token. + + - `type ConversationItemInputAudioTranscriptionFailedEvent struct{…}` + + Returned when input audio transcription is configured, and a transcription + request for a user message failed. These events are separate from other + `error` events so that the client can identify the related Item. + + - `ContentIndex int64` + + The index of the content part containing the audio. + + - `Error ConversationItemInputAudioTranscriptionFailedEventError` + + Details of the transcription error. + + - `Code string` + + Error code, if any. + + - `Message string` + + A human-readable error message. + + - `Param string` + + Parameter related to the error, if any. + + - `Type string` + + The type of error. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item. + + - `Type ConversationItemInputAudioTranscriptionFailed` + + The event type, must be + `conversation.item.input_audio_transcription.failed`. + + - `const ConversationItemInputAudioTranscriptionFailedConversationItemInputAudioTranscriptionFailed ConversationItemInputAudioTranscriptionFailed = "conversation.item.input_audio_transcription.failed"` + + - `RealtimeServerEventConversationItemRetrieved` + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `Type ConversationItemRetrieved` + + The event type, must be `conversation.item.retrieved`. + + - `const ConversationItemRetrievedConversationItemRetrieved ConversationItemRetrieved = "conversation.item.retrieved"` + + - `type ConversationItemTruncatedEvent struct{…}` + + Returned when an earlier assistant audio message item is truncated by the + client with a `conversation.item.truncate` event. This event is used to + synchronize the server's understanding of the audio with the client's playback. + + This action will truncate the audio and remove the server-side text transcript + to ensure there is no text in the context that hasn't been heard by the user. + + - `AudioEndMs int64` + + The duration up to which the audio was truncated, in milliseconds. + + - `ContentIndex int64` + + The index of the content part that was truncated. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the assistant message item that was truncated. + + - `Type ConversationItemTruncated` + + The event type, must be `conversation.item.truncated`. + + - `const ConversationItemTruncatedConversationItemTruncated ConversationItemTruncated = "conversation.item.truncated"` + + - `type RealtimeErrorEvent struct{…}` + + Returned when an error occurs, which could be a client problem or a server + problem. Most errors are recoverable and the session will stay open, we + recommend to implementors to monitor and log error messages by default. + + - `Error RealtimeError` + + Details of the error. + + - `Message string` + + A human-readable error message. + + - `Type string` + + The type of error (e.g., "invalid_request_error", "server_error"). + + - `Code string` + + Error code, if any. + + - `EventID string` + + The event_id of the client event that caused the error, if applicable. + + - `Param string` + + Parameter related to the error, if any. + + - `EventID string` + + The unique ID of the server event. + + - `Type Error` + + The event type, must be `error`. + + - `const ErrorError Error = "error"` + + - `type InputAudioBufferClearedEvent struct{…}` + + Returned when the input audio buffer is cleared by the client with a + `input_audio_buffer.clear` event. + + - `EventID string` + + The unique ID of the server event. + + - `Type InputAudioBufferCleared` + + The event type, must be `input_audio_buffer.cleared`. + + - `const InputAudioBufferClearedInputAudioBufferCleared InputAudioBufferCleared = "input_audio_buffer.cleared"` + + - `type InputAudioBufferCommittedEvent struct{…}` + + Returned when an input audio buffer is committed, either by the client or + automatically in server VAD mode. The `item_id` property is the ID of the user + message item that will be created, thus a `conversation.item.created` event + will also be sent to the client. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item that will be created. + + - `Type InputAudioBufferCommitted` + + The event type, must be `input_audio_buffer.committed`. + + - `const InputAudioBufferCommittedInputAudioBufferCommitted InputAudioBufferCommitted = "input_audio_buffer.committed"` + + - `PreviousItemID string` + + The ID of the preceding item after which the new item will be inserted. + Can be `null` if the item has no predecessor. + + - `type InputAudioBufferDtmfEventReceivedEvent struct{…}` + + **SIP Only:** Returned when an DTMF event is received. A DTMF event is a message that + represents a telephone keypad press (0–9, *, #, A–D). The `event` property + is the keypad that the user press. The `received_at` is the UTC Unix Timestamp + that the server received the event. + + - `Event string` + + The telephone keypad that was pressed by the user. + + - `ReceivedAt int64` + + UTC Unix Timestamp when DTMF Event was received by server. + + - `Type InputAudioBufferDtmfEventReceived` + + The event type, must be `input_audio_buffer.dtmf_event_received`. + + - `const InputAudioBufferDtmfEventReceivedInputAudioBufferDtmfEventReceived InputAudioBufferDtmfEventReceived = "input_audio_buffer.dtmf_event_received"` + + - `type InputAudioBufferSpeechStartedEvent struct{…}` + + Sent by the server when in `server_vad` mode to indicate that speech has been + detected in the audio buffer. This can happen any time audio is added to the + buffer (unless speech is already detected). The client may want to use this + event to interrupt audio playback or provide visual feedback to the user. + + The client should expect to receive a `input_audio_buffer.speech_stopped` event + when speech stops. The `item_id` property is the ID of the user message item + that will be created when speech stops and will also be included in the + `input_audio_buffer.speech_stopped` event (unless the client manually commits + the audio buffer during VAD activation). + + - `AudioStartMs int64` + + Milliseconds from the start of all audio written to the buffer during the + session when speech was first detected. This will correspond to the + beginning of audio sent to the model, and thus includes the + `prefix_padding_ms` configured in the Session. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item that will be created when speech stops. + + - `Type InputAudioBufferSpeechStarted` + + The event type, must be `input_audio_buffer.speech_started`. + + - `const InputAudioBufferSpeechStartedInputAudioBufferSpeechStarted InputAudioBufferSpeechStarted = "input_audio_buffer.speech_started"` + + - `type InputAudioBufferSpeechStoppedEvent struct{…}` + + Returned in `server_vad` mode when the server detects the end of speech in + the audio buffer. The server will also send an `conversation.item.created` + event with the user message item that is created from the audio buffer. + + - `AudioEndMs int64` + + Milliseconds since the session started when speech stopped. This will + correspond to the end of audio sent to the model, and thus includes the + `min_silence_duration_ms` configured in the Session. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the user message item that will be created. + + - `Type InputAudioBufferSpeechStopped` + + The event type, must be `input_audio_buffer.speech_stopped`. + + - `const InputAudioBufferSpeechStoppedInputAudioBufferSpeechStopped InputAudioBufferSpeechStopped = "input_audio_buffer.speech_stopped"` + + - `type RateLimitsUpdatedEvent struct{…}` + + Emitted at the beginning of a Response to indicate the updated rate limits. + When a Response is created some tokens will be "reserved" for the output + tokens, the rate limits shown here reflect that reservation, which is then + adjusted accordingly once the Response is completed. + + - `EventID string` + + The unique ID of the server event. + + - `RateLimits []RateLimitsUpdatedEventRateLimit` + + List of rate limit information. + + - `Limit int64` + + The maximum allowed value for the rate limit. + + - `Name string` + + The name of the rate limit (`requests`, `tokens`). + + - `const RateLimitsUpdatedEventRateLimitNameRequests RateLimitsUpdatedEventRateLimitName = "requests"` + + - `const RateLimitsUpdatedEventRateLimitNameTokens RateLimitsUpdatedEventRateLimitName = "tokens"` + + - `Remaining int64` + + The remaining value before the limit is reached. + + - `ResetSeconds float64` + + Seconds until the rate limit resets. + + - `Type RateLimitsUpdated` + + The event type, must be `rate_limits.updated`. + + - `const RateLimitsUpdatedRateLimitsUpdated RateLimitsUpdated = "rate_limits.updated"` + + - `type ResponseAudioDeltaEvent struct{…}` + + Returned when the model-generated audio is updated. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + Base64-encoded audio data delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputAudioDelta` + + The event type, must be `response.output_audio.delta`. + + - `const ResponseOutputAudioDeltaResponseOutputAudioDelta ResponseOutputAudioDelta = "response.output_audio.delta"` + + - `type ResponseAudioDoneEvent struct{…}` + + Returned when the model-generated audio is done. Also emitted when a Response + is interrupted, incomplete, or cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputAudioDone` + + The event type, must be `response.output_audio.done`. + + - `const ResponseOutputAudioDoneResponseOutputAudioDone ResponseOutputAudioDone = "response.output_audio.done"` + + - `type ResponseAudioTranscriptDeltaEvent struct{…}` + + Returned when the model-generated transcription of audio output is updated. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + The transcript delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputAudioTranscriptDelta` + + The event type, must be `response.output_audio_transcript.delta`. + + - `const ResponseOutputAudioTranscriptDeltaResponseOutputAudioTranscriptDelta ResponseOutputAudioTranscriptDelta = "response.output_audio_transcript.delta"` + + - `type ResponseAudioTranscriptDoneEvent struct{…}` + + Returned when the model-generated transcription of audio output is done + streaming. Also emitted when a Response is interrupted, incomplete, or + cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Transcript string` + + The final transcript of the audio. + + - `Type ResponseOutputAudioTranscriptDone` + + The event type, must be `response.output_audio_transcript.done`. + + - `const ResponseOutputAudioTranscriptDoneResponseOutputAudioTranscriptDone ResponseOutputAudioTranscriptDone = "response.output_audio_transcript.done"` + + - `type ResponseContentPartAddedEvent struct{…}` + + Returned when a new content part is added to an assistant message item during + response generation. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item to which the content part was added. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Part ResponseContentPartAddedEventPart` + + The content part that was added. + + - `Audio string` + + Base64-encoded audio data (if type is "audio"). + + - `Text string` + + The text content (if type is "text"). + + - `Transcript string` + + The transcript of the audio (if type is "audio"). + + - `Type string` + + The content type ("text", "audio"). + + - `const ResponseContentPartAddedEventPartTypeText ResponseContentPartAddedEventPartType = "text"` + + - `const ResponseContentPartAddedEventPartTypeAudio ResponseContentPartAddedEventPartType = "audio"` + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseContentPartAdded` + + The event type, must be `response.content_part.added`. + + - `const ResponseContentPartAddedResponseContentPartAdded ResponseContentPartAdded = "response.content_part.added"` + + - `type ResponseContentPartDoneEvent struct{…}` + + Returned when a content part is done streaming in an assistant message item. + Also emitted when a Response is interrupted, incomplete, or cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Part ResponseContentPartDoneEventPart` + + The content part that is done. + + - `Audio string` + + Base64-encoded audio data (if type is "audio"). + + - `Text string` + + The text content (if type is "text"). + + - `Transcript string` + + The transcript of the audio (if type is "audio"). + + - `Type string` + + The content type ("text", "audio"). + + - `const ResponseContentPartDoneEventPartTypeText ResponseContentPartDoneEventPartType = "text"` + + - `const ResponseContentPartDoneEventPartTypeAudio ResponseContentPartDoneEventPartType = "audio"` + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseContentPartDone` + + The event type, must be `response.content_part.done`. + + - `const ResponseContentPartDoneResponseContentPartDone ResponseContentPartDone = "response.content_part.done"` + + - `type ResponseCreatedEvent struct{…}` + + Returned when a new Response is created. The first event of response creation, + where the response is in an initial state of `in_progress`. + + - `EventID string` + + The unique ID of the server event. + + - `Response RealtimeResponse` + + The response resource. + + - `ID string` + + The unique ID of the response, will look like `resp_1234`. + + - `Audio RealtimeResponseAudio` + + Configuration for audio output. + + - `Output RealtimeResponseAudioOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice string` + + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, + `shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for + best quality. + + - `string` + + - `string` + + - `const RealtimeResponseAudioOutputVoiceAlloy RealtimeResponseAudioOutputVoice = "alloy"` + + - `const RealtimeResponseAudioOutputVoiceAsh RealtimeResponseAudioOutputVoice = "ash"` + + - `const RealtimeResponseAudioOutputVoiceBallad RealtimeResponseAudioOutputVoice = "ballad"` + + - `const RealtimeResponseAudioOutputVoiceCoral RealtimeResponseAudioOutputVoice = "coral"` + + - `const RealtimeResponseAudioOutputVoiceEcho RealtimeResponseAudioOutputVoice = "echo"` + + - `const RealtimeResponseAudioOutputVoiceSage RealtimeResponseAudioOutputVoice = "sage"` + + - `const RealtimeResponseAudioOutputVoiceShimmer RealtimeResponseAudioOutputVoice = "shimmer"` + + - `const RealtimeResponseAudioOutputVoiceVerse RealtimeResponseAudioOutputVoice = "verse"` + + - `const RealtimeResponseAudioOutputVoiceMarin RealtimeResponseAudioOutputVoice = "marin"` + + - `const RealtimeResponseAudioOutputVoiceCedar RealtimeResponseAudioOutputVoice = "cedar"` + + - `ConversationID string` + + Which conversation the response is added to, determined by the `conversation` + field in the `response.create` event. If `auto`, the response will be added to + the default conversation and the value of `conversation_id` will be an id like + `conv_1234`. If `none`, the response will not be added to any conversation and + the value of `conversation_id` will be `null`. If responses are being triggered + automatically by VAD the response will be added to the default conversation + + - `MaxOutputTokens RealtimeResponseMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls, that was used in this response. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Metadata Metadata` + + Set of 16 key-value pairs that can be attached to an object. This can be + useful for storing additional information about the object in a structured + format, and querying for objects via API or the dashboard. + + Keys are strings with a maximum length of 64 characters. Values are strings + with a maximum length of 512 characters. + + - `Object RealtimeResponseObject` + + The object type, must be `realtime.response`. + + - `const RealtimeResponseObjectRealtimeResponse RealtimeResponseObject = "realtime.response"` + + - `Output []ConversationItemUnion` + + The list of output items generated by the response. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `OutputModalities []string` + + The set of modalities the model used to respond, currently the only possible values are + `[\"audio\"]`, `[\"text\"]`. Audio output always include a text transcript. Setting the + output to mode `text` will disable audio output from the model. + + - `const RealtimeResponseOutputModalityText RealtimeResponseOutputModality = "text"` + + - `const RealtimeResponseOutputModalityAudio RealtimeResponseOutputModality = "audio"` + + - `Status RealtimeResponseStatus` + + The final status of the response (`completed`, `cancelled`, `failed`, or + `incomplete`, `in_progress`). + + - `const RealtimeResponseStatusCompleted RealtimeResponseStatus = "completed"` + + - `const RealtimeResponseStatusCancelled RealtimeResponseStatus = "cancelled"` + + - `const RealtimeResponseStatusFailed RealtimeResponseStatus = "failed"` + + - `const RealtimeResponseStatusIncomplete RealtimeResponseStatus = "incomplete"` + + - `const RealtimeResponseStatusInProgress RealtimeResponseStatus = "in_progress"` + + - `StatusDetails RealtimeResponseStatus` + + Additional details about the status. + + - `Error RealtimeResponseStatusError` + + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + + - `Code string` + + Error code, if any. + + - `Type string` + + The type of error. + + - `Reason RealtimeResponseStatusReason` + + The reason the Response did not complete. For a `cancelled` Response, one of `turn_detected` (the server VAD detected a new start of speech) or `client_cancelled` (the client sent a cancel event). For an `incomplete` Response, one of `max_output_tokens` or `content_filter` (the server-side safety filter activated and cut off the response). + + - `const RealtimeResponseStatusReasonTurnDetected RealtimeResponseStatusReason = "turn_detected"` + + - `const RealtimeResponseStatusReasonClientCancelled RealtimeResponseStatusReason = "client_cancelled"` + + - `const RealtimeResponseStatusReasonMaxOutputTokens RealtimeResponseStatusReason = "max_output_tokens"` + + - `const RealtimeResponseStatusReasonContentFilter RealtimeResponseStatusReason = "content_filter"` + + - `Type RealtimeResponseStatusType` + + The type of error that caused the response to fail, corresponding + with the `status` field (`completed`, `cancelled`, `incomplete`, + `failed`). + + - `const RealtimeResponseStatusTypeCompleted RealtimeResponseStatusType = "completed"` + + - `const RealtimeResponseStatusTypeCancelled RealtimeResponseStatusType = "cancelled"` + + - `const RealtimeResponseStatusTypeIncomplete RealtimeResponseStatusType = "incomplete"` + + - `const RealtimeResponseStatusTypeFailed RealtimeResponseStatusType = "failed"` + + - `Usage RealtimeResponseUsage` + + Usage statistics for the Response, this will correspond to billing. A + Realtime API session will maintain a conversation context and append new + Items to the Conversation, thus output from previous turns (text and + audio tokens) will become the input for later turns. + + - `InputTokenDetails RealtimeResponseUsageInputTokenDetails` + + Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens. + + - `AudioTokens int64` + + The number of audio tokens used as input for the Response. + + - `CachedTokens int64` + + The number of cached tokens used as input for the Response. + + - `CachedTokensDetails RealtimeResponseUsageInputTokenDetailsCachedTokensDetails` + + Details about the cached tokens used as input for the Response. + + - `AudioTokens int64` + + The number of cached audio tokens used as input for the Response. + + - `ImageTokens int64` + + The number of cached image tokens used as input for the Response. + + - `TextTokens int64` + + The number of cached text tokens used as input for the Response. + + - `ImageTokens int64` + + The number of image tokens used as input for the Response. + + - `TextTokens int64` + + The number of text tokens used as input for the Response. + + - `InputTokens int64` + + The number of input tokens used in the Response, including text and + audio tokens. + + - `OutputTokenDetails RealtimeResponseUsageOutputTokenDetails` + + Details about the output tokens used in the Response. + + - `AudioTokens int64` + + The number of audio tokens used in the Response. + + - `TextTokens int64` + + The number of text tokens used in the Response. + + - `OutputTokens int64` + + The number of output tokens sent in the Response, including text and + audio tokens. + + - `TotalTokens int64` + + The total number of tokens in the Response including input and output + text and audio tokens. + + - `Type ResponseCreated` + + The event type, must be `response.created`. + + - `const ResponseCreatedResponseCreated ResponseCreated = "response.created"` + + - `type ResponseDoneEvent struct{…}` + + Returned when a Response is done streaming. Always emitted, no matter the + final state. The Response object included in the `response.done` event will + include all output Items in the Response but will omit the raw audio data. + + Clients should check the `status` field of the Response to determine if it was successful + (`completed`) or if there was another outcome: `cancelled`, `failed`, or `incomplete`. + + A response will contain all output items that were generated during the response, excluding + any audio content. + + - `EventID string` + + The unique ID of the server event. + + - `Response RealtimeResponse` + + The response resource. + + - `Type ResponseDone` + + The event type, must be `response.done`. + + - `const ResponseDoneResponseDone ResponseDone = "response.done"` + + - `type ResponseFunctionCallArgumentsDeltaEvent struct{…}` + + Returned when the model-generated function call arguments are updated. + + - `CallID string` + + The ID of the function call. + + - `Delta string` + + The arguments delta as a JSON string. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the function call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseFunctionCallArgumentsDelta` + + The event type, must be `response.function_call_arguments.delta`. + + - `const ResponseFunctionCallArgumentsDeltaResponseFunctionCallArgumentsDelta ResponseFunctionCallArgumentsDelta = "response.function_call_arguments.delta"` + + - `type ResponseFunctionCallArgumentsDoneEvent struct{…}` + + Returned when the model-generated function call arguments are done streaming. + Also emitted when a Response is interrupted, incomplete, or cancelled. + + - `Arguments string` + + The final arguments as a JSON string. + + - `CallID string` + + The ID of the function call. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the function call item. + + - `Name string` + + The name of the function that was called. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseFunctionCallArgumentsDone` + + The event type, must be `response.function_call_arguments.done`. + + - `const ResponseFunctionCallArgumentsDoneResponseFunctionCallArgumentsDone ResponseFunctionCallArgumentsDone = "response.function_call_arguments.done"` + + - `type ResponseOutputItemAddedEvent struct{…}` + + Returned when a new Item is created during Response generation. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `OutputIndex int64` + + The index of the output item in the Response. + + - `ResponseID string` + + The ID of the Response to which the item belongs. + + - `Type ResponseOutputItemAdded` + + The event type, must be `response.output_item.added`. + + - `const ResponseOutputItemAddedResponseOutputItemAdded ResponseOutputItemAdded = "response.output_item.added"` + + - `type ResponseOutputItemDoneEvent struct{…}` + + Returned when an Item is done streaming. Also emitted when a Response is + interrupted, incomplete, or cancelled. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `OutputIndex int64` + + The index of the output item in the Response. + + - `ResponseID string` + + The ID of the Response to which the item belongs. + + - `Type ResponseOutputItemDone` + + The event type, must be `response.output_item.done`. + + - `const ResponseOutputItemDoneResponseOutputItemDone ResponseOutputItemDone = "response.output_item.done"` + + - `type ResponseTextDeltaEvent struct{…}` + + Returned when the text value of an "output_text" content part is updated. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + The text delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputTextDelta` + + The event type, must be `response.output_text.delta`. + + - `const ResponseOutputTextDeltaResponseOutputTextDelta ResponseOutputTextDelta = "response.output_text.delta"` + + - `type ResponseTextDoneEvent struct{…}` + + Returned when the text value of an "output_text" content part is done streaming. Also + emitted when a Response is interrupted, incomplete, or cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Text string` + + The final text content. + + - `Type ResponseOutputTextDone` + + The event type, must be `response.output_text.done`. + + - `const ResponseOutputTextDoneResponseOutputTextDone ResponseOutputTextDone = "response.output_text.done"` + + - `type SessionCreatedEvent struct{…}` + + Returned when a Session is created. Emitted automatically when a new + connection is established as the first server event. This event will contain + the default Session configuration. + + - `EventID string` + + The unique ID of the server event. + + - `Session SessionCreatedEventSessionUnion` + + The session configuration. + + - `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeAudioConfig` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateRequestModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionCreateRequestModel` + + - `const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime1_5 RealtimeSessionCreateRequestModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2 RealtimeSessionCreateRequestModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateRequestModelGPTAudio1_5 RealtimeSessionCreateRequestModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"` + + - `const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeToolChoiceConfigUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools RealtimeToolsConfig` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeTracingConfigUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + + - `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type Transcription` + + The type of session to create. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionAudio` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Type SessionCreated` + + The event type, must be `session.created`. + + - `const SessionCreatedSessionCreated SessionCreated = "session.created"` + + - `type SessionUpdatedEvent struct{…}` + + Returned when a session is updated with a `session.update` event, unless + there is an error. + + - `EventID string` + + The unique ID of the server event. + + - `Session SessionUpdatedEventSessionUnion` + + The session configuration. + + - `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type SessionUpdated` + + The event type, must be `session.updated`. + + - `const SessionUpdatedSessionUpdated SessionUpdated = "session.updated"` + + - `RealtimeServerEventOutputAudioBufferStarted` + + - `EventID string` + + The unique ID of the server event. + + - `ResponseID string` + + The unique ID of the response that produced the audio. + + - `Type OutputAudioBufferStarted` + + The event type, must be `output_audio_buffer.started`. + + - `const OutputAudioBufferStartedOutputAudioBufferStarted OutputAudioBufferStarted = "output_audio_buffer.started"` + + - `RealtimeServerEventOutputAudioBufferStopped` + + - `EventID string` + + The unique ID of the server event. + + - `ResponseID string` + + The unique ID of the response that produced the audio. + + - `Type OutputAudioBufferStopped` + + The event type, must be `output_audio_buffer.stopped`. + + - `const OutputAudioBufferStoppedOutputAudioBufferStopped OutputAudioBufferStopped = "output_audio_buffer.stopped"` + + - `RealtimeServerEventOutputAudioBufferCleared` + + - `EventID string` + + The unique ID of the server event. + + - `ResponseID string` + + The unique ID of the response that produced the audio. + + - `Type OutputAudioBufferCleared` + + The event type, must be `output_audio_buffer.cleared`. + + - `const OutputAudioBufferClearedOutputAudioBufferCleared OutputAudioBufferCleared = "output_audio_buffer.cleared"` + + - `type ConversationItemAdded struct{…}` + + Sent by the server when an Item is added to the default Conversation. This can happen in several cases: + + - When the client sends a `conversation.item.create` event. + - When the input audio buffer is committed. In this case the item will be a user message containing the audio from the buffer. + - When the model is generating a Response. In this case the `conversation.item.added` event will be sent when the model starts generating a specific Item, and thus it will not yet have any content (and `status` will be `in_progress`). + + The event will include the full content of the Item (except when model is generating a Response) except for audio data, which can be retrieved separately with a `conversation.item.retrieve` event if necessary. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `Type ConversationItemAdded` + + The event type, must be `conversation.item.added`. + + - `const ConversationItemAddedConversationItemAdded ConversationItemAdded = "conversation.item.added"` + + - `PreviousItemID string` + + The ID of the item that precedes this one, if any. This is used to + maintain ordering when items are inserted. + + - `type ConversationItemDone struct{…}` + + Returned when a conversation item is finalized. + + The event will include the full content of the Item except for audio data, which can be retrieved separately with a `conversation.item.retrieve` event if needed. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `Type ConversationItemDone` + + The event type, must be `conversation.item.done`. + + - `const ConversationItemDoneConversationItemDone ConversationItemDone = "conversation.item.done"` + + - `PreviousItemID string` + + The ID of the item that precedes this one, if any. This is used to + maintain ordering when items are inserted. + + - `type InputAudioBufferTimeoutTriggered struct{…}` + + Returned when the Server VAD timeout is triggered for the input audio buffer. This is configured + with `idle_timeout_ms` in the `turn_detection` settings of the session, and it indicates that + there hasn't been any speech detected for the configured duration. + + The `audio_start_ms` and `audio_end_ms` fields indicate the segment of audio after the last + model response up to the triggering time, as an offset from the beginning of audio written + to the input audio buffer. This means it demarcates the segment of audio that was silent and + the difference between the start and end values will roughly match the configured timeout. + + The empty audio will be committed to the conversation as an `input_audio` item (there will be a + `input_audio_buffer.committed` event) and a model response will be generated. There may be speech + that didn't trigger VAD but is still detected by the model, so the model may respond with + something relevant to the conversation or a prompt to continue speaking. + + - `AudioEndMs int64` + + Millisecond offset of audio written to the input audio buffer at the time the timeout was triggered. + + - `AudioStartMs int64` + + Millisecond offset of audio written to the input audio buffer that was after the playback time of the last model response. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item associated with this segment. + + - `Type InputAudioBufferTimeoutTriggered` + + The event type, must be `input_audio_buffer.timeout_triggered`. + + - `const InputAudioBufferTimeoutTriggeredInputAudioBufferTimeoutTriggered InputAudioBufferTimeoutTriggered = "input_audio_buffer.timeout_triggered"` + + - `type ConversationItemInputAudioTranscriptionSegment struct{…}` + + Returned when an input audio transcription segment is identified for an item. + + - `ID string` + + The segment identifier. + + - `ContentIndex int64` + + The index of the input audio content part within the item. + + - `End float64` + + End time of the segment in seconds. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item containing the input audio content. + + - `Speaker string` + + The detected speaker label for this segment. + + - `Start float64` + + Start time of the segment in seconds. + + - `Text string` + + The text for this segment. + + - `Type ConversationItemInputAudioTranscriptionSegment` + + The event type, must be `conversation.item.input_audio_transcription.segment`. + + - `const ConversationItemInputAudioTranscriptionSegmentConversationItemInputAudioTranscriptionSegment ConversationItemInputAudioTranscriptionSegment = "conversation.item.input_audio_transcription.segment"` + + - `type McpListToolsInProgress struct{…}` + + Returned when listing MCP tools is in progress for an item. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP list tools item. + + - `Type McpListToolsInProgress` + + The event type, must be `mcp_list_tools.in_progress`. + + - `const McpListToolsInProgressMcpListToolsInProgress McpListToolsInProgress = "mcp_list_tools.in_progress"` + + - `type McpListToolsCompleted struct{…}` + + Returned when listing MCP tools has completed for an item. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP list tools item. + + - `Type McpListToolsCompleted` + + The event type, must be `mcp_list_tools.completed`. + + - `const McpListToolsCompletedMcpListToolsCompleted McpListToolsCompleted = "mcp_list_tools.completed"` + + - `type McpListToolsFailed struct{…}` + + Returned when listing MCP tools has failed for an item. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP list tools item. + + - `Type McpListToolsFailed` + + The event type, must be `mcp_list_tools.failed`. + + - `const McpListToolsFailedMcpListToolsFailed McpListToolsFailed = "mcp_list_tools.failed"` + + - `type ResponseMcpCallArgumentsDelta struct{…}` + + Returned when MCP tool call arguments are updated during response generation. + + - `Delta string` + + The JSON-encoded arguments delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseMcpCallArgumentsDelta` + + The event type, must be `response.mcp_call_arguments.delta`. + + - `const ResponseMcpCallArgumentsDeltaResponseMcpCallArgumentsDelta ResponseMcpCallArgumentsDelta = "response.mcp_call_arguments.delta"` + + - `Obfuscation string` + + If present, indicates the delta text was obfuscated. + + - `type ResponseMcpCallArgumentsDone struct{…}` + + Returned when MCP tool call arguments are finalized during response generation. + + - `Arguments string` + + The final JSON-encoded arguments string. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseMcpCallArgumentsDone` + + The event type, must be `response.mcp_call_arguments.done`. + + - `const ResponseMcpCallArgumentsDoneResponseMcpCallArgumentsDone ResponseMcpCallArgumentsDone = "response.mcp_call_arguments.done"` + + - `type ResponseMcpCallInProgress struct{…}` + + Returned when an MCP tool call has started and is in progress. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Type ResponseMcpCallInProgress` + + The event type, must be `response.mcp_call.in_progress`. + + - `const ResponseMcpCallInProgressResponseMcpCallInProgress ResponseMcpCallInProgress = "response.mcp_call.in_progress"` + + - `type ResponseMcpCallCompleted struct{…}` + + Returned when an MCP tool call has completed successfully. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Type ResponseMcpCallCompleted` + + The event type, must be `response.mcp_call.completed`. + + - `const ResponseMcpCallCompletedResponseMcpCallCompleted ResponseMcpCallCompleted = "response.mcp_call.completed"` + + - `type ResponseMcpCallFailed struct{…}` + + Returned when an MCP tool call has failed. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Type ResponseMcpCallFailed` + + The event type, must be `response.mcp_call.failed`. + + - `const ResponseMcpCallFailedResponseMcpCallFailed ResponseMcpCallFailed = "response.mcp_call.failed"` + +### Realtime Session + +- `type RealtimeSession struct{…}` + + Realtime session object for the beta interface. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Include []string` + + Additional fields to include in server outputs. + + - `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionInclude = "item.input_audio_transcription.logprobs"` + + - `InputAudioFormat RealtimeSessionInputAudioFormat` + + The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + For `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, + single channel (mono), and little-endian byte order. + + - `const RealtimeSessionInputAudioFormatPcm16 RealtimeSessionInputAudioFormat = "pcm16"` + + - `const RealtimeSessionInputAudioFormatG711Ulaw RealtimeSessionInputAudioFormat = "g711_ulaw"` + + - `const RealtimeSessionInputAudioFormatG711Alaw RealtimeSessionInputAudioFormat = "g711_alaw"` + + - `InputAudioNoiseReduction RealtimeSessionInputAudioNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `InputAudioTranscription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model + calls. This field allows the client to guide the model on desired + responses. The model can be instructed on response content and format, + (e.g. "be extremely succinct", "act friendly", "here are examples of good + responses") and on audio behavior (e.g. "talk quickly", "inject emotion + into your voice", "laugh frequently"). The instructions are not + guaranteed to be followed by the model, but they provide guidance to the + model on the desired behavior. + + Note that the server sets default instructions which will be used if this + field is not set and are visible in the `session.created` event at the + start of the session. + + - `MaxResponseOutputTokens RealtimeSessionMaxResponseOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Modalities []string` + + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + + - `const RealtimeSessionModalityText RealtimeSessionModality = "text"` + + - `const RealtimeSessionModalityAudio RealtimeSessionModality = "audio"` + + - `Model RealtimeSessionModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionModel` + + - `const RealtimeSessionModelGPTRealtime RealtimeSessionModel = "gpt-realtime"` + + - `const RealtimeSessionModelGPTRealtime1_5 RealtimeSessionModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionModelGPTRealtime2025_08_28 RealtimeSessionModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionModelGPT4oRealtimePreview RealtimeSessionModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionModelGPT4oRealtimePreview2024_10_01 RealtimeSessionModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionModelGPT4oRealtimePreview2024_12_17 RealtimeSessionModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionModelGPT4oRealtimePreview2025_06_03 RealtimeSessionModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionModelGPT4oMiniRealtimePreview RealtimeSessionModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionModelGPTRealtimeMini RealtimeSessionModel = "gpt-realtime-mini"` + + - `const RealtimeSessionModelGPTRealtimeMini2025_10_06 RealtimeSessionModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionModelGPTRealtimeMini2025_12_15 RealtimeSessionModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionModelGPTAudio1_5 RealtimeSessionModel = "gpt-audio-1.5"` + + - `const RealtimeSessionModelGPTAudioMini RealtimeSessionModel = "gpt-audio-mini"` + + - `const RealtimeSessionModelGPTAudioMini2025_10_06 RealtimeSessionModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionModelGPTAudioMini2025_12_15 RealtimeSessionModel = "gpt-audio-mini-2025-12-15"` + + - `Object RealtimeSessionObject` + + The object type. Always `realtime.session`. + + - `const RealtimeSessionObjectRealtimeSession RealtimeSessionObject = "realtime.session"` + + - `OutputAudioFormat RealtimeSessionOutputAudioFormat` + + The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + For `pcm16`, output audio is sampled at a rate of 24kHz. + + - `const RealtimeSessionOutputAudioFormatPcm16 RealtimeSessionOutputAudioFormat = "pcm16"` + + - `const RealtimeSessionOutputAudioFormatG711Ulaw RealtimeSessionOutputAudioFormat = "g711_ulaw"` + + - `const RealtimeSessionOutputAudioFormatG711Alaw RealtimeSessionOutputAudioFormat = "g711_alaw"` + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Speed float64` + + The speed of the model's spoken response. 1.0 is the default speed. 0.25 is + the minimum speed. 1.5 is the maximum speed. This value can only be changed + in between model turns, not while a response is in progress. + + - `Temperature float64` + + Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance. + + - `ToolChoice string` + + How the model chooses tools. Options are `auto`, `none`, `required`, or + specify a function. + + - `Tools []RealtimeFunctionTool` + + Tools (functions) available to the model. + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `Tracing RealtimeSessionTracingUnion` + + Configuration options for tracing. Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeSessionTracingTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the traces dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the traces dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the traces dashboard. + + - `TurnDetection RealtimeSessionTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeSessionTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeSessionTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeSessionTurnDetectionSemanticVadEagernessLow RealtimeSessionTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeSessionTurnDetectionSemanticVadEagernessMedium RealtimeSessionTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeSessionTurnDetectionSemanticVadEagernessHigh RealtimeSessionTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeSessionTurnDetectionSemanticVadEagernessAuto RealtimeSessionTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Voice RealtimeSessionVoice` + + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, + `shimmer`, and `verse`. + + - `string` + + - `RealtimeSessionVoice` + + - `const RealtimeSessionVoiceAlloy RealtimeSessionVoice = "alloy"` + + - `const RealtimeSessionVoiceAsh RealtimeSessionVoice = "ash"` + + - `const RealtimeSessionVoiceBallad RealtimeSessionVoice = "ballad"` + + - `const RealtimeSessionVoiceCoral RealtimeSessionVoice = "coral"` + + - `const RealtimeSessionVoiceEcho RealtimeSessionVoice = "echo"` + + - `const RealtimeSessionVoiceSage RealtimeSessionVoice = "sage"` + + - `const RealtimeSessionVoiceShimmer RealtimeSessionVoice = "shimmer"` + + - `const RealtimeSessionVoiceVerse RealtimeSessionVoice = "verse"` + + - `const RealtimeSessionVoiceMarin RealtimeSessionVoice = "marin"` + + - `const RealtimeSessionVoiceCedar RealtimeSessionVoice = "cedar"` + +### Realtime Session Create Request + +- `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeAudioConfig` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateRequestModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionCreateRequestModel` + + - `const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime1_5 RealtimeSessionCreateRequestModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2 RealtimeSessionCreateRequestModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateRequestModelGPTAudio1_5 RealtimeSessionCreateRequestModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"` + + - `const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeToolChoiceConfigUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools RealtimeToolsConfig` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeTracingConfigUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + +### Realtime Tool Choice Config + +- `type RealtimeToolChoiceConfigUnion interface{…}` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + +### Realtime Tools Config + +- `type RealtimeToolsConfig []RealtimeToolsConfigUnion` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + +### Realtime Tools Config Union + +- `type RealtimeToolsConfigUnion interface{…}` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + +### Realtime Tracing Config + +- `type RealtimeTracingConfigUnion interface{…}` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + +### Realtime Transcription Session Audio + +- `type RealtimeTranscriptionSessionAudio struct{…}` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + +### Realtime Transcription Session Audio Input + +- `type RealtimeTranscriptionSessionAudioInput struct{…}` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + +### Realtime Transcription Session Audio Input Turn Detection + +- `type RealtimeTranscriptionSessionAudioInputTurnDetectionUnion interface{…}` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + +### Realtime Transcription Session Create Request + +- `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type Transcription` + + The type of session to create. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionAudio` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + +### Realtime Translation Client Event + +- `type RealtimeTranslationClientEventUnion interface{…}` + + A Realtime translation client event. + + - `type RealtimeTranslationSessionUpdateEvent struct{…}` + + Send this event to update the translation session configuration. Translation + sessions support updates to `audio.output.language`, `audio.input.transcription`, + and `audio.input.noise_reduction`. + + - `Session RealtimeTranslationSessionUpdateRequest` + + Translation session fields to update. The session `type` and `model` are set + at creation and cannot be changed with `session.update`. + + - `Audio RealtimeTranslationSessionUpdateRequestAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionUpdateRequestAudioInput` + + - `NoiseReduction RealtimeTranslationSessionUpdateRequestAudioInputNoiseReduction` + + Optional input noise reduction. Set to `null` to disable it. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionUpdateRequestAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model to use for source transcript deltas. + + - `Output RealtimeTranslationSessionUpdateRequestAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `Type SessionUpdate` + + The event type, must be `session.update`. + + - `const SessionUpdateSessionUpdate SessionUpdate = "session.update"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type RealtimeTranslationInputAudioBufferAppendEvent struct{…}` + + Send this event to append audio bytes to the translation session input audio buffer. + + WebSocket translation sessions accept base64-encoded 24 kHz PCM16 mono + little-endian raw audio bytes. Unsupported websocket audio formats return a + validation error because lower-quality audio materially degrades translation + quality. + + Translation consumes 200 ms engine frames. For best realtime behavior, append + audio in 200 ms chunks. If a chunk is shorter, the server buffers it until it + has enough audio for one frame. If a chunk is longer, the server splits it into + 200 ms frames and enqueues them back-to-back. + + Keep appending silence while the session is active. If a client stops sending + audio and later resumes, model time treats the resumed audio as contiguous with + the previous audio rather than as a real-world pause. + + - `Audio string` + + Base64-encoded 24 kHz PCM16 mono audio bytes. + + - `Type SessionInputAudioBufferAppend` + + The event type, must be `session.input_audio_buffer.append`. + + - `const SessionInputAudioBufferAppendSessionInputAudioBufferAppend SessionInputAudioBufferAppend = "session.input_audio_buffer.append"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `type RealtimeTranslationSessionCloseEvent struct{…}` + + Gracefully close the realtime translation session. The server flushes pending + input audio and emits any remaining translated output before closing the + session. + + - `Type SessionClose` + + The event type, must be `session.close`. + + - `const SessionCloseSessionClose SessionClose = "session.close"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Realtime Translation Client Secret Create Request + +- `type RealtimeTranslationClientSecretCreateRequest struct{…}` + + Create a translation session and client secret for the Realtime API. + + - `Session RealtimeTranslationSessionCreateRequest` + + Realtime translation session configuration. Translation sessions stream source + audio in and translated audio plus transcript deltas out continuously. + + - `Model string` + + The Realtime translation model used for this session. + + - `Audio RealtimeTranslationSessionCreateRequestAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionCreateRequestAudioInput` + + - `NoiseReduction RealtimeTranslationSessionCreateRequestAudioInputNoiseReduction` + + Optional input noise reduction. Set to `null` to disable it. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionCreateRequestAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model to use for source transcript deltas. + + - `Output RealtimeTranslationSessionCreateRequestAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `ExpiresAfter RealtimeTranslationClientSecretCreateRequestExpiresAfter` + + Configuration for the client secret expiration. Expiration refers to the time after which + a client secret will no longer be valid for creating sessions. The session itself may + continue after that time once started. A secret can be used to create multiple sessions + until it expires. + + - `Anchor string` + + The anchor point for the client secret expiration, meaning that `seconds` will be added to the `created_at` time of the client secret to produce an expiration timestamp. Only `created_at` is currently supported. + + - `const RealtimeTranslationClientSecretCreateRequestExpiresAfterAnchorCreatedAt RealtimeTranslationClientSecretCreateRequestExpiresAfterAnchor = "created_at"` + + - `Seconds int64` + + The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200` (2 hours). This default to 600 seconds (10 minutes) if not specified. + +### Realtime Translation Client Secret Create Response + +- `type RealtimeTranslationClientSecretCreateResponse struct{…}` + + Response from creating a translation session and client secret for the Realtime API. + + - `ExpiresAt int64` + + Expiration timestamp for the client secret, in seconds since epoch. + + - `Session RealtimeTranslationSession` + + A Realtime translation session. Translation sessions continuously translate input + audio into the configured output language. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Audio RealtimeTranslationSessionAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionAudioInput` + + - `NoiseReduction RealtimeTranslationSessionAudioInputNoiseReduction` + + Optional input noise reduction. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model used for source transcript deltas. + + - `Output RealtimeTranslationSessionAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Model string` + + The Realtime translation model used for this session. This field is set at + session creation and cannot be changed with `session.update`. + + - `Type Translation` + + The session type. Always `translation` for Realtime translation sessions. + + - `const TranslationTranslation Translation = "translation"` + + - `Value string` + + The generated client secret value. + +### Realtime Translation Input Audio Buffer Append Event + +- `type RealtimeTranslationInputAudioBufferAppendEvent struct{…}` + + Send this event to append audio bytes to the translation session input audio buffer. + + WebSocket translation sessions accept base64-encoded 24 kHz PCM16 mono + little-endian raw audio bytes. Unsupported websocket audio formats return a + validation error because lower-quality audio materially degrades translation + quality. + + Translation consumes 200 ms engine frames. For best realtime behavior, append + audio in 200 ms chunks. If a chunk is shorter, the server buffers it until it + has enough audio for one frame. If a chunk is longer, the server splits it into + 200 ms frames and enqueues them back-to-back. + + Keep appending silence while the session is active. If a client stops sending + audio and later resumes, model time treats the resumed audio as contiguous with + the previous audio rather than as a real-world pause. + + - `Audio string` + + Base64-encoded 24 kHz PCM16 mono audio bytes. + + - `Type SessionInputAudioBufferAppend` + + The event type, must be `session.input_audio_buffer.append`. + + - `const SessionInputAudioBufferAppendSessionInputAudioBufferAppend SessionInputAudioBufferAppend = "session.input_audio_buffer.append"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Realtime Translation Input Transcript Delta Event + +- `type RealtimeTranslationInputTranscriptDeltaEvent struct{…}` + + Returned when optional source-language transcript text is available. This event + is emitted only when `audio.input.transcription` is configured. + + Transcript deltas are append-only text fragments. Clients should not insert + unconditional spaces between deltas. + + - `Delta string` + + Append-only source-language transcript text. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionInputTranscriptDelta` + + The event type, must be `session.input_transcript.delta`. + + - `const SessionInputTranscriptDeltaSessionInputTranscriptDelta SessionInputTranscriptDelta = "session.input_transcript.delta"` + + - `ElapsedMs int64` + + Timing metadata for stream alignment, derived from the translation frame + when available. It advances in 200 ms increments, but multiple transcript + deltas may share the same `elapsed_ms`. Treat it as alignment metadata, + not a unique transcript-delta identifier. + +### Realtime Translation Output Audio Delta Event + +- `type RealtimeTranslationOutputAudioDeltaEvent struct{…}` + + Returned when translated output audio is available. Output audio deltas are + 200 ms frames of PCM16 audio. + + - `Delta string` + + Base64-encoded translated audio data. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionOutputAudioDelta` + + The event type, must be `session.output_audio.delta`. + + - `const SessionOutputAudioDeltaSessionOutputAudioDelta SessionOutputAudioDelta = "session.output_audio.delta"` + + - `Channels int64` + + Number of audio channels. + + - `ElapsedMs int64` + + Timing metadata for stream alignment, derived from the translation frame + when available. Treat `elapsed_ms` as alignment metadata, not a unique + event identifier. + + - `Format RealtimeTranslationOutputAudioDeltaEventFormat` + + Audio encoding for `delta`. + + - `const RealtimeTranslationOutputAudioDeltaEventFormatPcm16 RealtimeTranslationOutputAudioDeltaEventFormat = "pcm16"` + + - `SampleRate int64` + + Sample rate of the audio delta. + +### Realtime Translation Output Transcript Delta Event + +- `type RealtimeTranslationOutputTranscriptDeltaEvent struct{…}` + + Returned when translated transcript text is available. + + Transcript deltas are append-only text fragments. Clients should not insert + unconditional spaces between deltas. + + - `Delta string` + + Append-only transcript text for the translated output audio. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionOutputTranscriptDelta` + + The event type, must be `session.output_transcript.delta`. + + - `const SessionOutputTranscriptDeltaSessionOutputTranscriptDelta SessionOutputTranscriptDelta = "session.output_transcript.delta"` + + - `ElapsedMs int64` + + Timing metadata for stream alignment, derived from the translation frame + when available. It advances in 200 ms increments, but multiple transcript + deltas may share the same `elapsed_ms`. Treat it as alignment metadata, + not a unique transcript-delta identifier. + +### Realtime Translation Server Event + +- `type RealtimeTranslationServerEventUnion interface{…}` + + A Realtime translation server event. + + - `type RealtimeErrorEvent struct{…}` + + Returned when an error occurs, which could be a client problem or a server + problem. Most errors are recoverable and the session will stay open, we + recommend to implementors to monitor and log error messages by default. + + - `Error RealtimeError` + + Details of the error. + + - `Message string` + + A human-readable error message. + + - `Type string` + + The type of error (e.g., "invalid_request_error", "server_error"). + + - `Code string` + + Error code, if any. + + - `EventID string` + + The event_id of the client event that caused the error, if applicable. + + - `Param string` + + Parameter related to the error, if any. + + - `EventID string` + + The unique ID of the server event. + + - `Type Error` + + The event type, must be `error`. + + - `const ErrorError Error = "error"` + + - `type RealtimeTranslationSessionCreatedEvent struct{…}` + + Returned when a translation session is created. Emitted automatically when a + new connection is established as the first server event. This event contains + the default translation session configuration. + + - `EventID string` + + The unique ID of the server event. + + - `Session RealtimeTranslationSession` + + The translation session configuration. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Audio RealtimeTranslationSessionAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionAudioInput` + + - `NoiseReduction RealtimeTranslationSessionAudioInputNoiseReduction` + + Optional input noise reduction. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model used for source transcript deltas. + + - `Output RealtimeTranslationSessionAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Model string` + + The Realtime translation model used for this session. This field is set at + session creation and cannot be changed with `session.update`. + + - `Type Translation` + + The session type. Always `translation` for Realtime translation sessions. + + - `const TranslationTranslation Translation = "translation"` + + - `Type SessionCreated` + + The event type, must be `session.created`. + + - `const SessionCreatedSessionCreated SessionCreated = "session.created"` + + - `type RealtimeTranslationSessionUpdatedEvent struct{…}` + + Returned when a translation session is updated with a `session.update` event, + unless there is an error. + + - `EventID string` + + The unique ID of the server event. + + - `Session RealtimeTranslationSession` + + The translation session configuration. + + - `Type SessionUpdated` + + The event type, must be `session.updated`. + + - `const SessionUpdatedSessionUpdated SessionUpdated = "session.updated"` + + - `type RealtimeTranslationSessionClosedEvent struct{…}` + + Returned when a realtime translation session is closed. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionClosed` + + The event type, must be `session.closed`. + + - `const SessionClosedSessionClosed SessionClosed = "session.closed"` + + - `type RealtimeTranslationInputTranscriptDeltaEvent struct{…}` + + Returned when optional source-language transcript text is available. This event + is emitted only when `audio.input.transcription` is configured. + + Transcript deltas are append-only text fragments. Clients should not insert + unconditional spaces between deltas. + + - `Delta string` + + Append-only source-language transcript text. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionInputTranscriptDelta` + + The event type, must be `session.input_transcript.delta`. + + - `const SessionInputTranscriptDeltaSessionInputTranscriptDelta SessionInputTranscriptDelta = "session.input_transcript.delta"` + + - `ElapsedMs int64` + + Timing metadata for stream alignment, derived from the translation frame + when available. It advances in 200 ms increments, but multiple transcript + deltas may share the same `elapsed_ms`. Treat it as alignment metadata, + not a unique transcript-delta identifier. + + - `type RealtimeTranslationOutputTranscriptDeltaEvent struct{…}` + + Returned when translated transcript text is available. + + Transcript deltas are append-only text fragments. Clients should not insert + unconditional spaces between deltas. + + - `Delta string` + + Append-only transcript text for the translated output audio. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionOutputTranscriptDelta` + + The event type, must be `session.output_transcript.delta`. + + - `const SessionOutputTranscriptDeltaSessionOutputTranscriptDelta SessionOutputTranscriptDelta = "session.output_transcript.delta"` + + - `ElapsedMs int64` + + Timing metadata for stream alignment, derived from the translation frame + when available. It advances in 200 ms increments, but multiple transcript + deltas may share the same `elapsed_ms`. Treat it as alignment metadata, + not a unique transcript-delta identifier. + + - `type RealtimeTranslationOutputAudioDeltaEvent struct{…}` + + Returned when translated output audio is available. Output audio deltas are + 200 ms frames of PCM16 audio. + + - `Delta string` + + Base64-encoded translated audio data. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionOutputAudioDelta` + + The event type, must be `session.output_audio.delta`. + + - `const SessionOutputAudioDeltaSessionOutputAudioDelta SessionOutputAudioDelta = "session.output_audio.delta"` + + - `Channels int64` + + Number of audio channels. + + - `ElapsedMs int64` + + Timing metadata for stream alignment, derived from the translation frame + when available. Treat `elapsed_ms` as alignment metadata, not a unique + event identifier. + + - `Format RealtimeTranslationOutputAudioDeltaEventFormat` + + Audio encoding for `delta`. + + - `const RealtimeTranslationOutputAudioDeltaEventFormatPcm16 RealtimeTranslationOutputAudioDeltaEventFormat = "pcm16"` + + - `SampleRate int64` + + Sample rate of the audio delta. + +### Realtime Translation Session + +- `type RealtimeTranslationSession struct{…}` + + A Realtime translation session. Translation sessions continuously translate input + audio into the configured output language. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Audio RealtimeTranslationSessionAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionAudioInput` + + - `NoiseReduction RealtimeTranslationSessionAudioInputNoiseReduction` + + Optional input noise reduction. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model used for source transcript deltas. + + - `Output RealtimeTranslationSessionAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Model string` + + The Realtime translation model used for this session. This field is set at + session creation and cannot be changed with `session.update`. + + - `Type Translation` + + The session type. Always `translation` for Realtime translation sessions. + + - `const TranslationTranslation Translation = "translation"` + +### Realtime Translation Session Close Event + +- `type RealtimeTranslationSessionCloseEvent struct{…}` + + Gracefully close the realtime translation session. The server flushes pending + input audio and emits any remaining translated output before closing the + session. + + - `Type SessionClose` + + The event type, must be `session.close`. + + - `const SessionCloseSessionClose SessionClose = "session.close"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Realtime Translation Session Closed Event + +- `type RealtimeTranslationSessionClosedEvent struct{…}` + + Returned when a realtime translation session is closed. + + - `EventID string` + + The unique ID of the server event. + + - `Type SessionClosed` + + The event type, must be `session.closed`. + + - `const SessionClosedSessionClosed SessionClosed = "session.closed"` + +### Realtime Translation Session Create Request + +- `type RealtimeTranslationSessionCreateRequest struct{…}` + + Realtime translation session configuration. Translation sessions stream source + audio in and translated audio plus transcript deltas out continuously. + + - `Model string` + + The Realtime translation model used for this session. + + - `Audio RealtimeTranslationSessionCreateRequestAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionCreateRequestAudioInput` + + - `NoiseReduction RealtimeTranslationSessionCreateRequestAudioInputNoiseReduction` + + Optional input noise reduction. Set to `null` to disable it. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionCreateRequestAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model to use for source transcript deltas. + + - `Output RealtimeTranslationSessionCreateRequestAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + +### Realtime Translation Session Created Event + +- `type RealtimeTranslationSessionCreatedEvent struct{…}` + + Returned when a translation session is created. Emitted automatically when a + new connection is established as the first server event. This event contains + the default translation session configuration. + + - `EventID string` + + The unique ID of the server event. + + - `Session RealtimeTranslationSession` + + The translation session configuration. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Audio RealtimeTranslationSessionAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionAudioInput` + + - `NoiseReduction RealtimeTranslationSessionAudioInputNoiseReduction` + + Optional input noise reduction. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model used for source transcript deltas. + + - `Output RealtimeTranslationSessionAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Model string` + + The Realtime translation model used for this session. This field is set at + session creation and cannot be changed with `session.update`. + + - `Type Translation` + + The session type. Always `translation` for Realtime translation sessions. + + - `const TranslationTranslation Translation = "translation"` + + - `Type SessionCreated` + + The event type, must be `session.created`. + + - `const SessionCreatedSessionCreated SessionCreated = "session.created"` + +### Realtime Translation Session Update Event + +- `type RealtimeTranslationSessionUpdateEvent struct{…}` + + Send this event to update the translation session configuration. Translation + sessions support updates to `audio.output.language`, `audio.input.transcription`, + and `audio.input.noise_reduction`. + + - `Session RealtimeTranslationSessionUpdateRequest` + + Translation session fields to update. The session `type` and `model` are set + at creation and cannot be changed with `session.update`. + + - `Audio RealtimeTranslationSessionUpdateRequestAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionUpdateRequestAudioInput` + + - `NoiseReduction RealtimeTranslationSessionUpdateRequestAudioInputNoiseReduction` + + Optional input noise reduction. Set to `null` to disable it. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionUpdateRequestAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model to use for source transcript deltas. + + - `Output RealtimeTranslationSessionUpdateRequestAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `Type SessionUpdate` + + The event type, must be `session.update`. + + - `const SessionUpdateSessionUpdate SessionUpdate = "session.update"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Realtime Translation Session Update Request + +- `type RealtimeTranslationSessionUpdateRequest struct{…}` + + Realtime translation session fields that can be updated with `session.update`. + + - `Audio RealtimeTranslationSessionUpdateRequestAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionUpdateRequestAudioInput` + + - `NoiseReduction RealtimeTranslationSessionUpdateRequestAudioInputNoiseReduction` + + Optional input noise reduction. Set to `null` to disable it. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionUpdateRequestAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model to use for source transcript deltas. + + - `Output RealtimeTranslationSessionUpdateRequestAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + +### Realtime Translation Session Updated Event + +- `type RealtimeTranslationSessionUpdatedEvent struct{…}` + + Returned when a translation session is updated with a `session.update` event, + unless there is an error. + + - `EventID string` + + The unique ID of the server event. + + - `Session RealtimeTranslationSession` + + The translation session configuration. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Audio RealtimeTranslationSessionAudio` + + Configuration for translation input and output audio. + + - `Input RealtimeTranslationSessionAudioInput` + + - `NoiseReduction RealtimeTranslationSessionAudioInputNoiseReduction` + + Optional input noise reduction. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription RealtimeTranslationSessionAudioInputTranscription` + + Optional source-language transcription. When configured, the server emits + `session.input_transcript.delta` events. Translation itself still runs from + the input audio stream. + + - `Model string` + + The transcription model used for source transcript deltas. + + - `Output RealtimeTranslationSessionAudioOutput` + + - `Language string` + + Target language for translated output audio and transcript deltas. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Model string` + + The Realtime translation model used for this session. This field is set at + session creation and cannot be changed with `session.update`. + + - `Type Translation` + + The session type. Always `translation` for Realtime translation sessions. + + - `const TranslationTranslation Translation = "translation"` + + - `Type SessionUpdated` + + The event type, must be `session.updated`. + + - `const SessionUpdatedSessionUpdated SessionUpdated = "session.updated"` + +### Realtime Truncation + +- `type RealtimeTruncationUnion interface{…}` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + +### Realtime Truncation Retention Ratio + +- `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + +### Response Audio Delta Event + +- `type ResponseAudioDeltaEvent struct{…}` + + Returned when the model-generated audio is updated. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + Base64-encoded audio data delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputAudioDelta` + + The event type, must be `response.output_audio.delta`. + + - `const ResponseOutputAudioDeltaResponseOutputAudioDelta ResponseOutputAudioDelta = "response.output_audio.delta"` + +### Response Audio Done Event + +- `type ResponseAudioDoneEvent struct{…}` + + Returned when the model-generated audio is done. Also emitted when a Response + is interrupted, incomplete, or cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputAudioDone` + + The event type, must be `response.output_audio.done`. + + - `const ResponseOutputAudioDoneResponseOutputAudioDone ResponseOutputAudioDone = "response.output_audio.done"` + +### Response Audio Transcript Delta Event + +- `type ResponseAudioTranscriptDeltaEvent struct{…}` + + Returned when the model-generated transcription of audio output is updated. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + The transcript delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputAudioTranscriptDelta` + + The event type, must be `response.output_audio_transcript.delta`. + + - `const ResponseOutputAudioTranscriptDeltaResponseOutputAudioTranscriptDelta ResponseOutputAudioTranscriptDelta = "response.output_audio_transcript.delta"` + +### Response Audio Transcript Done Event + +- `type ResponseAudioTranscriptDoneEvent struct{…}` + + Returned when the model-generated transcription of audio output is done + streaming. Also emitted when a Response is interrupted, incomplete, or + cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Transcript string` + + The final transcript of the audio. + + - `Type ResponseOutputAudioTranscriptDone` + + The event type, must be `response.output_audio_transcript.done`. + + - `const ResponseOutputAudioTranscriptDoneResponseOutputAudioTranscriptDone ResponseOutputAudioTranscriptDone = "response.output_audio_transcript.done"` + +### Response Cancel Event + +- `type ResponseCancelEvent struct{…}` + + Send this event to cancel an in-progress response. The server will respond + with a `response.done` event with a status of `response.status=cancelled`. If + there is no response to cancel, the server will respond with an error. It's safe + to call `response.cancel` even if no response is in progress, an error will be + returned the session will remain unaffected. + + - `Type ResponseCancel` + + The event type, must be `response.cancel`. + + - `const ResponseCancelResponseCancel ResponseCancel = "response.cancel"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `ResponseID string` + + A specific response ID to cancel - if not provided, will cancel an + in-progress response in the default conversation. + +### Response Content Part Added Event + +- `type ResponseContentPartAddedEvent struct{…}` + + Returned when a new content part is added to an assistant message item during + response generation. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item to which the content part was added. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Part ResponseContentPartAddedEventPart` + + The content part that was added. + + - `Audio string` + + Base64-encoded audio data (if type is "audio"). + + - `Text string` + + The text content (if type is "text"). + + - `Transcript string` + + The transcript of the audio (if type is "audio"). + + - `Type string` + + The content type ("text", "audio"). + + - `const ResponseContentPartAddedEventPartTypeText ResponseContentPartAddedEventPartType = "text"` + + - `const ResponseContentPartAddedEventPartTypeAudio ResponseContentPartAddedEventPartType = "audio"` + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseContentPartAdded` + + The event type, must be `response.content_part.added`. + + - `const ResponseContentPartAddedResponseContentPartAdded ResponseContentPartAdded = "response.content_part.added"` + +### Response Content Part Done Event + +- `type ResponseContentPartDoneEvent struct{…}` + + Returned when a content part is done streaming in an assistant message item. + Also emitted when a Response is interrupted, incomplete, or cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Part ResponseContentPartDoneEventPart` + + The content part that is done. + + - `Audio string` + + Base64-encoded audio data (if type is "audio"). + + - `Text string` + + The text content (if type is "text"). + + - `Transcript string` + + The transcript of the audio (if type is "audio"). + + - `Type string` + + The content type ("text", "audio"). + + - `const ResponseContentPartDoneEventPartTypeText ResponseContentPartDoneEventPartType = "text"` + + - `const ResponseContentPartDoneEventPartTypeAudio ResponseContentPartDoneEventPartType = "audio"` + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseContentPartDone` + + The event type, must be `response.content_part.done`. + + - `const ResponseContentPartDoneResponseContentPartDone ResponseContentPartDone = "response.content_part.done"` + +### Response Create Event + +- `type ResponseCreateEvent struct{…}` + + This event instructs the server to create a Response, which means triggering + model inference. When in Server VAD mode, the server will create Responses + automatically. + + A Response will include at least one Item, and may have two, in which case + the second will be a function call. These Items will be appended to the + conversation history by default. + + The server will respond with a `response.created` event, events for Items + and content created, and finally a `response.done` event to indicate the + Response is complete. + + The `response.create` event includes inference configuration like + `instructions` and `tools`. If these are set, they will override the Session's + configuration for this Response only. + + Responses can be created out-of-band of the default Conversation, meaning that they can + have arbitrary input, and it's possible to disable writing the output to the Conversation. + Only one Response can write to the default Conversation at a time, but otherwise multiple + Responses can be created in parallel. The `metadata` field is a good way to disambiguate + multiple simultaneous Responses. + + Clients can set `conversation` to `none` to create a Response that does not write to the default + Conversation. Arbitrary input can be provided with the `input` field, which is an array accepting + raw Items and references to existing Items. + + - `Type ResponseCreate` + + The event type, must be `response.create`. + + - `const ResponseCreateResponseCreate ResponseCreate = "response.create"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + + - `Response RealtimeResponseCreateParamsResp` + + Create a new Realtime response with these parameters + + - `Audio RealtimeResponseCreateAudioOutput` + + Configuration for audio input and output. + + - `Output RealtimeResponseCreateAudioOutputOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice RealtimeResponseCreateAudioOutputOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Alloy RealtimeResponseCreateAudioOutputOutputVoiceString2 = "alloy"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ash RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ash"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Ballad RealtimeResponseCreateAudioOutputOutputVoiceString2 = "ballad"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Coral RealtimeResponseCreateAudioOutputOutputVoiceString2 = "coral"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Echo RealtimeResponseCreateAudioOutputOutputVoiceString2 = "echo"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Sage RealtimeResponseCreateAudioOutputOutputVoiceString2 = "sage"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Shimmer RealtimeResponseCreateAudioOutputOutputVoiceString2 = "shimmer"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Verse RealtimeResponseCreateAudioOutputOutputVoiceString2 = "verse"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Marin RealtimeResponseCreateAudioOutputOutputVoiceString2 = "marin"` + + - `const RealtimeResponseCreateAudioOutputOutputVoiceString2Cedar RealtimeResponseCreateAudioOutputOutputVoiceString2 = "cedar"` + + - `RealtimeResponseCreateAudioOutputOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Conversation RealtimeResponseCreateParamsConversation` + + Controls which conversation the response is added to. Currently supports + `auto` and `none`, with `auto` as the default value. The `auto` value + means that the contents of the response will be added to the default + conversation. Set this to `none` to create an out-of-band response which + will not add items to default conversation. + + - `string` + + - `RealtimeResponseCreateParamsConversation` + + - `const RealtimeResponseCreateParamsConversationAuto RealtimeResponseCreateParamsConversation = "auto"` + + - `const RealtimeResponseCreateParamsConversationNone RealtimeResponseCreateParamsConversation = "none"` + + - `Input []ConversationItemUnion` + + Input items to include in the prompt for the model. Using this field + creates a new context for this Response instead of using the default + conversation. An empty array `[]` will clear the context for this Response. + Note that this can include references to items that previously appeared in the session + using their id. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeResponseCreateParamsMaxOutputTokensUnionResp` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Metadata Metadata` + + Set of 16 key-value pairs that can be attached to an object. This can be + useful for storing additional information about the object in a structured + format, and querying for objects via API or the dashboard. + + Keys are strings with a maximum length of 64 characters. Values are strings + with a maximum length of 512 characters. + + - `OutputModalities []string` + + The set of modalities the model used to respond, currently the only possible values are + `[\"audio\"]`, `[\"text\"]`. Audio output always include a text transcript. Setting the + output to mode `text` will disable audio output from the model. + + - `const RealtimeResponseCreateParamsOutputModalityText RealtimeResponseCreateParamsOutputModality = "text"` + + - `const RealtimeResponseCreateParamsOutputModalityAudio RealtimeResponseCreateParamsOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeResponseCreateParamsToolChoiceUnionResp` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools []RealtimeResponseCreateParamsToolUnionResp` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `type RealtimeResponseCreateMcpTool struct{…}` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeResponseCreateMcpToolAllowedToolsUnion` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeResponseCreateMcpToolAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID RealtimeResponseCreateMcpToolConnectorID` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorDropbox RealtimeResponseCreateMcpToolConnectorID = "connector_dropbox"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGmail RealtimeResponseCreateMcpToolConnectorID = "connector_gmail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGooglecalendar RealtimeResponseCreateMcpToolConnectorID = "connector_googlecalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorGoogledrive RealtimeResponseCreateMcpToolConnectorID = "connector_googledrive"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorMicrosoftteams RealtimeResponseCreateMcpToolConnectorID = "connector_microsoftteams"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookcalendar RealtimeResponseCreateMcpToolConnectorID = "connector_outlookcalendar"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorOutlookemail RealtimeResponseCreateMcpToolConnectorID = "connector_outlookemail"` + + - `const RealtimeResponseCreateMcpToolConnectorIDConnectorSharepoint RealtimeResponseCreateMcpToolConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeResponseCreateMcpToolRequireApprovalUnion` + + Specify which of the MCP server's tools require approval. + + - `RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeResponseCreateMcpToolRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + +### Response Created Event + +- `type ResponseCreatedEvent struct{…}` + + Returned when a new Response is created. The first event of response creation, + where the response is in an initial state of `in_progress`. + + - `EventID string` + + The unique ID of the server event. + + - `Response RealtimeResponse` + + The response resource. + + - `ID string` + + The unique ID of the response, will look like `resp_1234`. + + - `Audio RealtimeResponseAudio` + + Configuration for audio output. + + - `Output RealtimeResponseAudioOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice string` + + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, + `shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for + best quality. + + - `string` + + - `string` + + - `const RealtimeResponseAudioOutputVoiceAlloy RealtimeResponseAudioOutputVoice = "alloy"` + + - `const RealtimeResponseAudioOutputVoiceAsh RealtimeResponseAudioOutputVoice = "ash"` + + - `const RealtimeResponseAudioOutputVoiceBallad RealtimeResponseAudioOutputVoice = "ballad"` + + - `const RealtimeResponseAudioOutputVoiceCoral RealtimeResponseAudioOutputVoice = "coral"` + + - `const RealtimeResponseAudioOutputVoiceEcho RealtimeResponseAudioOutputVoice = "echo"` + + - `const RealtimeResponseAudioOutputVoiceSage RealtimeResponseAudioOutputVoice = "sage"` + + - `const RealtimeResponseAudioOutputVoiceShimmer RealtimeResponseAudioOutputVoice = "shimmer"` + + - `const RealtimeResponseAudioOutputVoiceVerse RealtimeResponseAudioOutputVoice = "verse"` + + - `const RealtimeResponseAudioOutputVoiceMarin RealtimeResponseAudioOutputVoice = "marin"` + + - `const RealtimeResponseAudioOutputVoiceCedar RealtimeResponseAudioOutputVoice = "cedar"` + + - `ConversationID string` + + Which conversation the response is added to, determined by the `conversation` + field in the `response.create` event. If `auto`, the response will be added to + the default conversation and the value of `conversation_id` will be an id like + `conv_1234`. If `none`, the response will not be added to any conversation and + the value of `conversation_id` will be `null`. If responses are being triggered + automatically by VAD the response will be added to the default conversation + + - `MaxOutputTokens RealtimeResponseMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls, that was used in this response. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Metadata Metadata` + + Set of 16 key-value pairs that can be attached to an object. This can be + useful for storing additional information about the object in a structured + format, and querying for objects via API or the dashboard. + + Keys are strings with a maximum length of 64 characters. Values are strings + with a maximum length of 512 characters. + + - `Object RealtimeResponseObject` + + The object type, must be `realtime.response`. + + - `const RealtimeResponseObjectRealtimeResponse RealtimeResponseObject = "realtime.response"` + + - `Output []ConversationItemUnion` + + The list of output items generated by the response. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `OutputModalities []string` + + The set of modalities the model used to respond, currently the only possible values are + `[\"audio\"]`, `[\"text\"]`. Audio output always include a text transcript. Setting the + output to mode `text` will disable audio output from the model. + + - `const RealtimeResponseOutputModalityText RealtimeResponseOutputModality = "text"` + + - `const RealtimeResponseOutputModalityAudio RealtimeResponseOutputModality = "audio"` + + - `Status RealtimeResponseStatus` + + The final status of the response (`completed`, `cancelled`, `failed`, or + `incomplete`, `in_progress`). + + - `const RealtimeResponseStatusCompleted RealtimeResponseStatus = "completed"` + + - `const RealtimeResponseStatusCancelled RealtimeResponseStatus = "cancelled"` + + - `const RealtimeResponseStatusFailed RealtimeResponseStatus = "failed"` + + - `const RealtimeResponseStatusIncomplete RealtimeResponseStatus = "incomplete"` + + - `const RealtimeResponseStatusInProgress RealtimeResponseStatus = "in_progress"` + + - `StatusDetails RealtimeResponseStatus` + + Additional details about the status. + + - `Error RealtimeResponseStatusError` + + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + + - `Code string` + + Error code, if any. + + - `Type string` + + The type of error. + + - `Reason RealtimeResponseStatusReason` + + The reason the Response did not complete. For a `cancelled` Response, one of `turn_detected` (the server VAD detected a new start of speech) or `client_cancelled` (the client sent a cancel event). For an `incomplete` Response, one of `max_output_tokens` or `content_filter` (the server-side safety filter activated and cut off the response). + + - `const RealtimeResponseStatusReasonTurnDetected RealtimeResponseStatusReason = "turn_detected"` + + - `const RealtimeResponseStatusReasonClientCancelled RealtimeResponseStatusReason = "client_cancelled"` + + - `const RealtimeResponseStatusReasonMaxOutputTokens RealtimeResponseStatusReason = "max_output_tokens"` + + - `const RealtimeResponseStatusReasonContentFilter RealtimeResponseStatusReason = "content_filter"` + + - `Type RealtimeResponseStatusType` + + The type of error that caused the response to fail, corresponding + with the `status` field (`completed`, `cancelled`, `incomplete`, + `failed`). + + - `const RealtimeResponseStatusTypeCompleted RealtimeResponseStatusType = "completed"` + + - `const RealtimeResponseStatusTypeCancelled RealtimeResponseStatusType = "cancelled"` + + - `const RealtimeResponseStatusTypeIncomplete RealtimeResponseStatusType = "incomplete"` + + - `const RealtimeResponseStatusTypeFailed RealtimeResponseStatusType = "failed"` + + - `Usage RealtimeResponseUsage` + + Usage statistics for the Response, this will correspond to billing. A + Realtime API session will maintain a conversation context and append new + Items to the Conversation, thus output from previous turns (text and + audio tokens) will become the input for later turns. + + - `InputTokenDetails RealtimeResponseUsageInputTokenDetails` + + Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens. + + - `AudioTokens int64` + + The number of audio tokens used as input for the Response. + + - `CachedTokens int64` + + The number of cached tokens used as input for the Response. + + - `CachedTokensDetails RealtimeResponseUsageInputTokenDetailsCachedTokensDetails` + + Details about the cached tokens used as input for the Response. + + - `AudioTokens int64` + + The number of cached audio tokens used as input for the Response. + + - `ImageTokens int64` + + The number of cached image tokens used as input for the Response. + + - `TextTokens int64` + + The number of cached text tokens used as input for the Response. + + - `ImageTokens int64` + + The number of image tokens used as input for the Response. + + - `TextTokens int64` + + The number of text tokens used as input for the Response. + + - `InputTokens int64` + + The number of input tokens used in the Response, including text and + audio tokens. + + - `OutputTokenDetails RealtimeResponseUsageOutputTokenDetails` + + Details about the output tokens used in the Response. + + - `AudioTokens int64` + + The number of audio tokens used in the Response. + + - `TextTokens int64` + + The number of text tokens used in the Response. + + - `OutputTokens int64` + + The number of output tokens sent in the Response, including text and + audio tokens. + + - `TotalTokens int64` + + The total number of tokens in the Response including input and output + text and audio tokens. + + - `Type ResponseCreated` + + The event type, must be `response.created`. + + - `const ResponseCreatedResponseCreated ResponseCreated = "response.created"` + +### Response Done Event + +- `type ResponseDoneEvent struct{…}` + + Returned when a Response is done streaming. Always emitted, no matter the + final state. The Response object included in the `response.done` event will + include all output Items in the Response but will omit the raw audio data. + + Clients should check the `status` field of the Response to determine if it was successful + (`completed`) or if there was another outcome: `cancelled`, `failed`, or `incomplete`. + + A response will contain all output items that were generated during the response, excluding + any audio content. + + - `EventID string` + + The unique ID of the server event. + + - `Response RealtimeResponse` + + The response resource. + + - `ID string` + + The unique ID of the response, will look like `resp_1234`. + + - `Audio RealtimeResponseAudio` + + Configuration for audio output. + + - `Output RealtimeResponseAudioOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `Voice string` + + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, + `shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for + best quality. + + - `string` + + - `string` + + - `const RealtimeResponseAudioOutputVoiceAlloy RealtimeResponseAudioOutputVoice = "alloy"` + + - `const RealtimeResponseAudioOutputVoiceAsh RealtimeResponseAudioOutputVoice = "ash"` + + - `const RealtimeResponseAudioOutputVoiceBallad RealtimeResponseAudioOutputVoice = "ballad"` + + - `const RealtimeResponseAudioOutputVoiceCoral RealtimeResponseAudioOutputVoice = "coral"` + + - `const RealtimeResponseAudioOutputVoiceEcho RealtimeResponseAudioOutputVoice = "echo"` + + - `const RealtimeResponseAudioOutputVoiceSage RealtimeResponseAudioOutputVoice = "sage"` + + - `const RealtimeResponseAudioOutputVoiceShimmer RealtimeResponseAudioOutputVoice = "shimmer"` + + - `const RealtimeResponseAudioOutputVoiceVerse RealtimeResponseAudioOutputVoice = "verse"` + + - `const RealtimeResponseAudioOutputVoiceMarin RealtimeResponseAudioOutputVoice = "marin"` + + - `const RealtimeResponseAudioOutputVoiceCedar RealtimeResponseAudioOutputVoice = "cedar"` + + - `ConversationID string` + + Which conversation the response is added to, determined by the `conversation` + field in the `response.create` event. If `auto`, the response will be added to + the default conversation and the value of `conversation_id` will be an id like + `conv_1234`. If `none`, the response will not be added to any conversation and + the value of `conversation_id` will be `null`. If responses are being triggered + automatically by VAD the response will be added to the default conversation + + - `MaxOutputTokens RealtimeResponseMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls, that was used in this response. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Metadata Metadata` + + Set of 16 key-value pairs that can be attached to an object. This can be + useful for storing additional information about the object in a structured + format, and querying for objects via API or the dashboard. + + Keys are strings with a maximum length of 64 characters. Values are strings + with a maximum length of 512 characters. + + - `Object RealtimeResponseObject` + + The object type, must be `realtime.response`. + + - `const RealtimeResponseObjectRealtimeResponse RealtimeResponseObject = "realtime.response"` + + - `Output []ConversationItemUnion` + + The list of output items generated by the response. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `OutputModalities []string` + + The set of modalities the model used to respond, currently the only possible values are + `[\"audio\"]`, `[\"text\"]`. Audio output always include a text transcript. Setting the + output to mode `text` will disable audio output from the model. + + - `const RealtimeResponseOutputModalityText RealtimeResponseOutputModality = "text"` + + - `const RealtimeResponseOutputModalityAudio RealtimeResponseOutputModality = "audio"` + + - `Status RealtimeResponseStatus` + + The final status of the response (`completed`, `cancelled`, `failed`, or + `incomplete`, `in_progress`). + + - `const RealtimeResponseStatusCompleted RealtimeResponseStatus = "completed"` + + - `const RealtimeResponseStatusCancelled RealtimeResponseStatus = "cancelled"` + + - `const RealtimeResponseStatusFailed RealtimeResponseStatus = "failed"` + + - `const RealtimeResponseStatusIncomplete RealtimeResponseStatus = "incomplete"` + + - `const RealtimeResponseStatusInProgress RealtimeResponseStatus = "in_progress"` + + - `StatusDetails RealtimeResponseStatus` + + Additional details about the status. + + - `Error RealtimeResponseStatusError` + + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + + - `Code string` + + Error code, if any. + + - `Type string` + + The type of error. + + - `Reason RealtimeResponseStatusReason` + + The reason the Response did not complete. For a `cancelled` Response, one of `turn_detected` (the server VAD detected a new start of speech) or `client_cancelled` (the client sent a cancel event). For an `incomplete` Response, one of `max_output_tokens` or `content_filter` (the server-side safety filter activated and cut off the response). + + - `const RealtimeResponseStatusReasonTurnDetected RealtimeResponseStatusReason = "turn_detected"` + + - `const RealtimeResponseStatusReasonClientCancelled RealtimeResponseStatusReason = "client_cancelled"` + + - `const RealtimeResponseStatusReasonMaxOutputTokens RealtimeResponseStatusReason = "max_output_tokens"` + + - `const RealtimeResponseStatusReasonContentFilter RealtimeResponseStatusReason = "content_filter"` + + - `Type RealtimeResponseStatusType` + + The type of error that caused the response to fail, corresponding + with the `status` field (`completed`, `cancelled`, `incomplete`, + `failed`). + + - `const RealtimeResponseStatusTypeCompleted RealtimeResponseStatusType = "completed"` + + - `const RealtimeResponseStatusTypeCancelled RealtimeResponseStatusType = "cancelled"` + + - `const RealtimeResponseStatusTypeIncomplete RealtimeResponseStatusType = "incomplete"` + + - `const RealtimeResponseStatusTypeFailed RealtimeResponseStatusType = "failed"` + + - `Usage RealtimeResponseUsage` + + Usage statistics for the Response, this will correspond to billing. A + Realtime API session will maintain a conversation context and append new + Items to the Conversation, thus output from previous turns (text and + audio tokens) will become the input for later turns. + + - `InputTokenDetails RealtimeResponseUsageInputTokenDetails` + + Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens. + + - `AudioTokens int64` + + The number of audio tokens used as input for the Response. + + - `CachedTokens int64` + + The number of cached tokens used as input for the Response. + + - `CachedTokensDetails RealtimeResponseUsageInputTokenDetailsCachedTokensDetails` + + Details about the cached tokens used as input for the Response. + + - `AudioTokens int64` + + The number of cached audio tokens used as input for the Response. + + - `ImageTokens int64` + + The number of cached image tokens used as input for the Response. + + - `TextTokens int64` + + The number of cached text tokens used as input for the Response. + + - `ImageTokens int64` + + The number of image tokens used as input for the Response. + + - `TextTokens int64` + + The number of text tokens used as input for the Response. + + - `InputTokens int64` + + The number of input tokens used in the Response, including text and + audio tokens. + + - `OutputTokenDetails RealtimeResponseUsageOutputTokenDetails` + + Details about the output tokens used in the Response. + + - `AudioTokens int64` + + The number of audio tokens used in the Response. + + - `TextTokens int64` + + The number of text tokens used in the Response. + + - `OutputTokens int64` + + The number of output tokens sent in the Response, including text and + audio tokens. + + - `TotalTokens int64` + + The total number of tokens in the Response including input and output + text and audio tokens. + + - `Type ResponseDone` + + The event type, must be `response.done`. + + - `const ResponseDoneResponseDone ResponseDone = "response.done"` + +### Response Function Call Arguments Delta Event + +- `type ResponseFunctionCallArgumentsDeltaEvent struct{…}` + + Returned when the model-generated function call arguments are updated. + + - `CallID string` + + The ID of the function call. + + - `Delta string` + + The arguments delta as a JSON string. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the function call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseFunctionCallArgumentsDelta` + + The event type, must be `response.function_call_arguments.delta`. + + - `const ResponseFunctionCallArgumentsDeltaResponseFunctionCallArgumentsDelta ResponseFunctionCallArgumentsDelta = "response.function_call_arguments.delta"` + +### Response Function Call Arguments Done Event + +- `type ResponseFunctionCallArgumentsDoneEvent struct{…}` + + Returned when the model-generated function call arguments are done streaming. + Also emitted when a Response is interrupted, incomplete, or cancelled. + + - `Arguments string` + + The final arguments as a JSON string. + + - `CallID string` + + The ID of the function call. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the function call item. + + - `Name string` + + The name of the function that was called. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseFunctionCallArgumentsDone` + + The event type, must be `response.function_call_arguments.done`. + + - `const ResponseFunctionCallArgumentsDoneResponseFunctionCallArgumentsDone ResponseFunctionCallArgumentsDone = "response.function_call_arguments.done"` + +### Response Mcp Call Arguments Delta + +- `type ResponseMcpCallArgumentsDelta struct{…}` + + Returned when MCP tool call arguments are updated during response generation. + + - `Delta string` + + The JSON-encoded arguments delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseMcpCallArgumentsDelta` + + The event type, must be `response.mcp_call_arguments.delta`. + + - `const ResponseMcpCallArgumentsDeltaResponseMcpCallArgumentsDelta ResponseMcpCallArgumentsDelta = "response.mcp_call_arguments.delta"` + + - `Obfuscation string` + + If present, indicates the delta text was obfuscated. + +### Response Mcp Call Arguments Done + +- `type ResponseMcpCallArgumentsDone struct{…}` + + Returned when MCP tool call arguments are finalized during response generation. + + - `Arguments string` + + The final JSON-encoded arguments string. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseMcpCallArgumentsDone` + + The event type, must be `response.mcp_call_arguments.done`. + + - `const ResponseMcpCallArgumentsDoneResponseMcpCallArgumentsDone ResponseMcpCallArgumentsDone = "response.mcp_call_arguments.done"` + +### Response Mcp Call Completed + +- `type ResponseMcpCallCompleted struct{…}` + + Returned when an MCP tool call has completed successfully. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Type ResponseMcpCallCompleted` + + The event type, must be `response.mcp_call.completed`. + + - `const ResponseMcpCallCompletedResponseMcpCallCompleted ResponseMcpCallCompleted = "response.mcp_call.completed"` + +### Response Mcp Call Failed + +- `type ResponseMcpCallFailed struct{…}` + + Returned when an MCP tool call has failed. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Type ResponseMcpCallFailed` + + The event type, must be `response.mcp_call.failed`. + + - `const ResponseMcpCallFailedResponseMcpCallFailed ResponseMcpCallFailed = "response.mcp_call.failed"` + +### Response Mcp Call In Progress + +- `type ResponseMcpCallInProgress struct{…}` + + Returned when an MCP tool call has started and is in progress. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the MCP tool call item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `Type ResponseMcpCallInProgress` + + The event type, must be `response.mcp_call.in_progress`. + + - `const ResponseMcpCallInProgressResponseMcpCallInProgress ResponseMcpCallInProgress = "response.mcp_call.in_progress"` + +### Response Output Item Added Event + +- `type ResponseOutputItemAddedEvent struct{…}` + + Returned when a new Item is created during Response generation. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `OutputIndex int64` + + The index of the output item in the Response. + + - `ResponseID string` + + The ID of the Response to which the item belongs. + + - `Type ResponseOutputItemAdded` + + The event type, must be `response.output_item.added`. + + - `const ResponseOutputItemAddedResponseOutputItemAdded ResponseOutputItemAdded = "response.output_item.added"` + +### Response Output Item Done Event + +- `type ResponseOutputItemDoneEvent struct{…}` + + Returned when an Item is done streaming. Also emitted when a Response is + interrupted, incomplete, or cancelled. + + - `EventID string` + + The unique ID of the server event. + + - `Item ConversationItemUnion` + + A single item within a Realtime conversation. + + - `type RealtimeConversationItemSystemMessage struct{…}` + + A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. "the user is now asking about a different topic"), use system messages. + + - `Content []RealtimeConversationItemSystemMessageContent` + + The content of the message. + + - `Text string` + + The text content. + + - `Type string` + + The content type. Always `input_text` for system messages. + + - `const RealtimeConversationItemSystemMessageContentTypeInputText RealtimeConversationItemSystemMessageContentType = "input_text"` + + - `Role System` + + The role of the message sender. Always `system`. + + - `const SystemSystem System = "system"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemSystemMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemSystemMessageObjectRealtimeItem RealtimeConversationItemSystemMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemSystemMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemSystemMessageStatusCompleted RealtimeConversationItemSystemMessageStatus = "completed"` + + - `const RealtimeConversationItemSystemMessageStatusIncomplete RealtimeConversationItemSystemMessageStatus = "incomplete"` + + - `const RealtimeConversationItemSystemMessageStatusInProgress RealtimeConversationItemSystemMessageStatus = "in_progress"` + + - `type RealtimeConversationItemUserMessage struct{…}` + + A user message item in a Realtime conversation. + + - `Content []RealtimeConversationItemUserMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Detail string` + + The detail level of the image (for `input_image`). `auto` will default to `high`. + + - `const RealtimeConversationItemUserMessageContentDetailAuto RealtimeConversationItemUserMessageContentDetail = "auto"` + + - `const RealtimeConversationItemUserMessageContentDetailLow RealtimeConversationItemUserMessageContentDetail = "low"` + + - `const RealtimeConversationItemUserMessageContentDetailHigh RealtimeConversationItemUserMessageContentDetail = "high"` + + - `ImageURL string` + + Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG. + + - `Text string` + + The text content (for `input_text`). + + - `Transcript string` + + Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference. + + - `Type string` + + The content type (`input_text`, `input_audio`, or `input_image`). + + - `const RealtimeConversationItemUserMessageContentTypeInputText RealtimeConversationItemUserMessageContentType = "input_text"` + + - `const RealtimeConversationItemUserMessageContentTypeInputAudio RealtimeConversationItemUserMessageContentType = "input_audio"` + + - `const RealtimeConversationItemUserMessageContentTypeInputImage RealtimeConversationItemUserMessageContentType = "input_image"` + + - `Role User` + + The role of the message sender. Always `user`. + + - `const UserUser User = "user"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemUserMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemUserMessageObjectRealtimeItem RealtimeConversationItemUserMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemUserMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemUserMessageStatusCompleted RealtimeConversationItemUserMessageStatus = "completed"` + + - `const RealtimeConversationItemUserMessageStatusIncomplete RealtimeConversationItemUserMessageStatus = "incomplete"` + + - `const RealtimeConversationItemUserMessageStatusInProgress RealtimeConversationItemUserMessageStatus = "in_progress"` + + - `type RealtimeConversationItemAssistantMessage struct{…}` + + An assistant message item in a Realtime conversation. + + - `Content []RealtimeConversationItemAssistantMessageContent` + + The content of the message. + + - `Audio string` + + Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified. + + - `Text string` + + The text content. + + - `Transcript string` + + The transcript of the audio content, this will always be present if the output type is `audio`. + + - `Type string` + + The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration. + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputText RealtimeConversationItemAssistantMessageContentType = "output_text"` + + - `const RealtimeConversationItemAssistantMessageContentTypeOutputAudio RealtimeConversationItemAssistantMessageContentType = "output_audio"` + + - `Role Assistant` + + The role of the message sender. Always `assistant`. + + - `const AssistantAssistant Assistant = "assistant"` + + - `Type Message` + + The type of the item. Always `message`. + + - `const MessageMessage Message = "message"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemAssistantMessageObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemAssistantMessageObjectRealtimeItem RealtimeConversationItemAssistantMessageObject = "realtime.item"` + + - `Status RealtimeConversationItemAssistantMessageStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemAssistantMessageStatusCompleted RealtimeConversationItemAssistantMessageStatus = "completed"` + + - `const RealtimeConversationItemAssistantMessageStatusIncomplete RealtimeConversationItemAssistantMessageStatus = "incomplete"` + + - `const RealtimeConversationItemAssistantMessageStatusInProgress RealtimeConversationItemAssistantMessageStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCall struct{…}` + + A function call item in a Realtime conversation. + + - `Arguments string` + + The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{"arg1": "value1", "arg2": 42}`. + + - `Name string` + + The name of the function being called. + + - `Type FunctionCall` + + The type of the item. Always `function_call`. + + - `const FunctionCallFunctionCall FunctionCall = "function_call"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `CallID string` + + The ID of the function call. + + - `Object RealtimeConversationItemFunctionCallObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallObjectRealtimeItem RealtimeConversationItemFunctionCallObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallStatusCompleted RealtimeConversationItemFunctionCallStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallStatusIncomplete RealtimeConversationItemFunctionCallStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallStatusInProgress RealtimeConversationItemFunctionCallStatus = "in_progress"` + + - `type RealtimeConversationItemFunctionCallOutput struct{…}` + + A function call output item in a Realtime conversation. + + - `CallID string` + + The ID of the function call this output is for. + + - `Output string` + + The output of the function call, this is free text and can contain any information or simply be empty. + + - `Type FunctionCallOutput` + + The type of the item. Always `function_call_output`. + + - `const FunctionCallOutputFunctionCallOutput FunctionCallOutput = "function_call_output"` + + - `ID string` + + The unique ID of the item. This may be provided by the client or generated by the server. + + - `Object RealtimeConversationItemFunctionCallOutputObject` + + Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item. + + - `const RealtimeConversationItemFunctionCallOutputObjectRealtimeItem RealtimeConversationItemFunctionCallOutputObject = "realtime.item"` + + - `Status RealtimeConversationItemFunctionCallOutputStatus` + + The status of the item. Has no effect on the conversation. + + - `const RealtimeConversationItemFunctionCallOutputStatusCompleted RealtimeConversationItemFunctionCallOutputStatus = "completed"` + + - `const RealtimeConversationItemFunctionCallOutputStatusIncomplete RealtimeConversationItemFunctionCallOutputStatus = "incomplete"` + + - `const RealtimeConversationItemFunctionCallOutputStatusInProgress RealtimeConversationItemFunctionCallOutputStatus = "in_progress"` + + - `type RealtimeMcpApprovalResponse struct{…}` + + A Realtime item responding to an MCP approval request. + + - `ID string` + + The unique ID of the approval response. + + - `ApprovalRequestID string` + + The ID of the approval request being answered. + + - `Approve bool` + + Whether the request was approved. + + - `Type McpApprovalResponse` + + The type of the item. Always `mcp_approval_response`. + + - `const McpApprovalResponseMcpApprovalResponse McpApprovalResponse = "mcp_approval_response"` + + - `Reason string` + + Optional reason for the decision. + + - `type RealtimeMcpListTools struct{…}` + + A Realtime item listing tools available on an MCP server. + + - `ServerLabel string` + + The label of the MCP server. + + - `Tools []RealtimeMcpListToolsTool` + + The tools available on the server. + + - `InputSchema any` + + The JSON schema describing the tool's input. + + - `Name string` + + The name of the tool. + + - `Annotations any` + + Additional annotations about the tool. + + - `Description string` + + The description of the tool. + + - `Type McpListTools` + + The type of the item. Always `mcp_list_tools`. + + - `const McpListToolsMcpListTools McpListTools = "mcp_list_tools"` + + - `ID string` + + The unique ID of the list. + + - `type RealtimeMcpToolCall struct{…}` + + A Realtime item representing an invocation of a tool on an MCP server. + + - `ID string` + + The unique ID of the tool call. + + - `Arguments string` + + A JSON string of the arguments passed to the tool. + + - `Name string` + + The name of the tool that was run. + + - `ServerLabel string` + + The label of the MCP server running the tool. + + - `Type McpCall` + + The type of the item. Always `mcp_call`. + + - `const McpCallMcpCall McpCall = "mcp_call"` + + - `ApprovalRequestID string` + + The ID of an associated approval request, if any. + + - `Error RealtimeMcpToolCallErrorUnion` + + The error from the tool call, if any. + + - `type RealtimeMcpProtocolError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type ProtocolError` + + - `const ProtocolErrorProtocolError ProtocolError = "protocol_error"` + + - `type RealtimeMcpToolExecutionError struct{…}` + + - `Message string` + + - `Type ToolExecutionError` + + - `const ToolExecutionErrorToolExecutionError ToolExecutionError = "tool_execution_error"` + + - `type RealtimeMcphttpError struct{…}` + + - `Code int64` + + - `Message string` + + - `Type HTTPError` + + - `const HTTPErrorHTTPError HTTPError = "http_error"` + + - `Output string` + + The output from the tool call. + + - `type RealtimeMcpApprovalRequest struct{…}` + + A Realtime item requesting human approval of a tool invocation. + + - `ID string` + + The unique ID of the approval request. + + - `Arguments string` + + A JSON string of arguments for the tool. + + - `Name string` + + The name of the tool to run. + + - `ServerLabel string` + + The label of the MCP server making the request. + + - `Type McpApprovalRequest` + + The type of the item. Always `mcp_approval_request`. + + - `const McpApprovalRequestMcpApprovalRequest McpApprovalRequest = "mcp_approval_request"` + + - `OutputIndex int64` + + The index of the output item in the Response. + + - `ResponseID string` + + The ID of the Response to which the item belongs. + + - `Type ResponseOutputItemDone` + + The event type, must be `response.output_item.done`. + + - `const ResponseOutputItemDoneResponseOutputItemDone ResponseOutputItemDone = "response.output_item.done"` + +### Response Text Delta Event + +- `type ResponseTextDeltaEvent struct{…}` + + Returned when the text value of an "output_text" content part is updated. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `Delta string` + + The text delta. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Type ResponseOutputTextDelta` + + The event type, must be `response.output_text.delta`. + + - `const ResponseOutputTextDeltaResponseOutputTextDelta ResponseOutputTextDelta = "response.output_text.delta"` + +### Response Text Done Event + +- `type ResponseTextDoneEvent struct{…}` + + Returned when the text value of an "output_text" content part is done streaming. Also + emitted when a Response is interrupted, incomplete, or cancelled. + + - `ContentIndex int64` + + The index of the content part in the item's content array. + + - `EventID string` + + The unique ID of the server event. + + - `ItemID string` + + The ID of the item. + + - `OutputIndex int64` + + The index of the output item in the response. + + - `ResponseID string` + + The ID of the response. + + - `Text string` + + The final text content. + + - `Type ResponseOutputTextDone` + + The event type, must be `response.output_text.done`. + + - `const ResponseOutputTextDoneResponseOutputTextDone ResponseOutputTextDone = "response.output_text.done"` + +### Session Created Event + +- `type SessionCreatedEvent struct{…}` + + Returned when a Session is created. Emitted automatically when a new + connection is established as the first server event. This event will contain + the default Session configuration. + + - `EventID string` + + The unique ID of the server event. + + - `Session SessionCreatedEventSessionUnion` + + The session configuration. + + - `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeAudioConfig` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateRequestModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionCreateRequestModel` + + - `const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime1_5 RealtimeSessionCreateRequestModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2 RealtimeSessionCreateRequestModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateRequestModelGPTAudio1_5 RealtimeSessionCreateRequestModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"` + + - `const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeToolChoiceConfigUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools RealtimeToolsConfig` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeTracingConfigUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + + - `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type Transcription` + + The type of session to create. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionAudio` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Type SessionCreated` + + The event type, must be `session.created`. + + - `const SessionCreatedSessionCreated SessionCreated = "session.created"` + +### Session Update Event + +- `type SessionUpdateEvent struct{…}` + + Send this event to update the session’s configuration. + The client may send this event at any time to update any field + except for `voice` and `model`. `voice` can be updated only if there have been no other audio outputs yet. + + When the server receives a `session.update`, it will respond + with a `session.updated` event showing the full, effective configuration. + Only the fields that are present in the `session.update` are updated. To clear a field like + `instructions`, pass an empty string. To clear a field like `tools`, pass an empty array. + To clear a field like `turn_detection`, pass `null`. + + - `Session SessionUpdateEventSessionUnion` + + Update the Realtime session. Choose either a realtime + session or a transcription session. + + - `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeAudioConfig` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateRequestModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionCreateRequestModel` + + - `const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime1_5 RealtimeSessionCreateRequestModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2 RealtimeSessionCreateRequestModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateRequestModelGPTAudio1_5 RealtimeSessionCreateRequestModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"` + + - `const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeToolChoiceConfigUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools RealtimeToolsConfig` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeTracingConfigUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + + - `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type Transcription` + + The type of session to create. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionAudio` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Type SessionUpdate` + + The event type, must be `session.update`. + + - `const SessionUpdateSessionUpdate SessionUpdate = "session.update"` + + - `EventID string` + + Optional client-generated ID used to identify this event. This is an arbitrary string that a client may assign. It will be passed back if there is an error with the event, but the corresponding `session.updated` event will not include it. + +### Session Updated Event + +- `type SessionUpdatedEvent struct{…}` + + Returned when a session is updated with a `session.update` event, unless + there is an error. + + - `EventID string` + + The unique ID of the server event. + + - `Session SessionUpdatedEventSessionUnion` + + The session configuration. + + - `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeAudioConfig` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateRequestModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionCreateRequestModel` + + - `const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime1_5 RealtimeSessionCreateRequestModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2 RealtimeSessionCreateRequestModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateRequestModelGPTAudio1_5 RealtimeSessionCreateRequestModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"` + + - `const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeToolChoiceConfigUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools RealtimeToolsConfig` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeTracingConfigUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + + - `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type Transcription` + + The type of session to create. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionAudio` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Type SessionUpdated` + + The event type, must be `session.updated`. + + - `const SessionUpdatedSessionUpdated SessionUpdated = "session.updated"` + +### Transcription Session Update + +- `type TranscriptionSessionUpdate struct{…}` + + Send this event to update a transcription session. + + - `Session TranscriptionSessionUpdateSession` + + Realtime transcription session object configuration. + + - `Include []string` + + The set of items to include in the transcription. Current available items are: + `item.input_audio_transcription.logprobs` + + - `const TranscriptionSessionUpdateSessionIncludeItemInputAudioTranscriptionLogprobs TranscriptionSessionUpdateSessionInclude = "item.input_audio_transcription.logprobs"` + + - `InputAudioFormat string` + + The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + For `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, + single channel (mono), and little-endian byte order. + + - `const TranscriptionSessionUpdateSessionInputAudioFormatPcm16 TranscriptionSessionUpdateSessionInputAudioFormat = "pcm16"` + + - `const TranscriptionSessionUpdateSessionInputAudioFormatG711Ulaw TranscriptionSessionUpdateSessionInputAudioFormat = "g711_ulaw"` + + - `const TranscriptionSessionUpdateSessionInputAudioFormatG711Alaw TranscriptionSessionUpdateSessionInputAudioFormat = "g711_alaw"` + + - `InputAudioNoiseReduction TranscriptionSessionUpdateSessionInputAudioNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `InputAudioTranscription AudioTranscription` + + Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection TranscriptionSessionUpdateSessionTurnDetection` + + Configuration for turn detection. Can be set to `null` to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + - `PrefixPaddingMs int64` + + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `Type string` + + Type of turn detection. Only `server_vad` is currently supported for transcription sessions. + + - `const TranscriptionSessionUpdateSessionTurnDetectionTypeServerVad TranscriptionSessionUpdateSessionTurnDetectionType = "server_vad"` + + - `Type TranscriptionSessionUpdate` + + The event type, must be `transcription_session.update`. + + - `const TranscriptionSessionUpdateTranscriptionSessionUpdate TranscriptionSessionUpdate = "transcription_session.update"` + + - `EventID string` + + Optional client-generated ID used to identify this event. + +### Transcription Session Updated Event + +- `type TranscriptionSessionUpdatedEvent struct{…}` + + Returned when a transcription session is updated with a `transcription_session.update` event, unless + there is an error. + + - `EventID string` + + The unique ID of the server event. + + - `Session TranscriptionSessionUpdatedEventSession` + + A new Realtime transcription session configuration. + + When a session is created on the server via REST API, the session object + also contains an ephemeral key. Default TTL for keys is 10 minutes. This + property is not present when a session is updated via the WebSocket API. + + - `ClientSecret TranscriptionSessionUpdatedEventSessionClientSecret` + + Ephemeral key returned by the API. Only present when the session is + created on the server via REST API. + + - `ExpiresAt int64` + + Timestamp for when the token expires. Currently, all tokens expire + after one minute. + + - `Value string` + + Ephemeral key usable in client environments to authenticate connections + to the Realtime API. Use this in client-side environments rather than + a standard API token, which should only be used server-side. + + - `InputAudioFormat string` + + The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + + - `InputAudioTranscription AudioTranscription` + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `Modalities []string` + + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + + - `const TranscriptionSessionUpdatedEventSessionModalityText TranscriptionSessionUpdatedEventSessionModality = "text"` + + - `const TranscriptionSessionUpdatedEventSessionModalityAudio TranscriptionSessionUpdatedEventSessionModality = "audio"` + + - `TurnDetection TranscriptionSessionUpdatedEventSessionTurnDetection` + + Configuration for turn detection. Can be set to `null` to turn off. Server + VAD means that the model will detect the start and end of speech based on + audio volume and respond at the end of user speech. + + - `PrefixPaddingMs int64` + + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `Type string` + + Type of turn detection, only `server_vad` is currently supported. + + - `Type TranscriptionSessionUpdated` + + The event type, must be `transcription_session.updated`. + + - `const TranscriptionSessionUpdatedTranscriptionSessionUpdated TranscriptionSessionUpdated = "transcription_session.updated"` + +# Client Secrets + +## Create client secret + +`client.Realtime.ClientSecrets.New(ctx, body) (*ClientSecretNewResponse, error)` + +**post** `/realtime/client_secrets` + +Create a Realtime client secret with an associated session configuration. + +Client secrets are short-lived tokens that can be passed to a client app, +such as a web frontend or mobile client, which grants access to the Realtime API without +leaking your main API key. You can configure a custom TTL for each client secret. + +You can also attach session configuration options to the client secret, which will be +applied to any sessions created using that client secret, but these can also be overridden +by the client connection. + +[Learn more about authentication with client secrets over WebRTC](https://platform.openai.com/docs/guides/realtime-webrtc). + +Returns the created client secret and the effective session object. The client secret is a string that looks like `ek_1234`. + +### Parameters + +- `body ClientSecretNewParams` + + - `ExpiresAfter param.Field[ClientSecretNewParamsExpiresAfter]` + + Configuration for the client secret expiration. Expiration refers to the time after which + a client secret will no longer be valid for creating sessions. The session itself may + continue after that time once started. A secret can be used to create multiple sessions + until it expires. + + - `Anchor string` + + The anchor point for the client secret expiration, meaning that `seconds` will be added to the `created_at` time of the client secret to produce an expiration timestamp. Only `created_at` is currently supported. + + - `const ClientSecretNewParamsExpiresAfterAnchorCreatedAt ClientSecretNewParamsExpiresAfterAnchor = "created_at"` + + - `Seconds int64` + + The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200` (2 hours). This default to 600 seconds (10 minutes) if not specified. + + - `Session param.Field[ClientSecretNewParamsSessionUnion]` + + Session configuration to use for the client secret. Choose either a realtime + session or a transcription session. + + - `type RealtimeSessionCreateRequest struct{…}` + + Realtime session object configuration. + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeAudioConfig` + + Configuration for input and output audio. + + - `Input RealtimeAudioConfigInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeAudioConfigInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessLow RealtimeAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeAudioConfigOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice RealtimeAudioConfigOutputVoiceUnion` + + The voice the model uses to respond. Supported built-in voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`, + `marin`, and `cedar`. You may also provide a custom voice object with + an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed + during the session once the model has responded with audio at least once. + We recommend `marin` and `cedar` for best quality. + + - `string` + + - `string` + + - `const RealtimeAudioConfigOutputVoiceString2Alloy RealtimeAudioConfigOutputVoiceString2 = "alloy"` + + - `const RealtimeAudioConfigOutputVoiceString2Ash RealtimeAudioConfigOutputVoiceString2 = "ash"` + + - `const RealtimeAudioConfigOutputVoiceString2Ballad RealtimeAudioConfigOutputVoiceString2 = "ballad"` + + - `const RealtimeAudioConfigOutputVoiceString2Coral RealtimeAudioConfigOutputVoiceString2 = "coral"` + + - `const RealtimeAudioConfigOutputVoiceString2Echo RealtimeAudioConfigOutputVoiceString2 = "echo"` + + - `const RealtimeAudioConfigOutputVoiceString2Sage RealtimeAudioConfigOutputVoiceString2 = "sage"` + + - `const RealtimeAudioConfigOutputVoiceString2Shimmer RealtimeAudioConfigOutputVoiceString2 = "shimmer"` + + - `const RealtimeAudioConfigOutputVoiceString2Verse RealtimeAudioConfigOutputVoiceString2 = "verse"` + + - `const RealtimeAudioConfigOutputVoiceString2Marin RealtimeAudioConfigOutputVoiceString2 = "marin"` + + - `const RealtimeAudioConfigOutputVoiceString2Cedar RealtimeAudioConfigOutputVoiceString2 = "cedar"` + + - `RealtimeAudioConfigOutputVoiceID` + + - `ID string` + + The custom voice ID, e.g. `voice_1234`. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateRequestMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `Inf` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateRequestModel` + + The Realtime model used for this session. + + - `string` + + - `RealtimeSessionCreateRequestModel` + + - `const RealtimeSessionCreateRequestModelGPTRealtime RealtimeSessionCreateRequestModel = "gpt-realtime"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime1_5 RealtimeSessionCreateRequestModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2 RealtimeSessionCreateRequestModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateRequestModelGPTRealtime2025_08_28 RealtimeSessionCreateRequestModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateRequestModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateRequestModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateRequestModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini RealtimeSessionCreateRequestModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateRequestModelGPTAudio1_5 RealtimeSessionCreateRequestModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini RealtimeSessionCreateRequestModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_10_06 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateRequestModelGPTAudioMini2025_12_15 RealtimeSessionCreateRequestModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateRequestOutputModalityText RealtimeSessionCreateRequestOutputModality = "text"` + + - `const RealtimeSessionCreateRequestOutputModalityAudio RealtimeSessionCreateRequestOutputModality = "audio"` + + - `ParallelToolCalls bool` + + Whether the model may call multiple tools in parallel. Only supported by + reasoning Realtime models such as `gpt-realtime-2`. + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeToolChoiceConfigUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools RealtimeToolsConfig` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `RealtimeToolsConfigUnionMcp` + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeToolsConfigUnionMcpAllowedTools` + + List of allowed tool names or a filter object. + + - `[]string` + + - `RealtimeToolsConfigUnionMcpAllowedToolsMcpToolFilter` + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorDropbox RealtimeToolsConfigUnionMcpConnectorID = "connector_dropbox"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGmail RealtimeToolsConfigUnionMcpConnectorID = "connector_gmail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGooglecalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_googlecalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorGoogledrive RealtimeToolsConfigUnionMcpConnectorID = "connector_googledrive"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorMicrosoftteams RealtimeToolsConfigUnionMcpConnectorID = "connector_microsoftteams"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookcalendar RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookcalendar"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorOutlookemail RealtimeToolsConfigUnionMcpConnectorID = "connector_outlookemail"` + + - `const RealtimeToolsConfigUnionMcpConnectorIDConnectorSharepoint RealtimeToolsConfigUnionMcpConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeToolsConfigUnionMcpRequireApproval` + + Specify which of the MCP server's tools require approval. + + - `RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilter` + + - `Always RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `string` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingAlways RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSettingNever RealtimeToolsConfigUnionMcpRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeTracingConfigUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `Auto` + + - `const AutoAuto Auto = "auto"` + + - `RealtimeTracingConfigTracingConfiguration` + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + + - `type RealtimeTranscriptionSessionCreateRequest struct{…}` + + Realtime transcription session object configuration. + + - `Type Transcription` + + The type of session to create. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionAudio` + + Configuration for input and output audio. + + - `Input RealtimeTranscriptionSessionAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `NoiseReduction RealtimeTranscriptionSessionAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `Transcription AudioTranscription` + + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + + - `TurnDetection RealtimeTranscriptionSessionAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionServerVad` + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVad` + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessLow RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeTranscriptionSessionAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateRequestIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateRequestInclude = "item.input_audio_transcription.logprobs"` + +### Returns + +- `type ClientSecretNewResponse struct{…}` + + Response from creating a session and client secret for the Realtime API. + + - `ExpiresAt int64` + + Expiration timestamp for the client secret, in seconds since epoch. + + - `Session ClientSecretNewResponseSessionUnion` + + The session configuration for either a realtime or transcription session. + + - `type RealtimeSessionCreateResponse struct{…}` + + A Realtime session configuration object. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Object RealtimeSession` + + The object type. Always `realtime.session`. + + - `const RealtimeSessionRealtimeSession RealtimeSession = "realtime.session"` + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeSessionCreateResponseAudio` + + Configuration for input and output audio. + + - `Input RealtimeSessionCreateResponseAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeSessionCreateResponseAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeSessionCreateResponseAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `type RealtimeSessionCreateResponseAudioInputTurnDetectionServerVad struct{…}` + + Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence. + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `type RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVad struct{…}` + + Server-side semantic turn detection which uses a model to determine when the user has finished speaking. + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessLow RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeSessionCreateResponseAudioOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice string` + + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, + `shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for + best quality. + + - `string` + + - `string` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceAlloy RealtimeSessionCreateResponseAudioOutputVoice = "alloy"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceAsh RealtimeSessionCreateResponseAudioOutputVoice = "ash"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceBallad RealtimeSessionCreateResponseAudioOutputVoice = "ballad"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceCoral RealtimeSessionCreateResponseAudioOutputVoice = "coral"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceEcho RealtimeSessionCreateResponseAudioOutputVoice = "echo"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceSage RealtimeSessionCreateResponseAudioOutputVoice = "sage"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceShimmer RealtimeSessionCreateResponseAudioOutputVoice = "shimmer"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceVerse RealtimeSessionCreateResponseAudioOutputVoice = "verse"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceMarin RealtimeSessionCreateResponseAudioOutputVoice = "marin"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceCedar RealtimeSessionCreateResponseAudioOutputVoice = "cedar"` + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateResponseIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateResponseInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateResponseMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `type Inf string` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateResponseModel` + + The Realtime model used for this session. + + - `string` + + - `type RealtimeSessionCreateResponseModel string` + + The Realtime model used for this session. + + - `const RealtimeSessionCreateResponseModelGPTRealtime RealtimeSessionCreateResponseModel = "gpt-realtime"` + + - `const RealtimeSessionCreateResponseModelGPTRealtime1_5 RealtimeSessionCreateResponseModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateResponseModelGPTRealtime2 RealtimeSessionCreateResponseModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateResponseModelGPTRealtime2025_08_28 RealtimeSessionCreateResponseModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateResponseModelGPT4oMiniRealtimePreview RealtimeSessionCreateResponseModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateResponseModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateResponseModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateResponseModelGPTRealtimeMini RealtimeSessionCreateResponseModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateResponseModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateResponseModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateResponseModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateResponseModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateResponseModelGPTAudio1_5 RealtimeSessionCreateResponseModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateResponseModelGPTAudioMini RealtimeSessionCreateResponseModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateResponseModelGPTAudioMini2025_10_06 RealtimeSessionCreateResponseModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateResponseModelGPTAudioMini2025_12_15 RealtimeSessionCreateResponseModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateResponseOutputModalityText RealtimeSessionCreateResponseOutputModality = "text"` + + - `const RealtimeSessionCreateResponseOutputModalityAudio RealtimeSessionCreateResponseOutputModality = "audio"` + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeSessionCreateResponseToolChoiceUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools []RealtimeSessionCreateResponseToolUnion` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `type RealtimeSessionCreateResponseToolMcpTool struct{…}` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeSessionCreateResponseToolMcpToolAllowedToolsUnion` + + List of allowed tool names or a filter object. + + - `type RealtimeSessionCreateResponseToolMcpToolAllowedToolsMcpAllowedTools []string` + + A string array of allowed tool names + + - `type RealtimeSessionCreateResponseToolMcpToolAllowedToolsMcpToolFilter struct{…}` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorDropbox RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_dropbox"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGmail RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_gmail"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGooglecalendar RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_googlecalendar"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGoogledrive RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_googledrive"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorMicrosoftteams RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_microsoftteams"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorOutlookcalendar RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_outlookcalendar"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorOutlookemail RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_outlookemail"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorSharepoint RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeSessionCreateResponseToolMcpToolRequireApprovalUnion` + + Specify which of the MCP server's tools require approval. + + - `type RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilter struct{…}` + + Specify which of the MCP server's tools require approval. Can be + `always`, `never`, or a filter object associated with tools + that require approval. + + - `Always RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `type RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting string` + + Specify a single approval policy for all tools. One of `always` or + `never`. When set to `always`, all tools will require approval. When + set to `never`, all tools will not require approval. + + - `const RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeSessionCreateResponseTracingUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `type Auto string` + + Enables tracing and sets default values for tracing configuration options. Always `auto`. + + - `const AutoAuto Auto = "auto"` + + - `type RealtimeSessionCreateResponseTracingTracingConfiguration struct{…}` + + Granular configuration for tracing. + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + + - `type RealtimeTranscriptionSessionCreateResponse struct{…}` + + A Realtime transcription session configuration object. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Object string` + + The object type. Always `realtime.transcription_session`. + + - `Type Transcription` + + The type of session. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionCreateResponseAudio` + + Configuration for input audio for the session. + + - `Input RealtimeTranscriptionSessionCreateResponseAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `NoiseReduction RealtimeTranscriptionSessionCreateResponseAudioInputNoiseReduction` + + Configuration for input audio noise reduction. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `Transcription AudioTranscription` + + - `TurnDetection RealtimeTranscriptionSessionTurnDetection` + + Configuration for turn detection. Can be set to `null` to turn off. Server + VAD means that the model will detect the start and end of speech based on + audio volume and respond at the end of user speech. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported. + + - `PrefixPaddingMs int64` + + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `Type string` + + Type of turn detection, only `server_vad` is currently supported. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Include []string` + + Additional fields to include in server outputs. + + - `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateResponseIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateResponseInclude = "item.input_audio_transcription.logprobs"` + + - `Value string` + + The generated client secret value. + +### Example + +```go +package main + +import ( + "context" + "fmt" + + "github.com/openai/openai-go" + "github.com/openai/openai-go/option" + "github.com/openai/openai-go/realtime" +) + +func main() { + client := openai.NewClient( + option.WithAPIKey("My API Key"), + ) + clientSecret, err := client.Realtime.ClientSecrets.New(context.TODO(), realtime.ClientSecretNewParams{ + + }) + if err != nil { + panic(err.Error()) + } + fmt.Printf("%+v\n", clientSecret.ExpiresAt) +} +``` + +#### Response + +```json +{ + "expires_at": 0, + "session": { + "id": "id", + "object": "realtime.session", + "type": "realtime", + "audio": { + "input": { + "format": { + "rate": 24000, + "type": "audio/pcm" + }, + "noise_reduction": { + "type": "near_field" + }, + "transcription": { + "delay": "minimal", + "language": "language", + "model": "whisper-1", + "prompt": "prompt" + }, + "turn_detection": { + "type": "server_vad", + "create_response": true, + "idle_timeout_ms": 5000, + "interrupt_response": true, + "prefix_padding_ms": 0, + "silence_duration_ms": 0, + "threshold": 0 + } + }, + "output": { + "format": { + "rate": 24000, + "type": "audio/pcm" + }, + "speed": 0.25, + "voice": "ash" + } + }, + "expires_at": 0, + "include": [ + "item.input_audio_transcription.logprobs" + ], + "instructions": "instructions", + "max_output_tokens": "inf", + "model": "gpt-realtime", + "output_modalities": [ + "text" + ], + "prompt": { + "id": "id", + "variables": { + "foo": "string" + }, + "version": "version" + }, + "reasoning": { + "effort": "minimal" + }, + "tool_choice": "none", + "tools": [ + { + "description": "description", + "name": "name", + "parameters": {}, + "type": "function" + } + ], + "tracing": "auto", + "truncation": "auto" + }, + "value": "value" +} +``` + +## Domain Types + +### Realtime Session Create Response + +- `type RealtimeSessionCreateResponse struct{…}` + + A Realtime session configuration object. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Object RealtimeSession` + + The object type. Always `realtime.session`. + + - `const RealtimeSessionRealtimeSession RealtimeSession = "realtime.session"` + + - `Type Realtime` + + The type of session to create. Always `realtime` for the Realtime API. + + - `const RealtimeRealtime Realtime = "realtime"` + + - `Audio RealtimeSessionCreateResponseAudio` + + Configuration for input and output audio. + + - `Input RealtimeSessionCreateResponseAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the input audio. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeSessionCreateResponseAudioInputNoiseReduction` + + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeSessionCreateResponseAudioInputTurnDetectionUnion` + + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + + For `gpt-realtime-whisper` transcription sessions, turn detection must be + set to `null`; VAD is not supported. + + - `type RealtimeSessionCreateResponseAudioInputTurnDetectionServerVad struct{…}` + + Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence. + + - `Type ServerVad` + + Type of turn detection, `server_vad` to turn on simple Server VAD. + + - `const ServerVadServerVad ServerVad = "server_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `IdleTimeoutMs int64` + + Optional timeout after which a model response will be triggered automatically. This is + useful for situations in which a long pause from the user is unexpected, such as a phone + call. The model will effectively prompt the user to continue the conversation based + on the current context. + + The timeout value will be applied after the last model response's audio has finished playing, + i.e. it's set to the `response.done` time plus audio playback duration. + + An `input_audio_buffer.timeout_triggered` event (plus events + associated with the Response) will be emitted when the timeout is reached. + Idle timeout is currently only supported for `server_vad` mode. + + - `InterruptResponse bool` + + Whether or not to automatically interrupt (cancel) any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete. + + If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted. + + - `PrefixPaddingMs int64` + + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `type RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVad struct{…}` + + Server-side semantic turn detection which uses a model to determine when the user has finished speaking. + + - `Type SemanticVad` + + Type of turn detection, `semantic_vad` to turn on Semantic VAD. + + - `const SemanticVadSemanticVad SemanticVad = "semantic_vad"` + + - `CreateResponse bool` + + Whether or not to automatically generate a response when a VAD stop event occurs. + + - `Eagerness string` + + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively. + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessLow RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "low"` + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessMedium RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "medium"` + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessHigh RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "high"` + + - `const RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagernessAuto RealtimeSessionCreateResponseAudioInputTurnDetectionSemanticVadEagerness = "auto"` + + - `InterruptResponse bool` + + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + + - `Output RealtimeSessionCreateResponseAudioOutput` + + - `Format RealtimeAudioFormatsUnion` + + The format of the output audio. + + - `Speed float64` + + The speed of the model's spoken response as a multiple of the original speed. + 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. + + This parameter is a post-processing adjustment to the audio after it is generated, it's + also possible to prompt the model to speak faster or slower. + + - `Voice string` + + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, + `shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for + best quality. + + - `string` + + - `string` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceAlloy RealtimeSessionCreateResponseAudioOutputVoice = "alloy"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceAsh RealtimeSessionCreateResponseAudioOutputVoice = "ash"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceBallad RealtimeSessionCreateResponseAudioOutputVoice = "ballad"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceCoral RealtimeSessionCreateResponseAudioOutputVoice = "coral"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceEcho RealtimeSessionCreateResponseAudioOutputVoice = "echo"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceSage RealtimeSessionCreateResponseAudioOutputVoice = "sage"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceShimmer RealtimeSessionCreateResponseAudioOutputVoice = "shimmer"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceVerse RealtimeSessionCreateResponseAudioOutputVoice = "verse"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceMarin RealtimeSessionCreateResponseAudioOutputVoice = "marin"` + + - `const RealtimeSessionCreateResponseAudioOutputVoiceCedar RealtimeSessionCreateResponseAudioOutputVoice = "cedar"` + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Include []string` + + Additional fields to include in server outputs. + + `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeSessionCreateResponseIncludeItemInputAudioTranscriptionLogprobs RealtimeSessionCreateResponseInclude = "item.input_audio_transcription.logprobs"` + + - `Instructions string` + + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + + - `MaxOutputTokens RealtimeSessionCreateResponseMaxOutputTokensUnion` + + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + + - `int64` + + - `type Inf string` + + - `const InfInf Inf = "inf"` + + - `Model RealtimeSessionCreateResponseModel` + + The Realtime model used for this session. + + - `string` + + - `type RealtimeSessionCreateResponseModel string` + + The Realtime model used for this session. + + - `const RealtimeSessionCreateResponseModelGPTRealtime RealtimeSessionCreateResponseModel = "gpt-realtime"` + + - `const RealtimeSessionCreateResponseModelGPTRealtime1_5 RealtimeSessionCreateResponseModel = "gpt-realtime-1.5"` + + - `const RealtimeSessionCreateResponseModelGPTRealtime2 RealtimeSessionCreateResponseModel = "gpt-realtime-2"` + + - `const RealtimeSessionCreateResponseModelGPTRealtime2025_08_28 RealtimeSessionCreateResponseModel = "gpt-realtime-2025-08-28"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2024_10_01 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2024-10-01"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2024_12_17 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateResponseModelGPT4oRealtimePreview2025_06_03 RealtimeSessionCreateResponseModel = "gpt-4o-realtime-preview-2025-06-03"` + + - `const RealtimeSessionCreateResponseModelGPT4oMiniRealtimePreview RealtimeSessionCreateResponseModel = "gpt-4o-mini-realtime-preview"` + + - `const RealtimeSessionCreateResponseModelGPT4oMiniRealtimePreview2024_12_17 RealtimeSessionCreateResponseModel = "gpt-4o-mini-realtime-preview-2024-12-17"` + + - `const RealtimeSessionCreateResponseModelGPTRealtimeMini RealtimeSessionCreateResponseModel = "gpt-realtime-mini"` + + - `const RealtimeSessionCreateResponseModelGPTRealtimeMini2025_10_06 RealtimeSessionCreateResponseModel = "gpt-realtime-mini-2025-10-06"` + + - `const RealtimeSessionCreateResponseModelGPTRealtimeMini2025_12_15 RealtimeSessionCreateResponseModel = "gpt-realtime-mini-2025-12-15"` + + - `const RealtimeSessionCreateResponseModelGPTAudio1_5 RealtimeSessionCreateResponseModel = "gpt-audio-1.5"` + + - `const RealtimeSessionCreateResponseModelGPTAudioMini RealtimeSessionCreateResponseModel = "gpt-audio-mini"` + + - `const RealtimeSessionCreateResponseModelGPTAudioMini2025_10_06 RealtimeSessionCreateResponseModel = "gpt-audio-mini-2025-10-06"` + + - `const RealtimeSessionCreateResponseModelGPTAudioMini2025_12_15 RealtimeSessionCreateResponseModel = "gpt-audio-mini-2025-12-15"` + + - `OutputModalities []string` + + The set of modalities the model can respond with. It defaults to `["audio"]`, indicating + that the model will respond with audio plus a transcript. `["text"]` can be used to make + the model respond with text only. It is not possible to request both `text` and `audio` at the same time. + + - `const RealtimeSessionCreateResponseOutputModalityText RealtimeSessionCreateResponseOutputModality = "text"` + + - `const RealtimeSessionCreateResponseOutputModalityAudio RealtimeSessionCreateResponseOutputModality = "audio"` + + - `Prompt ResponsePrompt` + + Reference to a prompt template and its variables. + [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). + + - `ID string` + + The unique identifier of the prompt template to use. + + - `Variables map[string, ResponsePromptVariableUnion]` + + Optional map of values to substitute in for variables in your + prompt. The substitution values can either be strings, or other + Response input types like images or files. + + - `string` + + - `type ResponseInputText struct{…}` + + A text input to the model. + + - `Text string` + + The text input to the model. + + - `Type InputText` + + The type of the input item. Always `input_text`. + + - `const InputTextInputText InputText = "input_text"` + + - `type ResponseInputImage struct{…}` + + An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). + + - `Detail ResponseInputImageDetail` + + The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. + + - `const ResponseInputImageDetailLow ResponseInputImageDetail = "low"` + + - `const ResponseInputImageDetailHigh ResponseInputImageDetail = "high"` + + - `const ResponseInputImageDetailAuto ResponseInputImageDetail = "auto"` + + - `const ResponseInputImageDetailOriginal ResponseInputImageDetail = "original"` + + - `Type InputImage` + + The type of the input item. Always `input_image`. + + - `const InputImageInputImage InputImage = "input_image"` + + - `FileID string` + + The ID of the file to be sent to the model. + + - `ImageURL string` + + The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. + + - `type ResponseInputFile struct{…}` + + A file input to the model. + + - `Type InputFile` + + The type of the input item. Always `input_file`. + + - `const InputFileInputFile InputFile = "input_file"` + + - `Detail ResponseInputFileDetail` + + The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. + + - `const ResponseInputFileDetailLow ResponseInputFileDetail = "low"` + + - `const ResponseInputFileDetailHigh ResponseInputFileDetail = "high"` + + - `FileData string` + + The content of the file to be sent to the model. + + - `FileID string` + + The ID of the file to be sent to the model. + + - `FileURL string` + + The URL of the file to be sent to the model. + + - `Filename string` + + The name of the file to be sent to the model. + + - `Version string` + + Optional version of the prompt template. + + - `Reasoning RealtimeReasoning` + + Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. + + - `Effort RealtimeReasoningEffort` + + Constrains effort on reasoning for reasoning-capable Realtime models such as + `gpt-realtime-2`. + + - `const RealtimeReasoningEffortMinimal RealtimeReasoningEffort = "minimal"` + + - `const RealtimeReasoningEffortLow RealtimeReasoningEffort = "low"` + + - `const RealtimeReasoningEffortMedium RealtimeReasoningEffort = "medium"` + + - `const RealtimeReasoningEffortHigh RealtimeReasoningEffort = "high"` + + - `const RealtimeReasoningEffortXhigh RealtimeReasoningEffort = "xhigh"` + + - `ToolChoice RealtimeSessionCreateResponseToolChoiceUnion` + + How the model chooses tools. Provide one of the string modes or force a specific + function/MCP tool. + + - `type ToolChoiceOptions string` + + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + + - `const ToolChoiceOptionsNone ToolChoiceOptions = "none"` + + - `const ToolChoiceOptionsAuto ToolChoiceOptions = "auto"` + + - `const ToolChoiceOptionsRequired ToolChoiceOptions = "required"` + + - `type ToolChoiceFunction struct{…}` + + Use this option to force the model to call a specific function. + + - `Name string` + + The name of the function to call. + + - `Type Function` + + For function calling, the type is always `function`. + + - `const FunctionFunction Function = "function"` + + - `type ToolChoiceMcp struct{…}` + + Use this option to force the model to call a specific tool on a remote MCP server. + + - `ServerLabel string` + + The label of the MCP server to use. + + - `Type Mcp` + + For MCP tools, the type is always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `Name string` + + The name of the tool to call on the server. + + - `Tools []RealtimeSessionCreateResponseToolUnion` + + Tools available to the model. + + - `type RealtimeFunctionTool struct{…}` + + - `Description string` + + The description of the function, including guidance on when and how + to call it, and guidance about what to tell the user when calling + (if anything). + + - `Name string` + + The name of the function. + + - `Parameters any` + + Parameters of the function in JSON Schema. + + - `Type RealtimeFunctionToolType` + + The type of the tool, i.e. `function`. + + - `const RealtimeFunctionToolTypeFunction RealtimeFunctionToolType = "function"` + + - `type RealtimeSessionCreateResponseToolMcpTool struct{…}` + + Give the model access to additional tools via remote Model Context Protocol + (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). + + - `ServerLabel string` + + A label for this MCP server, used to identify it in tool calls. + + - `Type Mcp` + + The type of the MCP tool. Always `mcp`. + + - `const McpMcp Mcp = "mcp"` + + - `AllowedTools RealtimeSessionCreateResponseToolMcpToolAllowedToolsUnion` + + List of allowed tool names or a filter object. + + - `type RealtimeSessionCreateResponseToolMcpToolAllowedToolsMcpAllowedTools []string` + + A string array of allowed tool names + + - `type RealtimeSessionCreateResponseToolMcpToolAllowedToolsMcpToolFilter struct{…}` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Authorization string` + + An OAuth access token that can be used with a remote MCP server, either + with a custom MCP server URL or a service connector. Your application + must handle the OAuth authorization flow and provide the token here. + + - `ConnectorID string` + + Identifier for service connectors, like those available in ChatGPT. One of + `server_url` or `connector_id` must be provided. Learn more about service + connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). + + Currently supported `connector_id` values are: + + - Dropbox: `connector_dropbox` + - Gmail: `connector_gmail` + - Google Calendar: `connector_googlecalendar` + - Google Drive: `connector_googledrive` + - Microsoft Teams: `connector_microsoftteams` + - Outlook Calendar: `connector_outlookcalendar` + - Outlook Email: `connector_outlookemail` + - SharePoint: `connector_sharepoint` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorDropbox RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_dropbox"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGmail RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_gmail"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGooglecalendar RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_googlecalendar"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorGoogledrive RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_googledrive"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorMicrosoftteams RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_microsoftteams"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorOutlookcalendar RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_outlookcalendar"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorOutlookemail RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_outlookemail"` + + - `const RealtimeSessionCreateResponseToolMcpToolConnectorIDConnectorSharepoint RealtimeSessionCreateResponseToolMcpToolConnectorID = "connector_sharepoint"` + + - `DeferLoading bool` + + Whether this MCP tool is deferred and discovered via tool search. + + - `Headers map[string, string]` + + Optional HTTP headers to send to the MCP server. Use for authentication + or other purposes. + + - `RequireApproval RealtimeSessionCreateResponseToolMcpToolRequireApprovalUnion` + + Specify which of the MCP server's tools require approval. + + - `type RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilter struct{…}` + + Specify which of the MCP server's tools require approval. Can be + `always`, `never`, or a filter object associated with tools + that require approval. + + - `Always RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilterAlways` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `Never RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalFilterNever` + + A filter object to specify which tools are allowed. + + - `ReadOnly bool` + + Indicates whether or not a tool modifies data or is read-only. If an + MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), + it will match this filter. + + - `ToolNames []string` + + List of allowed tool names. + + - `type RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting string` + + Specify a single approval policy for all tools. One of `always` or + `never`. When set to `always`, all tools will require approval. When + set to `never`, all tools will not require approval. + + - `const RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSettingAlways RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting = "always"` + + - `const RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSettingNever RealtimeSessionCreateResponseToolMcpToolRequireApprovalMcpToolApprovalSetting = "never"` + + - `ServerDescription string` + + Optional description of the MCP server, used to provide more context. + + - `ServerURL string` + + The URL for the MCP server. One of `server_url` or `connector_id` must be + provided. + + - `Tracing RealtimeSessionCreateResponseTracingUnion` + + Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + + - `type Auto string` + + Enables tracing and sets default values for tracing configuration options. Always `auto`. + + - `const AutoAuto Auto = "auto"` + + - `type RealtimeSessionCreateResponseTracingTracingConfiguration struct{…}` + + Granular configuration for tracing. + + - `GroupID string` + + The group id to attach to this trace to enable filtering and + grouping in the Traces Dashboard. + + - `Metadata any` + + The arbitrary metadata to attach to this trace to enable + filtering in the Traces Dashboard. + + - `WorkflowName string` + + The name of the workflow to attach to this trace. This is used to + name the trace in the Traces Dashboard. + + - `Truncation RealtimeTruncationUnion` + + When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. + + Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. + + Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. + + Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. + + - `type RealtimeTruncationRealtimeTruncationStrategy string` + + The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. + + - `const RealtimeTruncationRealtimeTruncationStrategyAuto RealtimeTruncationRealtimeTruncationStrategy = "auto"` + + - `const RealtimeTruncationRealtimeTruncationStrategyDisabled RealtimeTruncationRealtimeTruncationStrategy = "disabled"` + + - `type RealtimeTruncationRetentionRatio struct{…}` + + Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. + + - `RetentionRatio float64` + + Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. + + - `Type RetentionRatio` + + Use retention ratio truncation. + + - `const RetentionRatioRetentionRatio RetentionRatio = "retention_ratio"` + + - `TokenLimits RealtimeTruncationRetentionRatioTokenLimits` + + Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. + + - `PostInstructions int64` + + Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. + +### Realtime Transcription Session Create Response + +- `type RealtimeTranscriptionSessionCreateResponse struct{…}` + + A Realtime transcription session configuration object. + + - `ID string` + + Unique identifier for the session that looks like `sess_1234567890abcdef`. + + - `Object string` + + The object type. Always `realtime.transcription_session`. + + - `Type Transcription` + + The type of session. Always `transcription` for transcription sessions. + + - `const TranscriptionTranscription Transcription = "transcription"` + + - `Audio RealtimeTranscriptionSessionCreateResponseAudio` + + Configuration for input audio for the session. + + - `Input RealtimeTranscriptionSessionCreateResponseAudioInput` + + - `Format RealtimeAudioFormatsUnion` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `type RealtimeAudioFormatsAudioPCM struct{…}` + + The PCM audio format. Only a 24kHz sample rate is supported. + + - `Rate int64` + + The sample rate of the audio. Always `24000`. + + - `const RealtimeAudioFormatsAudioPCMRate24000 RealtimeAudioFormatsAudioPCMRate = 24000` + + - `Type string` + + The audio format. Always `audio/pcm`. + + - `const RealtimeAudioFormatsAudioPCMTypeAudioPCM RealtimeAudioFormatsAudioPCMType = "audio/pcm"` + + - `type RealtimeAudioFormatsAudioPCMU struct{…}` + + The G.711 μ-law format. + + - `Type string` + + The audio format. Always `audio/pcmu`. + + - `const RealtimeAudioFormatsAudioPCMUTypeAudioPCMU RealtimeAudioFormatsAudioPCMUType = "audio/pcmu"` + + - `type RealtimeAudioFormatsAudioPCMA struct{…}` + + The G.711 A-law format. + + - `Type string` + + The audio format. Always `audio/pcma`. + + - `const RealtimeAudioFormatsAudioPCMATypeAudioPCMA RealtimeAudioFormatsAudioPCMAType = "audio/pcma"` + + - `NoiseReduction RealtimeTranscriptionSessionCreateResponseAudioInputNoiseReduction` + + Configuration for input audio noise reduction. + + - `Type NoiseReductionType` + + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + + - `const NoiseReductionTypeNearField NoiseReductionType = "near_field"` + + - `const NoiseReductionTypeFarField NoiseReductionType = "far_field"` + + - `Transcription AudioTranscription` + + - `Delay AudioTranscriptionDelay` + + Controls how long the model waits before emitting transcription text. + Higher values can improve transcription accuracy at the cost of latency. + Only supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `const AudioTranscriptionDelayMinimal AudioTranscriptionDelay = "minimal"` + + - `const AudioTranscriptionDelayLow AudioTranscriptionDelay = "low"` + + - `const AudioTranscriptionDelayMedium AudioTranscriptionDelay = "medium"` + + - `const AudioTranscriptionDelayHigh AudioTranscriptionDelay = "high"` + + - `const AudioTranscriptionDelayXhigh AudioTranscriptionDelay = "xhigh"` + + - `Language string` + + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + + - `Model AudioTranscriptionModel` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `string` + + - `type AudioTranscriptionModel string` + + The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. + + - `const AudioTranscriptionModelWhisper1 AudioTranscriptionModel = "whisper-1"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe AudioTranscriptionModel = "gpt-4o-mini-transcribe"` + + - `const AudioTranscriptionModelGPT4oMiniTranscribe2025_12_15 AudioTranscriptionModel = "gpt-4o-mini-transcribe-2025-12-15"` + + - `const AudioTranscriptionModelGPT4oTranscribe AudioTranscriptionModel = "gpt-4o-transcribe"` + + - `const AudioTranscriptionModelGPT4oTranscribeDiarize AudioTranscriptionModel = "gpt-4o-transcribe-diarize"` + + - `const AudioTranscriptionModelGPTRealtimeWhisper AudioTranscriptionModel = "gpt-realtime-whisper"` + + - `Prompt string` + + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". + Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. + + - `TurnDetection RealtimeTranscriptionSessionTurnDetection` + + Configuration for turn detection. Can be set to `null` to turn off. Server + VAD means that the model will detect the start and end of speech based on + audio volume and respond at the end of user speech. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported. + + - `PrefixPaddingMs int64` + + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `Type string` + + Type of turn detection, only `server_vad` is currently supported. + + - `ExpiresAt int64` + + Expiration timestamp for the session, in seconds since epoch. + + - `Include []string` + + Additional fields to include in server outputs. + + - `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. + + - `const RealtimeTranscriptionSessionCreateResponseIncludeItemInputAudioTranscriptionLogprobs RealtimeTranscriptionSessionCreateResponseInclude = "item.input_audio_transcription.logprobs"` + +### Realtime Transcription Session Turn Detection + +- `type RealtimeTranscriptionSessionTurnDetection struct{…}` + + Configuration for turn detection. Can be set to `null` to turn off. Server + VAD means that the model will detect the start and end of speech based on + audio volume and respond at the end of user speech. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported. + + - `PrefixPaddingMs int64` + + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + + - `SilenceDurationMs int64` + + Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + + - `Threshold float64` + + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + + - `Type string` + + Type of turn detection, only `server_vad` is currently supported. + +# Calls + +## Accept call + +`client.Realtime.Calls.Accept(ctx, callID, body) error` + +**post** `/realtime/calls/{call_id}/accept` + +Accept an incoming SIP call and configure the realtime session that will +handle it. + +### Parameters + +- `callID string` + +- `body CallAcceptParams` + + - `RealtimeSessionCreateRequest param.Field[RealtimeSessionCreateRequest]` + + Realtime session object configuration. + +### Example + +```go +package main + +import ( + "context" + + "github.com/openai/openai-go" + "github.com/openai/openai-go/option" + "github.com/openai/openai-go/realtime" +) + +func main() { + client := openai.NewClient( + option.WithAPIKey("My API Key"), + ) + err := client.Realtime.Calls.Accept( + context.TODO(), + "call_id", + realtime.CallAcceptParams{ + RealtimeSessionCreateRequest: realtime.RealtimeSessionCreateRequestParam{ + + }, + }, + ) + if err != nil { + panic(err.Error()) + } +} +``` + +## Hang up call + +`client.Realtime.Calls.Hangup(ctx, callID) error` + +**post** `/realtime/calls/{call_id}/hangup` + +End an active Realtime API call, whether it was initiated over SIP or +WebRTC. + +### Parameters + +- `callID string` + +### Example + +```go +package main + +import ( + "context" + + "github.com/openai/openai-go" + "github.com/openai/openai-go/option" +) + +func main() { + client := openai.NewClient( + option.WithAPIKey("My API Key"), + ) + err := client.Realtime.Calls.Hangup(context.TODO(), "call_id") + if err != nil { + panic(err.Error()) + } +} +``` + +## Refer call + +`client.Realtime.Calls.Refer(ctx, callID, body) error` + +**post** `/realtime/calls/{call_id}/refer` + +Transfer an active SIP call to a new destination using the SIP REFER verb. + +### Parameters + +- `callID string` + +- `body CallReferParams` + + - `TargetUri param.Field[string]` + + URI that should appear in the SIP Refer-To header. Supports values like + `tel:+14155550123` or `sip:agent@example.com`. + +### Example + +```go +package main + +import ( + "context" + + "github.com/openai/openai-go" + "github.com/openai/openai-go/option" + "github.com/openai/openai-go/realtime" +) + +func main() { + client := openai.NewClient( + option.WithAPIKey("My API Key"), + ) + err := client.Realtime.Calls.Refer( + context.TODO(), + "call_id", + realtime.CallReferParams{ + TargetUri: "tel:+14155550123", + }, + ) + if err != nil { + panic(err.Error()) + } +} +``` + +## Reject call + +`client.Realtime.Calls.Reject(ctx, callID, body) error` + +**post** `/realtime/calls/{call_id}/reject` + +Decline an incoming SIP call by returning a SIP status code to the caller. + +### Parameters + +- `callID string` + +- `body CallRejectParams` + + - `StatusCode param.Field[int64]` + + SIP response code to send back to the caller. Defaults to `603` (Decline) + when omitted. + +### Example + +```go +package main + +import ( + "context" + + "github.com/openai/openai-go" + "github.com/openai/openai-go/option" + "github.com/openai/openai-go/realtime" +) + +func main() { + client := openai.NewClient( + option.WithAPIKey("My API Key"), + ) + err := client.Realtime.Calls.Reject( + context.TODO(), + "call_id", + realtime.CallRejectParams{ + + }, + ) + if err != nil { + panic(err.Error()) + } +} +``` + +# Translations + +# Client Secrets + +# Sessions + +# Transcription Sessions