Transcriptions

Create transcription

client.Audio.Transcriptions.New(ctx, body) (*AudioTranscriptionNewResponseUnion, error)

post /audio/transcriptions

Create transcription

Parameters

body AudioTranscriptionNewParams
- File param.Field[Reader]
  
  The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
- Model param.Field[AudioModel]
  
  ID of the model to use. The options are gpt-4o-transcribe, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, whisper-1 (which is powered by our open source Whisper V2 model), and gpt-4o-transcribe-diarize.
  - string
  - type AudioModel string
    - const AudioModelWhisper1 AudioModel = "whisper-1"
    - const AudioModelGPT4oTranscribe AudioModel = "gpt-4o-transcribe"
    - const AudioModelGPT4oMiniTranscribe AudioModel = "gpt-4o-mini-transcribe"
    - const AudioModelGPT4oMiniTranscribe2025_12_15 AudioModel = "gpt-4o-mini-transcribe-2025-12-15"
    - const AudioModelGPT4oTranscribeDiarize AudioModel = "gpt-4o-transcribe-diarize"
- ChunkingStrategy param.Field[any]
- Include param.Field[[]TranscriptionInclude]
  
  Additional information to include in the transcription response. logprobs will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription. logprobs only works with response_format set to json and only with the models gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-mini-transcribe-2025-12-15. This field is not supported when using gpt-4o-transcribe-diarize.
  - const TranscriptionIncludeLogprobs TranscriptionInclude = "logprobs"
- KnownSpeakerNames param.Field[[]string]
  
  Optional list of speaker names that correspond to the audio samples provided in known_speaker_references[]. Each entry should be a short identifier (for example customer or agent). Up to 4 speakers are supported.
- KnownSpeakerReferences param.Field[[]string]
  
  Optional list of audio samples (as data URLs) that contain known speaker references matching known_speaker_names[]. Each sample must be between 2 and 10 seconds, and can use any of the same input audio formats supported by file.
- Language param.Field[string]
  
  The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.
- Prompt param.Field[string]
  
  An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. This field is not supported when using gpt-4o-transcribe-diarize.
- ResponseFormat param.Field[AudioResponseFormat]
  
  The format of the output, in one of these options: json, text, srt, verbose_json, vtt, or diarized_json. For gpt-4o-transcribe and gpt-4o-mini-transcribe, the only supported format is json. For gpt-4o-transcribe-diarize, the supported formats are json, text, and diarized_json, with diarized_json required to receive speaker annotations.
- ``
- Temperature param.Field[float64]
  
  The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
- TimestampGranularities param.Field[[]string]
  
  The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. This option is not available for gpt-4o-transcribe-diarize.
  - const AudioTranscriptionNewParamsTimestampGranularityWord AudioTranscriptionNewParamsTimestampGranularity = "word"
  - const AudioTranscriptionNewParamsTimestampGranularitySegment AudioTranscriptionNewParamsTimestampGranularity = "segment"

Returns

type AudioTranscriptionNewResponseUnion interface{…}

Represents a transcription response returned by model, based on the provided input.
- type Transcription struct{…}
  
  Represents a transcription response returned by model, based on the provided input.
  - Text string
    
    The transcribed text.
  - Logprobs []TranscriptionLogprob
    
    The log probabilities of the tokens in the transcription. Only returned with the models gpt-4o-transcribe and gpt-4o-mini-transcribe if logprobs is added to the include array.
    - Token string
      
      The token in the transcription.
    - Bytes []float64
      
      The bytes of the token.
    - Logprob float64
      
      The log probability of the token.
  - Usage TranscriptionUsageUnion
    
    Token usage statistics for the request.
    - type TranscriptionUsageTokens struct{…}
      
      Usage statistics for models billed by token usage.
      - 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 TranscriptionUsageTokensInputTokenDetails
        
        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.
    - type TranscriptionUsageDuration struct{…}
      
      Usage statistics for models billed by audio input duration.
      - 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"
- type TranscriptionVerbose struct{…}
  
  Represents a verbose json transcription response returned by model, based on the provided input.
  - Duration float64
    
    The duration of the input audio.
  - Language string
    
    The language of the input audio.
  - Text string
    
    The transcribed text.
  - Segments []TranscriptionSegment
    
    Segments of the transcribed text and their corresponding details.
    - ID int64
      
      Unique identifier of the segment.
    - AvgLogprob float64
      
      Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
    - CompressionRatio float64
      
      Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
    - End float64
      
      End time of the segment in seconds.
    - NoSpeechProb float64
      
      Probability of no speech in the segment. If the value is higher than 1.0 and the avg_logprob is below -1, consider this segment silent.
    - Seek int64
      
      Seek offset of the segment.
    - Start float64
      
      Start time of the segment in seconds.
    - Temperature float64
      
      Temperature parameter used for generating the segment.
    - Text string
      
      Text content of the segment.
    - Tokens []int64
      
      Array of token IDs for the text content.
  - Usage TranscriptionVerboseUsage
    
    Usage statistics for models billed by audio input duration.
    - 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"
  - Words []TranscriptionWord
    
    Extracted words and their corresponding timestamps.
    - End float64
      
      End time of the word in seconds.
    - Start float64
      
      Start time of the word in seconds.
    - Word string
      
      The text content of the word.

Example

package main

import (
  "bytes"
  "context"
  "fmt"
  "io"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  transcription, err := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
    File: io.Reader(bytes.NewBuffer([]byte("Example data"))),
    Model: openai.AudioModelGPT4oTranscribe,
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", transcription)
}

Response

{
  "text": "text",
  "logprobs": [
    {
      "token": "token",
      "bytes": [
        0
      ],
      "logprob": 0
    }
  ],
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0,
    "type": "tokens",
    "input_token_details": {
      "audio_tokens": 0,
      "text_tokens": 0
    }
  }
}

Domain Types

Transcription

type Transcription struct{…}

Represents a transcription response returned by model, based on the provided input.
- Text string
  
  The transcribed text.
- Logprobs []TranscriptionLogprob
  
  The log probabilities of the tokens in the transcription. Only returned with the models gpt-4o-transcribe and gpt-4o-mini-transcribe if logprobs is added to the include array.
  - Token string
    
    The token in the transcription.
  - Bytes []float64
    
    The bytes of the token.
  - Logprob float64
    
    The log probability of the token.
- Usage TranscriptionUsageUnion
  
  Token usage statistics for the request.
  - type TranscriptionUsageTokens struct{…}
    
    Usage statistics for models billed by token usage.
    - 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 TranscriptionUsageTokensInputTokenDetails
      
      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.
  - type TranscriptionUsageDuration struct{…}
    
    Usage statistics for models billed by audio input duration.
    - 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"

Transcription Diarized

type TranscriptionDiarized struct{…}

Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations.
- Duration float64
  
  Duration of the input audio in seconds.
- Segments []TranscriptionDiarizedSegment
  
  Segments of the transcript annotated with timestamps and speaker labels.
  - ID string
    
    Unique identifier for the segment.
  - End float64
    
    End timestamp of the segment in seconds.
  - Speaker string
    
    Speaker label for this segment. When known speakers are provided, the label matches known_speaker_names[]. Otherwise speakers are labeled sequentially using capital letters (A, B, ...).
  - Start float64
    
    Start timestamp of the segment in seconds.
  - Text string
    
    Transcript text for this segment.
  - Type TranscriptTextSegment
    
    The type of the segment. Always transcript.text.segment.
    - const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"
- Task Transcribe
  
  The type of task that was run. Always transcribe.
  - const TranscribeTranscribe Transcribe = "transcribe"
- Text string
  
  The concatenated transcript text for the entire audio input.
- Usage TranscriptionDiarizedUsageUnion
  
  Token or duration usage statistics for the request.
  - TranscriptionDiarizedUsageTokens
    - 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 TranscriptionDiarizedUsageTokensInputTokenDetails
      
      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.
  - TranscriptionDiarizedUsageDuration
    - 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"

Transcription Diarized Segment

type TranscriptionDiarizedSegment struct{…}

A segment of diarized transcript text with speaker metadata.
- ID string
  
  Unique identifier for the segment.
- End float64
  
  End timestamp of the segment in seconds.
- Speaker string
  
  Speaker label for this segment. When known speakers are provided, the label matches known_speaker_names[]. Otherwise speakers are labeled sequentially using capital letters (A, B, ...).
- Start float64
  
  Start timestamp of the segment in seconds.
- Text string
  
  Transcript text for this segment.
- Type TranscriptTextSegment
  
  The type of the segment. Always transcript.text.segment.
  - const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"

Transcription Include

type TranscriptionInclude string
- const TranscriptionIncludeLogprobs TranscriptionInclude = "logprobs"

Transcription Segment

type TranscriptionSegment struct{…}
- ID int64
  
  Unique identifier of the segment.
- AvgLogprob float64
  
  Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
- CompressionRatio float64
  
  Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
- End float64
  
  End time of the segment in seconds.
- NoSpeechProb float64
  
  Probability of no speech in the segment. If the value is higher than 1.0 and the avg_logprob is below -1, consider this segment silent.
- Seek int64
  
  Seek offset of the segment.
- Start float64
  
  Start time of the segment in seconds.
- Temperature float64
  
  Temperature parameter used for generating the segment.
- Text string
  
  Text content of the segment.
- Tokens []int64
  
  Array of token IDs for the text content.

Transcription Stream Event

type TranscriptionStreamEventUnion interface{…}

Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you create a transcription with stream set to true and response_format set to diarized_json.
- type TranscriptionTextSegmentEvent struct{…}
  
  Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you create a transcription with stream set to true and response_format set to diarized_json.
  - ID string
    
    Unique identifier for the segment.
  - End float64
    
    End timestamp of the segment in seconds.
  - Speaker string
    
    Speaker label for this segment.
  - Start float64
    
    Start timestamp of the segment in seconds.
  - Text string
    
    Transcript text for this segment.
  - Type TranscriptTextSegment
    
    The type of the event. Always transcript.text.segment.
    - const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"
- type TranscriptionTextDeltaEvent struct{…}
  
  Emitted when there is an additional text delta. This is also the first event emitted when the transcription starts. Only emitted when you create a transcription with the Stream parameter set to true.
  - Delta string
    
    The text delta that was additionally transcribed.
  - Type TranscriptTextDelta
    
    The type of the event. Always transcript.text.delta.
    - const TranscriptTextDeltaTranscriptTextDelta TranscriptTextDelta = "transcript.text.delta"
  - Logprobs []TranscriptionTextDeltaEventLogprob
    
    The log probabilities of the delta. Only included if you create a transcription with the include[] parameter set to logprobs.
    - 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.
  - SegmentID string
    
    Identifier of the diarized segment that this delta belongs to. Only present when using gpt-4o-transcribe-diarize.
- type TranscriptionTextDoneEvent struct{…}
  
  Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you create a transcription with the Stream parameter set to true.
  - Text string
    
    The text that was transcribed.
  - Type TranscriptTextDone
    
    The type of the event. Always transcript.text.done.
    - const TranscriptTextDoneTranscriptTextDone TranscriptTextDone = "transcript.text.done"
  - Logprobs []TranscriptionTextDoneEventLogprob
    
    The log probabilities of the individual tokens in the transcription. Only included if you create a transcription with the include[] parameter set to logprobs.
    - 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.
  - Usage TranscriptionTextDoneEventUsage
    
    Usage statistics for models billed by token usage.
    - 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 TranscriptionTextDoneEventUsageInputTokenDetails
      
      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.

Transcription Text Delta Event

type TranscriptionTextDeltaEvent struct{…}

Emitted when there is an additional text delta. This is also the first event emitted when the transcription starts. Only emitted when you create a transcription with the Stream parameter set to true.
- Delta string
  
  The text delta that was additionally transcribed.
- Type TranscriptTextDelta
  
  The type of the event. Always transcript.text.delta.
  - const TranscriptTextDeltaTranscriptTextDelta TranscriptTextDelta = "transcript.text.delta"
- Logprobs []TranscriptionTextDeltaEventLogprob
  
  The log probabilities of the delta. Only included if you create a transcription with the include[] parameter set to logprobs.
  - 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.
- SegmentID string
  
  Identifier of the diarized segment that this delta belongs to. Only present when using gpt-4o-transcribe-diarize.

Transcription Text Done Event

type TranscriptionTextDoneEvent struct{…}

Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you create a transcription with the Stream parameter set to true.
- Text string
  
  The text that was transcribed.
- Type TranscriptTextDone
  
  The type of the event. Always transcript.text.done.
  - const TranscriptTextDoneTranscriptTextDone TranscriptTextDone = "transcript.text.done"
- Logprobs []TranscriptionTextDoneEventLogprob
  
  The log probabilities of the individual tokens in the transcription. Only included if you create a transcription with the include[] parameter set to logprobs.
  - 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.
- Usage TranscriptionTextDoneEventUsage
  
  Usage statistics for models billed by token usage.
  - 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 TranscriptionTextDoneEventUsageInputTokenDetails
    
    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.

Transcription Text Segment Event

type TranscriptionTextSegmentEvent struct{…}

Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you create a transcription with stream set to true and response_format set to diarized_json.
- ID string
  
  Unique identifier for the segment.
- End float64
  
  End timestamp of the segment in seconds.
- Speaker string
  
  Speaker label for this segment.
- Start float64
  
  Start timestamp of the segment in seconds.
- Text string
  
  Transcript text for this segment.
- Type TranscriptTextSegment
  
  The type of the event. Always transcript.text.segment.
  - const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"

Transcription Verbose

type TranscriptionVerbose struct{…}

Represents a verbose json transcription response returned by model, based on the provided input.
- Duration float64
  
  The duration of the input audio.
- Language string
  
  The language of the input audio.
- Text string
  
  The transcribed text.
- Segments []TranscriptionSegment
  
  Segments of the transcribed text and their corresponding details.
  - ID int64
    
    Unique identifier of the segment.
  - AvgLogprob float64
    
    Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
  - CompressionRatio float64
    
    Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
  - End float64
    
    End time of the segment in seconds.
  - NoSpeechProb float64
    
    Probability of no speech in the segment. If the value is higher than 1.0 and the avg_logprob is below -1, consider this segment silent.
  - Seek int64
    
    Seek offset of the segment.
  - Start float64
    
    Start time of the segment in seconds.
  - Temperature float64
    
    Temperature parameter used for generating the segment.
  - Text string
    
    Text content of the segment.
  - Tokens []int64
    
    Array of token IDs for the text content.
- Usage TranscriptionVerboseUsage
  
  Usage statistics for models billed by audio input duration.
  - 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"
- Words []TranscriptionWord
  
  Extracted words and their corresponding timestamps.
  - End float64
    
    End time of the word in seconds.
  - Start float64
    
    Start time of the word in seconds.
  - Word string
    
    The text content of the word.

Transcription Word

type TranscriptionWord struct{…}
- End float64
  
  End time of the word in seconds.
- Start float64
  
  Start time of the word in seconds.
- Word string
  
  The text content of the word.

go/resources/audio/subresources/transcriptions/index.md +947 −0 created

1# Transcriptions

3## Create transcription

5`client.Audio.Transcriptions.New(ctx, body) (*AudioTranscriptionNewResponseUnion, error)`

7**post** `/audio/transcriptions`

9Create transcription

11### Parameters

13- `body AudioTranscriptionNewParams`

15 - `File param.Field[Reader]`

17 The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

19 - `Model param.Field[AudioModel]`

21 ID of the model to use. The options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1` (which is powered by our open source Whisper V2 model), and `gpt-4o-transcribe-diarize`.

23 - `string`

25 - `type AudioModel string`

27 - `const AudioModelWhisper1 AudioModel = "whisper-1"`

29 - `const AudioModelGPT4oTranscribe AudioModel = "gpt-4o-transcribe"`

31 - `const AudioModelGPT4oMiniTranscribe AudioModel = "gpt-4o-mini-transcribe"`

33 - `const AudioModelGPT4oMiniTranscribe2025_12_15 AudioModel = "gpt-4o-mini-transcribe-2025-12-15"`

35 - `const AudioModelGPT4oTranscribeDiarize AudioModel = "gpt-4o-transcribe-diarize"`

37 - `ChunkingStrategy param.Field[any]`

39 - `Include param.Field[[]TranscriptionInclude]`

41 Additional information to include in the transcription response.

42 `logprobs` will return the log probabilities of the tokens in the

43 response to understand the model's confidence in the transcription.

44 `logprobs` only works with response_format set to `json` and only with

45 the models `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is not supported when using `gpt-4o-transcribe-diarize`.

47 - `const TranscriptionIncludeLogprobs TranscriptionInclude = "logprobs"`

49 - `KnownSpeakerNames param.Field[[]string]`

51 Optional list of speaker names that correspond to the audio samples provided in `known_speaker_references[]`. Each entry should be a short identifier (for example `customer` or `agent`). Up to 4 speakers are supported.

53 - `KnownSpeakerReferences param.Field[[]string]`

55 Optional list of audio samples (as [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs)) that contain known speaker references matching `known_speaker_names[]`. Each sample must be between 2 and 10 seconds, and can use any of the same input audio formats supported by `file`.

57 - `Language param.Field[string]`

59 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.

61 - `Prompt param.Field[string]`

63 An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting) should match the audio language. This field is not supported when using `gpt-4o-transcribe-diarize`.

65 - `ResponseFormat param.Field[AudioResponseFormat]`

67 The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`, the only supported format is `json`. For `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and `diarized_json`, with `diarized_json` required to receive speaker annotations.

69 - ``

71 - `Temperature param.Field[float64]`

73 The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.

75 - `TimestampGranularities param.Field[[]string]`

77 The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

78 This option is not available for `gpt-4o-transcribe-diarize`.

80 - `const AudioTranscriptionNewParamsTimestampGranularityWord AudioTranscriptionNewParamsTimestampGranularity = "word"`

82 - `const AudioTranscriptionNewParamsTimestampGranularitySegment AudioTranscriptionNewParamsTimestampGranularity = "segment"`

84### Returns

86- `type AudioTranscriptionNewResponseUnion interface{…}`

88 Represents a transcription response returned by model, based on the provided input.

90 - `type Transcription struct{…}`

92 Represents a transcription response returned by model, based on the provided input.

94 - `Text string`

96 The transcribed text.

98 - `Logprobs []TranscriptionLogprob`

100 The log probabilities of the tokens in the transcription. Only returned with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array.

101

102 - `Token string`

103

104 The token in the transcription.

105

106 - `Bytes []float64`

107

108 The bytes of the token.

109

110 - `Logprob float64`

111

112 The log probability of the token.

113

114 - `Usage TranscriptionUsageUnion`

115

116 Token usage statistics for the request.

117

118 - `type TranscriptionUsageTokens struct{…}`

119

120 Usage statistics for models billed by token usage.

121

122 - `InputTokens int64`

123

124 Number of input tokens billed for this request.

125

126 - `OutputTokens int64`

127

128 Number of output tokens generated.

129

130 - `TotalTokens int64`

131

132 Total number of tokens used (input + output).

133

134 - `Type Tokens`

135

136 The type of the usage object. Always `tokens` for this variant.

137

138 - `const TokensTokens Tokens = "tokens"`

139

140 - `InputTokenDetails TranscriptionUsageTokensInputTokenDetails`

141

142 Details about the input tokens billed for this request.

143

144 - `AudioTokens int64`

145

146 Number of audio tokens billed for this request.

147

148 - `TextTokens int64`

149

150 Number of text tokens billed for this request.

151

152 - `type TranscriptionUsageDuration struct{…}`

153

154 Usage statistics for models billed by audio input duration.

155

156 - `Seconds float64`

157

158 Duration of the input audio in seconds.

159

160 - `Type Duration`

161

162 The type of the usage object. Always `duration` for this variant.

163

164 - `const DurationDuration Duration = "duration"`

165

166 - `type TranscriptionVerbose struct{…}`

167

168 Represents a verbose json transcription response returned by model, based on the provided input.

169

170 - `Duration float64`

171

172 The duration of the input audio.

173

174 - `Language string`

175

176 The language of the input audio.

177

178 - `Text string`

179

180 The transcribed text.

181

182 - `Segments []TranscriptionSegment`

183

184 Segments of the transcribed text and their corresponding details.

185

186 - `ID int64`

187

188 Unique identifier of the segment.

189

190 - `AvgLogprob float64`

191

192 Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.

193

194 - `CompressionRatio float64`

195

196 Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.

197

198 - `End float64`

199

200 End time of the segment in seconds.

201

202 - `NoSpeechProb float64`

203

204 Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent.

205

206 - `Seek int64`

207

208 Seek offset of the segment.

209

210 - `Start float64`

211

212 Start time of the segment in seconds.

213

214 - `Temperature float64`

215

216 Temperature parameter used for generating the segment.

217

218 - `Text string`

219

220 Text content of the segment.

221

222 - `Tokens []int64`

223

224 Array of token IDs for the text content.

225

226 - `Usage TranscriptionVerboseUsage`

227

228 Usage statistics for models billed by audio input duration.

229

230 - `Seconds float64`

231

232 Duration of the input audio in seconds.

233

234 - `Type Duration`

235

236 The type of the usage object. Always `duration` for this variant.

237

238 - `const DurationDuration Duration = "duration"`

239

240 - `Words []TranscriptionWord`

241

242 Extracted words and their corresponding timestamps.

243

244 - `End float64`

245

246 End time of the word in seconds.

247

248 - `Start float64`

249

250 Start time of the word in seconds.

251

252 - `Word string`

253

254 The text content of the word.

255

256### Example

257

258```go

259package main

260

261import (

262 "bytes"

263 "context"

264 "fmt"

265 "io"

266

267 "github.com/openai/openai-go"

268 "github.com/openai/openai-go/option"

269)

270

271func main() {

272 client := openai.NewClient(

273 option.WithAPIKey("My API Key"),

274 )

275 transcription, err := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{

276 File: io.Reader(bytes.NewBuffer([]byte("Example data"))),

277 Model: openai.AudioModelGPT4oTranscribe,

278 })

279 if err != nil {

280 panic(err.Error())

281 }

282 fmt.Printf("%+v\n", transcription)

283}

284```

285

286#### Response

287

288```json

289{

290 "text": "text",

291 "logprobs": [

292 {

293 "token": "token",

294 "bytes": [

295 0

296 ],

297 "logprob": 0

298 }

299 ],

300 "usage": {

301 "input_tokens": 0,

302 "output_tokens": 0,

303 "total_tokens": 0,

304 "type": "tokens",

305 "input_token_details": {

306 "audio_tokens": 0,

307 "text_tokens": 0

308 }

309 }

310}

311```

312

313## Domain Types

314

315### Transcription

316

317- `type Transcription struct{…}`

318

319 Represents a transcription response returned by model, based on the provided input.

320

321 - `Text string`

322

323 The transcribed text.

324

325 - `Logprobs []TranscriptionLogprob`

326

327 The log probabilities of the tokens in the transcription. Only returned with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array.

328

329 - `Token string`

330

331 The token in the transcription.

332

333 - `Bytes []float64`

334

335 The bytes of the token.

336

337 - `Logprob float64`

338

339 The log probability of the token.

340

341 - `Usage TranscriptionUsageUnion`

342

343 Token usage statistics for the request.

344

345 - `type TranscriptionUsageTokens struct{…}`

346

347 Usage statistics for models billed by token usage.

348

349 - `InputTokens int64`

350

351 Number of input tokens billed for this request.

352

353 - `OutputTokens int64`

354

355 Number of output tokens generated.

356

357 - `TotalTokens int64`

358

359 Total number of tokens used (input + output).

360

361 - `Type Tokens`

362

363 The type of the usage object. Always `tokens` for this variant.

364

365 - `const TokensTokens Tokens = "tokens"`

366

367 - `InputTokenDetails TranscriptionUsageTokensInputTokenDetails`

368

369 Details about the input tokens billed for this request.

370

371 - `AudioTokens int64`

372

373 Number of audio tokens billed for this request.

374

375 - `TextTokens int64`

376

377 Number of text tokens billed for this request.

378

379 - `type TranscriptionUsageDuration struct{…}`

380

381 Usage statistics for models billed by audio input duration.

382

383 - `Seconds float64`

384

385 Duration of the input audio in seconds.

386

387 - `Type Duration`

388

389 The type of the usage object. Always `duration` for this variant.

390

391 - `const DurationDuration Duration = "duration"`

392

393### Transcription Diarized

394

395- `type TranscriptionDiarized struct{…}`

396

397 Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations.

398

399 - `Duration float64`

400

401 Duration of the input audio in seconds.

402

403 - `Segments []TranscriptionDiarizedSegment`

404

405 Segments of the transcript annotated with timestamps and speaker labels.

406

407 - `ID string`

408

409 Unique identifier for the segment.

410

411 - `End float64`

412

413 End timestamp of the segment in seconds.

414

415 - `Speaker string`

416

417 Speaker label for this segment. When known speakers are provided, the label matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially using capital letters (`A`, `B`, ...).

418

419 - `Start float64`

420

421 Start timestamp of the segment in seconds.

422

423 - `Text string`

424

425 Transcript text for this segment.

426

427 - `Type TranscriptTextSegment`

428

429 The type of the segment. Always `transcript.text.segment`.

430

431 - `const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"`

432

433 - `Task Transcribe`

434

435 The type of task that was run. Always `transcribe`.

436

437 - `const TranscribeTranscribe Transcribe = "transcribe"`

438

439 - `Text string`

440

441 The concatenated transcript text for the entire audio input.

442

443 - `Usage TranscriptionDiarizedUsageUnion`

444

445 Token or duration usage statistics for the request.

446

447 - `TranscriptionDiarizedUsageTokens`

448

449 - `InputTokens int64`

450

451 Number of input tokens billed for this request.

452

453 - `OutputTokens int64`

454

455 Number of output tokens generated.

456

457 - `TotalTokens int64`

458

459 Total number of tokens used (input + output).

460

461 - `Type Tokens`

462

463 The type of the usage object. Always `tokens` for this variant.

464

465 - `const TokensTokens Tokens = "tokens"`

466

467 - `InputTokenDetails TranscriptionDiarizedUsageTokensInputTokenDetails`

468

469 Details about the input tokens billed for this request.

470

471 - `AudioTokens int64`

472

473 Number of audio tokens billed for this request.

474

475 - `TextTokens int64`

476

477 Number of text tokens billed for this request.

478

479 - `TranscriptionDiarizedUsageDuration`

480

481 - `Seconds float64`

482

483 Duration of the input audio in seconds.

484

485 - `Type Duration`

486

487 The type of the usage object. Always `duration` for this variant.

488

489 - `const DurationDuration Duration = "duration"`

490

491### Transcription Diarized Segment

492

493- `type TranscriptionDiarizedSegment struct{…}`

494

495 A segment of diarized transcript text with speaker metadata.

496

497 - `ID string`

498

499 Unique identifier for the segment.

500

501 - `End float64`

502

503 End timestamp of the segment in seconds.

504

505 - `Speaker string`

506

507 Speaker label for this segment. When known speakers are provided, the label matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially using capital letters (`A`, `B`, ...).

508

509 - `Start float64`

510

511 Start timestamp of the segment in seconds.

512

513 - `Text string`

514

515 Transcript text for this segment.

516

517 - `Type TranscriptTextSegment`

518

519 The type of the segment. Always `transcript.text.segment`.

520

521 - `const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"`

522

523### Transcription Include

524

525- `type TranscriptionInclude string`

526

527 - `const TranscriptionIncludeLogprobs TranscriptionInclude = "logprobs"`

528

529### Transcription Segment

530

531- `type TranscriptionSegment struct{…}`

532

533 - `ID int64`

534

535 Unique identifier of the segment.

536

537 - `AvgLogprob float64`

538

539 Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.

540

541 - `CompressionRatio float64`

542

543 Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.

544

545 - `End float64`

546

547 End time of the segment in seconds.

548

549 - `NoSpeechProb float64`

550

551 Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent.

552

553 - `Seek int64`

554

555 Seek offset of the segment.

556

557 - `Start float64`

558

559 Start time of the segment in seconds.

560

561 - `Temperature float64`

562

563 Temperature parameter used for generating the segment.

564

565 - `Text string`

566

567 Text content of the segment.

568

569 - `Tokens []int64`

570

571 Array of token IDs for the text content.

572

573### Transcription Stream Event

574

575- `type TranscriptionStreamEventUnion interface{…}`

576

577 Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with `stream` set to `true` and `response_format` set to `diarized_json`.

578

579 - `type TranscriptionTextSegmentEvent struct{…}`

580

581 Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with `stream` set to `true` and `response_format` set to `diarized_json`.

582

583 - `ID string`

584

585 Unique identifier for the segment.

586

587 - `End float64`

588

589 End timestamp of the segment in seconds.

590

591 - `Speaker string`

592

593 Speaker label for this segment.

594

595 - `Start float64`

596

597 Start timestamp of the segment in seconds.

598

599 - `Text string`

600

601 Transcript text for this segment.

602

603 - `Type TranscriptTextSegment`

604

605 The type of the event. Always `transcript.text.segment`.

606

607 - `const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"`

608

609 - `type TranscriptionTextDeltaEvent struct{…}`

610

611 Emitted when there is an additional text delta. This is also the first event emitted when the transcription starts. Only emitted when you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`.

612

613 - `Delta string`

614

615 The text delta that was additionally transcribed.

616

617 - `Type TranscriptTextDelta`

618

619 The type of the event. Always `transcript.text.delta`.

620

621 - `const TranscriptTextDeltaTranscriptTextDelta TranscriptTextDelta = "transcript.text.delta"`

622

623 - `Logprobs []TranscriptionTextDeltaEventLogprob`

624

625 The log probabilities of the delta. Only included if you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`.

626

627 - `Token string`

628

629 The token that was used to generate the log probability.

630

631 - `Bytes []int64`

632

633 The bytes that were used to generate the log probability.

634

635 - `Logprob float64`

636

637 The log probability of the token.

638

639 - `SegmentID string`

640

641 Identifier of the diarized segment that this delta belongs to. Only present when using `gpt-4o-transcribe-diarize`.

642

643 - `type TranscriptionTextDoneEvent struct{…}`

644

645 Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`.

646

647 - `Text string`

648

649 The text that was transcribed.

650

651 - `Type TranscriptTextDone`

652

653 The type of the event. Always `transcript.text.done`.

654

655 - `const TranscriptTextDoneTranscriptTextDone TranscriptTextDone = "transcript.text.done"`

656

657 - `Logprobs []TranscriptionTextDoneEventLogprob`

658

659 The log probabilities of the individual tokens in the transcription. Only included if you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`.

660

661 - `Token string`

662

663 The token that was used to generate the log probability.

664

665 - `Bytes []int64`

666

667 The bytes that were used to generate the log probability.

668

669 - `Logprob float64`

670

671 The log probability of the token.

672

673 - `Usage TranscriptionTextDoneEventUsage`

674

675 Usage statistics for models billed by token usage.

676

677 - `InputTokens int64`

678

679 Number of input tokens billed for this request.

680

681 - `OutputTokens int64`

682

683 Number of output tokens generated.

684

685 - `TotalTokens int64`

686

687 Total number of tokens used (input + output).

688

689 - `Type Tokens`

690

691 The type of the usage object. Always `tokens` for this variant.

692

693 - `const TokensTokens Tokens = "tokens"`

694

695 - `InputTokenDetails TranscriptionTextDoneEventUsageInputTokenDetails`

696

697 Details about the input tokens billed for this request.

698

699 - `AudioTokens int64`

700

701 Number of audio tokens billed for this request.

702

703 - `TextTokens int64`

704

705 Number of text tokens billed for this request.

706

707### Transcription Text Delta Event

708

709- `type TranscriptionTextDeltaEvent struct{…}`

710

711 Emitted when there is an additional text delta. This is also the first event emitted when the transcription starts. Only emitted when you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`.

712

713 - `Delta string`

714

715 The text delta that was additionally transcribed.

716

717 - `Type TranscriptTextDelta`

718

719 The type of the event. Always `transcript.text.delta`.

720

721 - `const TranscriptTextDeltaTranscriptTextDelta TranscriptTextDelta = "transcript.text.delta"`

722

723 - `Logprobs []TranscriptionTextDeltaEventLogprob`

724

725 The log probabilities of the delta. Only included if you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`.

726

727 - `Token string`

728

729 The token that was used to generate the log probability.

730

731 - `Bytes []int64`

732

733 The bytes that were used to generate the log probability.

734

735 - `Logprob float64`

736

737 The log probability of the token.

738

739 - `SegmentID string`

740

741 Identifier of the diarized segment that this delta belongs to. Only present when using `gpt-4o-transcribe-diarize`.

742

743### Transcription Text Done Event

744

745- `type TranscriptionTextDoneEvent struct{…}`

746

747 Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`.

748

749 - `Text string`

750

751 The text that was transcribed.

752

753 - `Type TranscriptTextDone`

754

755 The type of the event. Always `transcript.text.done`.

756

757 - `const TranscriptTextDoneTranscriptTextDone TranscriptTextDone = "transcript.text.done"`

758

759 - `Logprobs []TranscriptionTextDoneEventLogprob`

760

761 The log probabilities of the individual tokens in the transcription. Only included if you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`.

762

763 - `Token string`

764

765 The token that was used to generate the log probability.

766

767 - `Bytes []int64`

768

769 The bytes that were used to generate the log probability.

770

771 - `Logprob float64`

772

773 The log probability of the token.

774

775 - `Usage TranscriptionTextDoneEventUsage`

776

777 Usage statistics for models billed by token usage.

778

779 - `InputTokens int64`

780

781 Number of input tokens billed for this request.

782

783 - `OutputTokens int64`

784

785 Number of output tokens generated.

786

787 - `TotalTokens int64`

788

789 Total number of tokens used (input + output).

790

791 - `Type Tokens`

792

793 The type of the usage object. Always `tokens` for this variant.

794

795 - `const TokensTokens Tokens = "tokens"`

796

797 - `InputTokenDetails TranscriptionTextDoneEventUsageInputTokenDetails`

798

799 Details about the input tokens billed for this request.

800

801 - `AudioTokens int64`

802

803 Number of audio tokens billed for this request.

804

805 - `TextTokens int64`

806

807 Number of text tokens billed for this request.

808

809### Transcription Text Segment Event

810

811- `type TranscriptionTextSegmentEvent struct{…}`

812

813 Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription) with `stream` set to `true` and `response_format` set to `diarized_json`.

814

815 - `ID string`

816

817 Unique identifier for the segment.

818

819 - `End float64`

820

821 End timestamp of the segment in seconds.

822

823 - `Speaker string`

824

825 Speaker label for this segment.

826

827 - `Start float64`

828

829 Start timestamp of the segment in seconds.

830

831 - `Text string`

832

833 Transcript text for this segment.

834

835 - `Type TranscriptTextSegment`

836

837 The type of the event. Always `transcript.text.segment`.

838

839 - `const TranscriptTextSegmentTranscriptTextSegment TranscriptTextSegment = "transcript.text.segment"`

840

841### Transcription Verbose

842

843- `type TranscriptionVerbose struct{…}`

844

845 Represents a verbose json transcription response returned by model, based on the provided input.

846

847 - `Duration float64`

848

849 The duration of the input audio.

850

851 - `Language string`

852

853 The language of the input audio.

854

855 - `Text string`

856

857 The transcribed text.

858

859 - `Segments []TranscriptionSegment`

860

861 Segments of the transcribed text and their corresponding details.

862

863 - `ID int64`

864

865 Unique identifier of the segment.

866

867 - `AvgLogprob float64`

868

869 Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.

870

871 - `CompressionRatio float64`

872

873 Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.

874

875 - `End float64`

876

877 End time of the segment in seconds.

878

879 - `NoSpeechProb float64`

880

881 Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent.

882

883 - `Seek int64`

884

885 Seek offset of the segment.

886

887 - `Start float64`

888

889 Start time of the segment in seconds.

890

891 - `Temperature float64`

892

893 Temperature parameter used for generating the segment.

894

895 - `Text string`

896

897 Text content of the segment.

898

899 - `Tokens []int64`

900

901 Array of token IDs for the text content.

902

903 - `Usage TranscriptionVerboseUsage`

904

905 Usage statistics for models billed by audio input duration.

906

907 - `Seconds float64`

908

909 Duration of the input audio in seconds.

910

911 - `Type Duration`

912

913 The type of the usage object. Always `duration` for this variant.

914

915 - `const DurationDuration Duration = "duration"`

916

917 - `Words []TranscriptionWord`

918

919 Extracted words and their corresponding timestamps.

920

921 - `End float64`

922

923 End time of the word in seconds.

924

925 - `Start float64`

926

927 Start time of the word in seconds.

928

929 - `Word string`

930

931 The text content of the word.

932

933### Transcription Word

934

935- `type TranscriptionWord struct{…}`

936

937 - `End float64`

938

939 End time of the word in seconds.

940

941 - `Start float64`

942

943 Start time of the word in seconds.

944

945 - `Word string`

946

947 The text content of the word.

go/resources/audio/subresources/transcriptions/index.md 2026-07-07 08:02 UTC to 2026-07-09 20:58 UTC

Transcriptions

Create transcription

Parameters

Returns

Example

Response

Domain Types

Transcription

Transcription Diarized

Transcription Diarized Segment

Transcription Include

Transcription Segment

Transcription Stream Event

Transcription Text Delta Event

Transcription Text Done Event

Transcription Text Segment Event

Transcription Verbose

Transcription Word