Translations

Create translation

$ openai audio:translations create

post /audio/translations

Create translation

Parameters

--file: string

The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
--model: string or AudioModel

ID of the model to use. Only whisper-1 (which is powered by our open source Whisper V2 model) is currently available.
--prompt: optional string

An optional text to guide the model's style or continue a previous audio segment. The prompt should be in English.
--response-format: optional "json" or "text" or "srt" or 2 more

The format of the output, in one of these options: json, text, srt, verbose_json, or vtt.
--temperature: optional number

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.

Returns

unnamed_schema_1: Translation or TranslationVerbose
- translation: object { text }
  - text: string
- translation_verbose: object { duration, language, text, segments }
  - duration: number
    
    The duration of the input audio.
  - language: string
    
    The language of the output translation (always english).
  - text: string
    
    The translated text.
  - segments: optional array of TranscriptionSegment
    
    Segments of the translated text and their corresponding details.
    - id: number
      
      Unique identifier of the segment.
    - avg_logprob: number
      
      Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
    - compression_ratio: number
      
      Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
    - end: number
      
      End time of the segment in seconds.
    - no_speech_prob: number
      
      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: number
      
      Seek offset of the segment.
    - start: number
      
      Start time of the segment in seconds.
    - temperature: number
      
      Temperature parameter used for generating the segment.
    - text: string
      
      Text content of the segment.
    - tokens: array of number
      
      Array of token IDs for the text content.

Example

openai audio:translations create \
  --api-key 'My API Key' \
  --file 'Example data' \
  --model whisper-1

Response

{
  "text": "text"
}

Domain Types

Translation

translation: object { text }
- text: string

Translation Verbose

translation_verbose: object { duration, language, text, segments }
- duration: number
  
  The duration of the input audio.
- language: string
  
  The language of the output translation (always english).
- text: string
  
  The translated text.
- segments: optional array of TranscriptionSegment
  
  Segments of the translated text and their corresponding details.
  - id: number
    
    Unique identifier of the segment.
  - avg_logprob: number
    
    Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
  - compression_ratio: number
    
    Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
  - end: number
    
    End time of the segment in seconds.
  - no_speech_prob: number
    
    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: number
    
    Seek offset of the segment.
  - start: number
    
    Start time of the segment in seconds.
  - temperature: number
    
    Temperature parameter used for generating the segment.
  - text: string
    
    Text content of the segment.
  - tokens: array of number
    
    Array of token IDs for the text content.

cli/resources/audio/subresources/translations/index.md +182 −0 created

1# Translations

3## Create translation

5`$ openai audio:translations create`

7**post** `/audio/translations`

9Create translation

11### Parameters

13- `--file: string`

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

17- `--model: string or AudioModel`

19 ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available.

21- `--prompt: optional string`

23 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 be in English.

25- `--response-format: optional "json" or "text" or "srt" or 2 more`

27 The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.

29- `--temperature: optional number`

31 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.

33### Returns

35- `unnamed_schema_1: Translation or TranslationVerbose`

37 - `translation: object { text }`

39 - `text: string`

41 - `translation_verbose: object { duration, language, text, segments }`

43 - `duration: number`

45 The duration of the input audio.

47 - `language: string`

49 The language of the output translation (always `english`).

51 - `text: string`

53 The translated text.

55 - `segments: optional array of TranscriptionSegment`

57 Segments of the translated text and their corresponding details.

59 - `id: number`

61 Unique identifier of the segment.

63 - `avg_logprob: number`

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

67 - `compression_ratio: number`

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

71 - `end: number`

73 End time of the segment in seconds.

75 - `no_speech_prob: number`

77 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.

79 - `seek: number`

81 Seek offset of the segment.

83 - `start: number`

85 Start time of the segment in seconds.

87 - `temperature: number`

89 Temperature parameter used for generating the segment.

91 - `text: string`

93 Text content of the segment.

95 - `tokens: array of number`

97 Array of token IDs for the text content.

99### Example

100

101```cli

102openai audio:translations create \

103 --api-key 'My API Key' \

104 --file 'Example data' \

105 --model whisper-1

106```

107

108#### Response

109

110```json

111{

112 "text": "text"

113}

114```

115

116## Domain Types

117

118### Translation

119

120- `translation: object { text }`

121

122 - `text: string`

123

124### Translation Verbose

125

126- `translation_verbose: object { duration, language, text, segments }`

127

128 - `duration: number`

129

130 The duration of the input audio.

131

132 - `language: string`

133

134 The language of the output translation (always `english`).

135

136 - `text: string`

137

138 The translated text.

139

140 - `segments: optional array of TranscriptionSegment`

141

142 Segments of the translated text and their corresponding details.

143

144 - `id: number`

145

146 Unique identifier of the segment.

147

148 - `avg_logprob: number`

149

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

151

152 - `compression_ratio: number`

153

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

155

156 - `end: number`

157

158 End time of the segment in seconds.

159

160 - `no_speech_prob: number`

161

162 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.

163

164 - `seek: number`

165

166 Seek offset of the segment.

167

168 - `start: number`

169

170 Start time of the segment in seconds.

171

172 - `temperature: number`

173

174 Temperature parameter used for generating the segment.

175

176 - `text: string`

177

178 Text content of the segment.

179

180 - `tokens: array of number`

181

182 Array of token IDs for the text content.

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

Translations

Create translation

Parameters

Returns

Example

Response

Domain Types

Translation

Translation Verbose