Translations

Create translation

audio.translations.create(**kwargs) -> TranslationCreateResponse

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 | AudioModel

ID of the model to use. Only whisper-1 (which is powered by our open source Whisper V2 model) is currently available.
- String = String
- AudioModel = :"whisper-1" | :"gpt-4o-transcribe" | :"gpt-4o-mini-transcribe" | 2 more
  - :"whisper-1"
  - :"gpt-4o-transcribe"
  - :"gpt-4o-mini-transcribe"
  - :"gpt-4o-mini-transcribe-2025-12-15"
  - :"gpt-4o-transcribe-diarize"
prompt: String

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

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

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

TranslationCreateResponse = Translation | TranslationVerbose
- class Translation
  - text: String
- class TranslationVerbose
  - duration: Float
    
    The duration of the input audio.
  - language: String
    
    The language of the output translation (always english).
  - text: String
    
    The translated text.
  - segments: Array[TranscriptionSegment]
    
    Segments of the translated text and their corresponding details.
    - id: Integer
      
      Unique identifier of the segment.
    - avg_logprob: Float
      
      Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
    - compression_ratio: Float
      
      Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
    - end_: Float
      
      End time of the segment in seconds.
    - no_speech_prob: Float
      
      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: Integer
      
      Seek offset of the segment.
    - start: Float
      
      Start time of the segment in seconds.
    - temperature: Float
      
      Temperature parameter used for generating the segment.
    - text: String
      
      Text content of the segment.
    - tokens: Array[Integer]
      
      Array of token IDs for the text content.

Example

require "openai"

openai = OpenAI::Client.new(api_key: "My API Key")

translation = openai.audio.translations.create(file: StringIO.new("Example data"), model: :"whisper-1")

puts(translation)

Response

{
  "text": "text"
}

Domain Types

Translation

class Translation
- text: String

Translation Verbose

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

Translation Create Response

TranslationCreateResponse = Translation | TranslationVerbose
- class Translation
  - text: String
- class TranslationVerbose
  - duration: Float
    
    The duration of the input audio.
  - language: String
    
    The language of the output translation (always english).
  - text: String
    
    The translated text.
  - segments: Array[TranscriptionSegment]
    
    Segments of the translated text and their corresponding details.
    - id: Integer
      
      Unique identifier of the segment.
    - avg_logprob: Float
      
      Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
    - compression_ratio: Float
      
      Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
    - end_: Float
      
      End time of the segment in seconds.
    - no_speech_prob: Float
      
      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: Integer
      
      Seek offset of the segment.
    - start: Float
      
      Start time of the segment in seconds.
    - temperature: Float
      
      Temperature parameter used for generating the segment.
    - text: String
      
      Text content of the segment.
    - tokens: Array[Integer]
      
      Array of token IDs for the text content.

ruby/resources/audio/subresources/translations/index.md +275 −0 created

1# Translations

3## Create translation

5`audio.translations.create(**kwargs) -> TranslationCreateResponse`

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 | 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 - `String = String`

23 - `AudioModel = :"whisper-1" | :"gpt-4o-transcribe" | :"gpt-4o-mini-transcribe" | 2 more`

25 - `:"whisper-1"`

27 - `:"gpt-4o-transcribe"`

29 - `:"gpt-4o-mini-transcribe"`

31 - `:"gpt-4o-mini-transcribe-2025-12-15"`

33 - `:"gpt-4o-transcribe-diarize"`

35- `prompt: String`

37 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.

39- `response_format: :json | :text | :srt | 2 more`

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

43 - `:json`

45 - `:text`

47 - `:srt`

49 - `:verbose_json`

51 - `:vtt`

53- `temperature: Float`

55 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.

57### Returns

59- `TranslationCreateResponse = Translation | TranslationVerbose`

61 - `class Translation`

63 - `text: String`

65 - `class TranslationVerbose`

67 - `duration: Float`

69 The duration of the input audio.

71 - `language: String`

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

75 - `text: String`

77 The translated text.

79 - `segments: Array[TranscriptionSegment]`

81 Segments of the translated text and their corresponding details.

83 - `id: Integer`

85 Unique identifier of the segment.

87 - `avg_logprob: Float`

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

91 - `compression_ratio: Float`

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

95 - `end_: Float`

97 End time of the segment in seconds.

99 - `no_speech_prob: Float`

100

101 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.

102

103 - `seek: Integer`

104

105 Seek offset of the segment.

106

107 - `start: Float`

108

109 Start time of the segment in seconds.

110

111 - `temperature: Float`

112

113 Temperature parameter used for generating the segment.

114

115 - `text: String`

116

117 Text content of the segment.

118

119 - `tokens: Array[Integer]`

120

121 Array of token IDs for the text content.

122

123### Example

124

125```ruby

126require "openai"

127

128openai = OpenAI::Client.new(api_key: "My API Key")

129

130translation = openai.audio.translations.create(file: StringIO.new("Example data"), model: :"whisper-1")

131

132puts(translation)

133```

134

135#### Response

136

137```json

138{

139 "text": "text"

140}

141```

142

143## Domain Types

144

145### Translation

146

147- `class Translation`

148

149 - `text: String`

150

151### Translation Verbose

152

153- `class TranslationVerbose`

154

155 - `duration: Float`

156

157 The duration of the input audio.

158

159 - `language: String`

160

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

162

163 - `text: String`

164

165 The translated text.

166

167 - `segments: Array[TranscriptionSegment]`

168

169 Segments of the translated text and their corresponding details.

170

171 - `id: Integer`

172

173 Unique identifier of the segment.

174

175 - `avg_logprob: Float`

176

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

178

179 - `compression_ratio: Float`

180

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

182

183 - `end_: Float`

184

185 End time of the segment in seconds.

186

187 - `no_speech_prob: Float`

188

189 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.

190

191 - `seek: Integer`

192

193 Seek offset of the segment.

194

195 - `start: Float`

196

197 Start time of the segment in seconds.

198

199 - `temperature: Float`

200

201 Temperature parameter used for generating the segment.

202

203 - `text: String`

204

205 Text content of the segment.

206

207 - `tokens: Array[Integer]`

208

209 Array of token IDs for the text content.

210

211### Translation Create Response

212

213- `TranslationCreateResponse = Translation | TranslationVerbose`

214

215 - `class Translation`

216

217 - `text: String`

218

219 - `class TranslationVerbose`

220

221 - `duration: Float`

222

223 The duration of the input audio.

224

225 - `language: String`

226

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

228

229 - `text: String`

230

231 The translated text.

232

233 - `segments: Array[TranscriptionSegment]`

234

235 Segments of the translated text and their corresponding details.

236

237 - `id: Integer`

238

239 Unique identifier of the segment.

240

241 - `avg_logprob: Float`

242

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

244

245 - `compression_ratio: Float`

246

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

248

249 - `end_: Float`

250

251 End time of the segment in seconds.

252

253 - `no_speech_prob: Float`

254

255 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.

256

257 - `seek: Integer`

258

259 Seek offset of the segment.

260

261 - `start: Float`

262

263 Start time of the segment in seconds.

264

265 - `temperature: Float`

266

267 Temperature parameter used for generating the segment.

268

269 - `text: String`

270

271 Text content of the segment.

272

273 - `tokens: Array[Integer]`

274

275 Array of token IDs for the text content.

ruby/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

Translation Create Response