Translations

Create translation

post /audio/translations

Create translation

Returns

Translation object { text }
- text: string
TranslationVerbose 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

curl https://api.openai.com/v1/audio/translations \
    -H 'Content-Type: multipart/form-data' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -F 'file=@/path/to/file' \
    -F model=whisper-1

Response

{
  "text": "text"
}

Example

curl https://api.openai.com/v1/audio/translations \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/german.m4a" \
  -F model="whisper-1"

Response

{
  "text": "Hello, my name is Wolfgang and I come from Germany. Where are you heading today?"
}

Domain Types

Translation

Translation object { text }
- text: string

Translation Verbose

TranslationVerbose 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.

Translation Create Response

TranslationCreateResponse = Translation or TranslationVerbose
- Translation object { text }
  - text: string
- TranslationVerbose 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.

resources/audio/subresources/translations/index.md +241 −0 created

1# Translations

3## Create translation

5**post** `/audio/translations`

7Create translation

9### Returns

11- `Translation object { text }`

13 - `text: string`

15- `TranslationVerbose object { duration, language, text, segments }`

17 - `duration: number`

19 The duration of the input audio.

21 - `language: string`

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

25 - `text: string`

27 The translated text.

29 - `segments: optional array of TranscriptionSegment`

31 Segments of the translated text and their corresponding details.

33 - `id: number`

35 Unique identifier of the segment.

37 - `avg_logprob: number`

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

41 - `compression_ratio: number`

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

45 - `end: number`

47 End time of the segment in seconds.

49 - `no_speech_prob: number`

51 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.

53 - `seek: number`

55 Seek offset of the segment.

57 - `start: number`

59 Start time of the segment in seconds.

61 - `temperature: number`

63 Temperature parameter used for generating the segment.

65 - `text: string`

67 Text content of the segment.

69 - `tokens: array of number`

71 Array of token IDs for the text content.

73### Example

75```http

76curl https://api.openai.com/v1/audio/translations \

77 -H 'Content-Type: multipart/form-data' \

78 -H "Authorization: Bearer $OPENAI_API_KEY" \

79 -F 'file=@/path/to/file' \

80 -F model=whisper-1

81```

83#### Response

85```json

86{

87 "text": "text"

88}

89```

91### Example

93```http

94curl https://api.openai.com/v1/audio/translations \

95 -H "Authorization: Bearer $OPENAI_API_KEY" \

96 -H "Content-Type: multipart/form-data" \

97 -F file="@/path/to/file/german.m4a" \

98 -F model="whisper-1"

99```

100

101#### Response

102

103```json

104{

105 "text": "Hello, my name is Wolfgang and I come from Germany. Where are you heading today?"

106}

107```

108

109## Domain Types

110

111### Translation

112

113- `Translation object { text }`

114

115 - `text: string`

116

117### Translation Verbose

118

119- `TranslationVerbose object { duration, language, text, segments }`

120

121 - `duration: number`

122

123 The duration of the input audio.

124

125 - `language: string`

126

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

128

129 - `text: string`

130

131 The translated text.

132

133 - `segments: optional array of TranscriptionSegment`

134

135 Segments of the translated text and their corresponding details.

136

137 - `id: number`

138

139 Unique identifier of the segment.

140

141 - `avg_logprob: number`

142

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

144

145 - `compression_ratio: number`

146

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

148

149 - `end: number`

150

151 End time of the segment in seconds.

152

153 - `no_speech_prob: number`

154

155 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.

156

157 - `seek: number`

158

159 Seek offset of the segment.

160

161 - `start: number`

162

163 Start time of the segment in seconds.

164

165 - `temperature: number`

166

167 Temperature parameter used for generating the segment.

168

169 - `text: string`

170

171 Text content of the segment.

172

173 - `tokens: array of number`

174

175 Array of token IDs for the text content.

176

177### Translation Create Response

178

179- `TranslationCreateResponse = Translation or TranslationVerbose`

180

181 - `Translation object { text }`

182

183 - `text: string`

184

185 - `TranslationVerbose object { duration, language, text, segments }`

186

187 - `duration: number`

188

189 The duration of the input audio.

190

191 - `language: string`

192

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

194

195 - `text: string`

196

197 The translated text.

198

199 - `segments: optional array of TranscriptionSegment`

200

201 Segments of the translated text and their corresponding details.

202

203 - `id: number`

204

205 Unique identifier of the segment.

206

207 - `avg_logprob: number`

208

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

210

211 - `compression_ratio: number`

212

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

214

215 - `end: number`

216

217 End time of the segment in seconds.

218

219 - `no_speech_prob: number`

220

221 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.

222

223 - `seek: number`

224

225 Seek offset of the segment.

226

227 - `start: number`

228

229 Start time of the segment in seconds.

230

231 - `temperature: number`

232

233 Temperature parameter used for generating the segment.

234

235 - `text: string`

236

237 Text content of the segment.

238

239 - `tokens: array of number`

240

241 Array of token IDs for the text content.

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

Translations

Create translation

Returns

Example

Response

Example

Response

Domain Types

Translation

Translation Verbose

Translation Create Response