Create Transcription
POST/v1/audio/transcriptions
Transcribe an audio file into text in the language it was spoken in.
The request body is multipart/form-data. Uploads are accepted up to 25 MB and 30 minutes, whichever limit is reached first; longer audio is rejected with audio_too_long. Recordings longer than about half a minute are split, transcribed in order and merged back into one transcript before the response is returned.
Request
Responses
- 200
- 400
- 401
- 402
- 403
- 404
- 413
- 422
- 429
- 502
- 503
- 504
Successful Response
Invalid request: missing or empty file, unsupported file format, unsupported parameter combination, background job requested, audio longer than a single request can transcribe (audio_too_long), or a model that does not support audio.
Unauthorized
Audio pricing is not configured for this model
The API key is not permitted to use this model
Model not found
Audio file exceeds the maximum upload size
Validation Error
Rate limit exceeded or audio quota exhausted
The model returned an unusable transcript; the request is not charged
Model or a dependent service is temporarily unavailable
The audio request exceeded the processing deadline