API OverviewAudio

Create transcription

Transcribe an uploaded audio file with a multipart request.

Authentication

AuthorizationBearer
Your production key sent as a bearer token.

Request

This endpoint expects a multipart form containing a file.
filefileRequired
Audio file to transcribe.
modelstringRequired

Transcription model, for example openai/whisper-1.

vendorstring or nullOptional
Pin the vendor that runs this request.
languagestring or nullOptional
Language of the audio.
promptstring or nullOptional
Text to guide the transcription.
response_formatstring or nullOptional

Output format, for example json or verbose_json.

temperaturedouble or nullOptional
Sampling temperature.

Response

Successful Response
textstring
Transcribed text.
vendorstring
Vendor that served the request.
languagestring or nullOptional
Detected language, when the model returns it.
durationdouble or nullOptional
Audio duration in seconds, when the model returns it.

Errors

422
Unprocessable Entity Error