Audio Transcription

This endpoint allows you to transcribe audio.

Headers

AuthorizationstringRequired

Bearer authentication of the form Bearer <token>, where token is your auth token.

ToxicitybooleanOptional
Whether to check the output for toxicity.
PiistringOptional
Whether to check the output for Pii, and what to do if found. Supported values are 'replace' and 'block'.
Replace-MethodstringOptional
Method to replace any found PII. Supported values are 'category', 'fake', 'mask', and 'random'.
InjectionbooleanOptional
Whether to check the output for a prompt injection.

Request

This endpoint expects a multipart form containing a file.
modelstringRequired
The transcription model to use.
filefileRequired
The audio file to upload.
languagestringRequired
The language the audio is in.
promptstringRequired
An optional text to guide the model's style or continue a previous audio segment.
temperaturedoubleRequired
The temperature parameter for controlling randomness in transcription.

Response

Successful response.
textstring or null
The transcribed audio.

Errors