API Reference

Audio Transcription

This endpoint allows you to transcribe audio.

Authentication

AuthorizationBearer

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

Headers

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'.
Entity-Listlist of stringsOptional
An array of entity types that the PII check should ignore.
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.
languagestringOptional
The language the audio is in.
promptstringOptional
An optional text to guide the model's style or continue a previous audio segment.
temperaturedoubleOptional

The temperature parameter for controlling randomness in transcription. Supports a range of 0.0-2.0.

timestamps_granularities[]string or list of anyOptional
Sets whether timestamps are returned and at what granularity.
diarizationbooleanOptional

Whether to diarize the audio and return speaker turns. Not currently supported in multi-tenant environments.

response_formatstringOptional

The format for the response object. Defaults to “json” and must be set to “verbose_json” when using diarization or timestamp granularities.

Response

Successful response.
textstring or null
The transcribed audio.
taskstring or null
The task used in the request
languagestring or null
The language of the audio file
segmentslist of any or null
An array containing objects with segment level data
wordslist of any or null
An array containing objects with word level data

Errors