Create Transcription

This action creates a transcription for an audio file with an AI model.

Action Settings

Setting Description
Model The ID of the model to use for transcribing the audio. This setting is required.
Language The language of the input audio.
Temperature The sampling temperature to use, between 0 and 1.

Action Parameters

Parameter Description
Input The audio file to transcribe. This parameter is required.
InputFormat The format of the input audio. This parameter is required.
Instructions An optional text to guide the model's style or continue a previous audio segment.

Result

The generated transcription is returned in the Transcription field. The action also returns the usage type and tokens used.