transcribeAudio

Convert an audio file to text using a transcription model.

mindstudio.transcribeAudio({ audioUrl, prompt }) → Result

Transcribes an audio file to text with a transcription model — the inverse of textToSpeech. Pair it with a text-generation step to summarize or extract from what was said.

Parameters

audioUrl

string

RequiredURL of the audio file to transcribe

prompt

string

RequiredOptional context to improve transcription accuracy (e.g. language, speaker names, domain terms)

transcriptionModelOverride

object

Optional model configuration override. Uses the workflow's default transcription model if not specified

Call from a method

import { mindstudio } from '@mindstudio-ai/agent';

const result = await mindstudio.transcribeAudio({
  audioUrl: /* ... */,
  prompt: /* ... */
});