RErequesty

Create transcription

Transcribes audio into text using a speech-to-text model. The audio file is sent as multipart/form-data.

post/v1/audio/transcriptions

Request

  • Base URL
    https://router.requesty.ai
  • URL
    https://router.requesty.ai/v1/audio/transcriptions
  • Auth
    HTTP bearer

Request body multipart/form-data

filestring binary required

The audio file to transcribe. Supported formats are flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, and webm. Maximum upload size is 32 MB.

modelstring required

The speech-to-text model to use, prefixed with the provider slug. Currently only OpenAI models are supported.

languagestring

The language of the input audio in ISO 639-1 format (for example, en, fr, ja). Supplying the language improves accuracy and latency. Auto-detected when omitted.

Example request

{
  "model": "openai/gpt-4o-transcribe"
}

Response

Transcription result

textstring required

The transcribed text.

Example response

{
  "text": "Hello, world.",
  "usage": {
    "type": "tokens"
  }
}

Changes

No recorded changes to this operation across all 4 revisions of this API.