Transcription

3 min read

OpenAI-compatible audio transcription - the same endpoint DevThrottle's own voice features use. Transcription is included in Pro and the 14-day Pro trial with no usage charge - the same entitlement that powers dictation in the app covers calls to this endpoint, with your own key or without one.

POST/audio/transcriptions

Transcribe an audio file. Multipart form data, OpenAI shape.

Request

Parameter	Type	Required	Description
`file`	file	Required	The audio to transcribe. Same formats as OpenAI: flac, m4a, mp3, mp4, mpeg, mpga, oga, ogg, wav, webm. Max 4 MB per request (see Limits).
`model`	string	Optional	Accepted for OpenAI compatibility (clients send whisper-1, gpt-4o-transcribe, ...). DevThrottle serves the request with its active speech-to-text model regardless of this value; see GET /api/v1/models for the current id.
`response_format`	string	Optional	json (default), text, or verbose_json - shaped to what you asked for.
`language`	string	Optional	Optional language hint.

Example

curl https://devthrottle.com/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $DEVTHROTTLE_API_KEY" \
  -F file=@recording.wav \
  -F model=whisper-1

Limits

Each request is a single, self-contained transcription with a 4 MB maximum body size. A larger upload returns 413 payload_too_large. There is no fixed limit on how much audio you can transcribe overall - only on how much fits in one request.

Note

For recordings larger than 4 MB, split the audio into sub-4 MB parts and transcribe each, then join the text. The DevThrottle app does this for you automatically (chunking long recordings on silence and transcribing the parts in parallel), so end users never hit the per-request limit.

Who can call it

Transcription comes with Pro and the 14-day Pro trial. A request from an account without that entitlement is declined as a subscription outcome - subscribing to Pro enables it, not loading credits. Each request's duration appears in Usage.

Note

The model parameter is deliberately forgiving: OpenAI-shaped clients hard-code their own model names, so DevThrottle accepts them and uses its own speech model - your client works unmodified.