# Prerecorded

The REST API provides speech-to-text transcription for complete audio files. You upload an audio file and receive the full transcript in the response.

## How It Works

1. **Authenticate** — Include an [authentication](../general/authentication.md) header in your request.
2. **Configure** — Use [query parameters](../../api/speech-to-text/prerecorded.md#query-parameters) to set the audio encoding and which fields to include in the response.
3. **Upload audio** — Send the audio file as the request body with `Content-Type: application/octet-stream`.
4. **Receive transcript** — The server processes the entire file and returns the transcript as JSON.

See the [API reference](../../api/speech-to-text/prerecorded.md) for full details on fields and error codes.

## Audio Format Detection

When the `encoding` query parameter is set to `auto` (the default), the server automatically detects the audio format from the uploaded file. Most common formats (WAV, M4A, MP3, OGG, FLAC, WebM, etc.) are supported. If you know the file is a seekable media container, you can set `encoding=m4a`, `m4v`, `mp4`, `mov`, `3gp`, or `3g2` explicitly. If you are sending raw PCM audio without container headers, set the `encoding` parameter explicitly (e.g., `pcm_s16le`) along with `sample_rate` and `channels`.

## Language

The server auto-detects the language by default; pass the `language` query parameter to pin a specific one. See [Languages](languages.md) for the supported set.