# Prepare audio for speech-to-text

Turn any recording or video into the 16 kHz mono 16-bit WAV that Whisper and other speech-to-text models expect.

- Endpoint: `POST https://setget.net/v1/tools/audio-to-stt-wav` with JSON `{"input": {...}}` (add `"wait": 30` to hold the reply until the job finishes)
- MCP: `run_tool` with `slug` = `audio-to-stt-wav`
- Page: https://setget.net/tools/audio-to-stt-wav

## Files in, files out

This is a file tool. Its file inputs take file references, not file contents and not web addresses.

- Get a reference by uploading: `curl -T FILE https://setget.net/drop/` prints a line `ref  <id>/f1`. Or `POST https://setget.net/v1/drops` with `{"files":[{"name","size"}]}`, PUT the bytes to the returned `upload.url` with the listed headers, and use the file's `ref`. Over MCP use the `drop` tool. A file under about 700 KB can also be sent in place as a `data:<type>;base64,<content>` URI.
- Uploads are at most 100 MB per file, are readable by anyone with the link, and expire (one hour by default). Programs are refused.
- The tool runs as a job. The reply is `{"tool", "ms", "result", "files", "job"}`: `result` is JSON, and every result file comes back in `files` as `{"name", "size", "content_type", "kind", "url", "ref"}`. Download it from `url`, or pass `ref` as the input of another file tool.
- A job still running when the wait ends answers 202 with `job`. Follow it with `GET https://setget.net/v1/jobs/<id>?wait=30`, or stream progress from `GET https://setget.net/v1/jobs/<id>/events` (over MCP: the `job` tool). A person can watch it at `job.url`.

## Inputs

- `file` (required, file, a file reference such as `DROP_ID/f1`, accepts audio, video): The recording, or a video with speech in it.
- `normalize` (optional, boolean, default `false`): Bring the speech to an even, clear loudness.
- `trim_silence` (optional, boolean, default `false`): Cut away silence at the start and the end.
- `threshold` (optional, number, default `-40`, range -90..-10): How quiet counts as silence, in dB below full volume. -40 suits most recordings; use -30 for a noisy room. Used when trimming silence.

## Example 1: MP3 to 16 kHz mono WAV

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.mp3](https://setget.net/static/samples/sample.mp3).

```json
{"input":{"file":"DROP_ID/f1"},"wait":30}
```

## Example 2: Speech from a video, levelled and trimmed

Upload first. Each placeholder below stands for the reference of one upload: `DROP_ID/f1` = [sample.mp4](https://setget.net/static/samples/sample.mp4).

```json
{"input":{"file":"DROP_ID/f1","normalize":true,"trim_silence":true},"wait":30}
```

**Why 16 kHz mono?** Most speech models were trained on 16 kHz mono sound and convert everything to it anyway. Sending it ready-made avoids surprises and keeps uploads small: about 1.9 MB per minute.

**My file is over the upload limit of the speech service. What now?** Split it with the split on silence tool, then prepare each part. The result tells you whether the file is under 25 MB, a common limit.
