# simplewhispr

minimalist ai-powered dictation for linux.

requires `ffmpeg` and `wtype`.

## install
```bash
uv tool install . --reinstall
```

## usage
run `simplewhispr-auto` to start dictating. run `simplewhispr-auto` again when
you are done. wait a few seconds, and what you said will be transcribed onto
your screen with wtype.

requires `~/.config/simplewhispr/config.json`:
```json
{
  "openai_api_key": "sk-...",
  "model": "gpt-4o-mini-transcribe" // optional, defaults to mini
}
```

## integrations
waybar: `tail -F /tmp/simplewhispr-waybar.log`, json output

---
Copyright (C) Noah Swerhun under the terms of [GNU GPLv3](https://www.gnu.org/licenses/gpl-3.0-standalone.html).