The short pitch is on the home page. This is everything underneath: the speech engines, how the AI runs, every knob you can turn, and the questions people ask.
Recognition runs entirely on your Mac. Start on the bundled one, switch anytime in Settings, no re-install.
| engine | size | best at | availability |
|---|---|---|---|
| SenseVoice | 228 MB | Fastest (~0.06s). Chinese-first; speaks zh / en / ja / ko / yue mixed in one sentence. | bundled · default |
| FireRed | ~740 MB | Steadier on long recordings and dialects. | free download |
| Qwen3-ASR | ~1.8 GB | Best zh/en mixing. 30 languages + 22 Chinese accents. Memory stays flat; your glossary doubles as built-in hotwords. | free download |
The AI modes (tidy up, draft an email, act on selected text, translate) run one of two ways.
Runs on your Mac. Offline and free. Loads only for the few seconds it's cleaning up, so idle memory is zero.
Routes by intent: a quick tidy takes ~1.7s; "write me an email" thinks for ~10s.
Plug in any OpenAI-compatible endpoint for top speed and quality.
Your key lives in the macOS Keychain, never uploaded and never written to a log.
The backend tries in order: BYOK → local Qwen → regex fallback. If one fails it steps down, so it never loses your words.
Almost everything is adjustable, and worded in plain language, so each switch tells you what happens when it's on.