A privacy-first desktop app that transforms your voice into text instantly. No cloud. No compromises.
“Hold hotkey → Speak → Release → Text appears instantly…”
Global hotkey activation. Press, speak, release. Text appears in your active app.
Written in native code. Maximum speed. Minimal resources. Zero bloat.
Everything stays on your machine. No cloud dependency. Full control.
Multiple model sizes. CPU or GPU. Local or online. Your choice.
Optional text optimization. Your API key. Your rules. Your data.
Free and open source. Community driven. Transparent by design.
No cloud by default. No data collection. No tracking. Your voice never leaves your machine unless you explicitly choose otherwise.
30 seconds of English audio transcription
Available for macOS, Windows, and Linux. Free and open source.