cjpais/Handy
Press a shortcut, speak, and your words appear in any app — fully offline, free and open source.
Runs speech-to-text entirely on your own machine: hold a configurable shortcut, speak, and the transcribed text pastes into whatever app has focus, with no audio sent to the cloud. Silence gets filtered by Silero VAD first, then transcription runs on your choice of Whisper models (Small through Large, with GPU acceleration) or the CPU-optimized Parakeet V3 with automatic language detection. It's free and open source, runs on Windows, macOS and Linux, and ships a debug mode and CLI flags for controlling a running instance.
What holds up
- +Free and open source — no paywall, and you can extend it yourself
- +Processes everything locally — no audio or transcript ever reaches the cloud
- +Choice of Whisper models with GPU acceleration or the CPU-optimized Parakeet V3
- +CLI flags let you control a running instance, useful for scripting it into other tools
Mind the limits
- −Fn-key shortcut doesn't work with third-party keyboards on Mac — an Apple hardware limit
- −Homebrew and winget installs aren't maintained by the Handy team, so they can lag the real release
Picked here? Add the badge
Put it on your site. It links back to this page. Free for every listed product.
<a href="https://stillworks.dev/products/p/cjpais-handy/"><img src="https://stillworks.dev/badge/cjpais-handy.svg" alt="Picked by StillWorks" width="230" height="54"></a>