Handy is a free, open-source speech-to-text app with 34,000+ stars on GitHub that turns your voice into text anywhere on your computer — completely offline.
Handy does one job and does it well: press a shortcut, speak, and the transcription lands in whatever text box you are using. Unlike cloud dictation tools, everything runs on your machine. It uses OpenAI’s Whisper models locally — small through large variants, with GPU acceleration when available — and Silero voice activity detection to filter silence, so no audio ever leaves your computer. Built with Tauri, it is a lightweight cross-platform desktop app for macOS, Windows and Linux, and it is extensible for people who want to adapt it. The project was born from an accessibility conviction — its motto is that accessibility tooling belongs in everyone’s hands, not behind a paywall — and it is actively maintained, with updates in October 2026.
Handy is part of a broader pushback against subscription dictation services: the models it runs are open, the audio never leaves the device, and the app itself costs nothing — a combination that cloud competitors structurally cannot match. It is also genuinely useful beyond accessibility: developers dictate commit messages and prompts, writers draft hands-free, and anyone with repetitive-strain issues gets a real alternative to the keyboard. Support for multiple Whisper sizes lets low-end machines trade a little accuracy for speed while desktops with GPUs run the largest models in near real time.
Handy is completely free and open source under the MIT license — no subscriptions, no paid tiers, no catch.
Writers, developers, accessibility users and privacy-conscious professionals who want fast, accurate dictation without sending their voice to the cloud.