Handy is a cross-platform desktop application that provides simple, privacy-focused speech transcription. Press a shortcut, speak, and have your words appear in any text field — all happening on your own computer without sending any information to the cloud.
Key Features
- Free & Open Source: Accessibility tooling belongs in everyone's hands, not behind a paywall. MIT licensed.
- Privacy-First: Your voice stays on your computer. Get transcriptions without sending audio to the cloud.
- Simple: One tool, one job. Transcribe what you say and put it into a text box.
- Extensible: Built to be the most forkable speech-to-text app. Take it, modify it, build something amazing.
How It Works
- Press a configurable keyboard shortcut to start/stop recording (or use push-to-talk mode)
- Speak your words while the shortcut is active
- Release and Handy processes your speech
- Get your transcribed text pasted directly into whatever app you're using
Technical Details
- Silence filtering using VAD (Voice Activity Detection) with Silero
- Multiple transcription models:
- Whisper models (Small/Medium/Turbo/Large) with GPU acceleration
- Parakeet V3 — CPU-optimized model with automatic language detection
- Cross-platform: Works on Windows, macOS, and Linux
- Tray integration: Lives in your menu bar for quick access
Installation
- macOS:
brew install --cask handyor download from website - Windows:
winget install cjpais.Handyor download from website - Linux: Download from GitHub releases
Handy was created to fill the gap for a truly open source, extensible speech-to-text tool. It isn't trying to be the best speech-to-text app — it's trying to be the most forkable one.
