Speech & VoiceEditorially verifiedFeatured
Handy
cjpais/Handy
Offline desktop speech-to-text that inserts transcriptions into the active text field.
A cross-platform transcription application designed to run locally. The README describes Whisper model options with optional GPU acceleration and Parakeet V3 with CPU-optimized inference. It supports Windows, macOS, and Linux and does not require sending speech to a hosted transcription service.
GitHub stars
37,262
Forks
3,505
Open issues
176
Primary language
Rust
Repository details
- License
- MIT LicenseMIT
- Default branch
- main
- Last commit
- Nov 2, 2026
- Repository updated
- Nov 3, 2026
- Last metadata check
- 2026-11-03
- Setup difficulty
- beginner
- Self-hosting
- Self-hostable
- GPU
- Not required
- API key
- Not required
- Paid service
- Not required for documented default
Categories & platforms
Speech & VoiceSelf-hosted Apps
Supported platforms
Windows · macOS · Linux
Topics
speech-to-textofflineprivacydesktopRust
Editorial notes
Public, active and unarchived. GitHub reports MIT. README describes local offline transcription; GPU is optional and a CPU-optimized model is available. Model downloads and disk/compute requirements still apply.
View license on GitHub