Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A free, open source, and extensible speech-to-text application that works completely offline.
| Date | Stars |
|---|---|
| 2026-07-24 | 27390 |
| 2026-07-25 | 27466 |
| 2026-07-28 | 27466 |
| 2026-07-30 | 27466 |
| 2026-08-06 | 27466 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
# Handy
[](https://discord.com/invite/WVBeWsNXK4)
**A free, open source, and extensible speech-to-text application that works completely offline.**
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. This happens on your own computer without sending any information to the cloud.
## Why Handy?
Handy was created to fill the gap for a truly open source, extensible speech-to-text tool. As stated on [handy.computer](https://handy.computer):
- **Free**: Accessibility tooling belongs in everyone's hands, not behind a paywall
- **Open Source**: Together we can build further. Extend Handy for yourself and contribute to something bigger
- **Private**: 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
Handy isn't trying to be the best speech-to-text app—it's trying to be the most forkable one.
## How It Works
1. **Press** a configurable keyboard shortcut to start/stop recording (or use push-to-talk mode)
2. **Speak** your words while the shortcut is active
3. **Release** and Handy processes your speech using Whisper
4. **Get** your transcribed text pasted directly into whatever app you're using
The process is entirely local:
- Silence is filtered using VAD (Voice Activity Detection) with Silero
- Transcription uses your choice of models:
- **Whisper models** (Small/Medium/Turbo/Large) with GPU acceleration when available
- **Parakeet V3** - CPU-optimized model with excellent performance and automatic language detection
- Works on Windows, macOS, and Linux
## Quick Start
### Installation
1. Download the latest release from the [releases page](https://github.com/cjpais/Handy/releases) or the [website](https://handy.computer)
- **macOS**: Also available via [Homebrew cask](https://formulae.brew.sh/cask/handy): `brew install --cask handy`
- **Windows**: Also available via [winget](https://github.com/microsoft/winget-pkgs): `winget install cjpais.Handy` \
**Note:** The Homebrew cask and winget package are not maintained by the Handy developers.
2. Install the application
3. Launch Handy and grant necessary system permissions (microphone, accessibility)
4. Configure your preferred keyboard shortcuts in Settings
5. Start transcribing!
### Development Setup
For detailed build instructions including platform-specific requirements, see [BUILD.md](BUILD.md).
## Integrations
<a href="https://www.raycast.com/mattiacolombomc/handy" title="Install Handy Raycast Extension"><img src="https://www.raycast.com/mattiacolombomc/handy/[email protected]?v=1.1" height="64" style="height: 64px;" alt="Install handy Raycast Extension" /></a>
Control Handy from [Raycast](https://www.raycast.com) — start/stop recording, browse transcript history, manage dictionary, switch models and languages.
[Source](https://github.com/mattiacolombomc/raycast-handy) · by [@mattiacolombomc](https://github.com/mattiacolombomc)
## Architecture
Handy is built as a Tauri application combining:
- **Frontend**: React + TypeScript with Tailwind CSS for the settings UI
- **Backend**: Rust for system integration, audio processing, and ML inference
- **Core Libraries**:
- `transcribe-cpp`: Local speech recognition with Whisper-family models (GGML/GGUF)
- `transcribe-rs`: CPU-optimized speech recognition with Parakeet models
- `cpal`: Cross-platform audio I/O
- `vad-rs`: Voice Activity Detection
- `rdev`: Global keyboard shortcuts and system events
- `rubato`: Audio resampling
### Debug Mode
Handy includes an advanced debug mode for development and troubleshooting. Access it by pressing:
- **macOS**: `Cmd+Shift+D`
- **Windows/Linux**: `Ctrl+Shift+D`
### CLI Parameters
Handy supports Excerpt of 21,680 characters
Read on GitHub
CJ Pais
506
Vlad Gerasimov
22
Viren Mohindra · NYU · Hong Kong
17
Evgeny Khudoba · Russia
12
Jackson · @tonarino
7
Mika Krul · Netherlands
7
Fero
6
Phuoc Thinh Vu
4
Alexander Yastrebov · @DataDog · Germany
4
Maicon
4
Sami Ansari · Canada
4
Zorin Os Team
3
3
3
Shehab Tarek · Egypt
3
Jorge · @ducflair · Portugal
3
Danny Smith · United Kingdom
3
Brandon · Taiwan
3
Erwann Mest · Sony Music · United Kingdom
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:67e7e2b6f241eee4, topic:speech-to-text, readme:speech recognition, desc:speech-to-text