🎙️ VoxPilot
Talk to your IDE coding assistant. On-device speech recognition. No API keys. No cloud. Just your voice.
Ctrl+Alt+V
🎙️ "Create a REST API endpoint for user authentication using JWT"
📝 Transcribed locally in ~200ms
💻 Sent to Copilot Chat → code generated
Why VoxPilot?
🔒
100% On-Device
Your audio never leaves your machine. No API keys, no cloud calls, no telemetry. Privacy by design.
🤖
Works With Any Assistant
GitHub Copilot, Continue, Kiro, Cody — any VS Code chat participant. Just configure and talk.
⚡
Tiny and Fast
27MB model downloads once, runs forever. No waiting for cloud responses. Transcription in milliseconds.
♿
Accessibility First
Voice input for developers with RSI, carpal tunnel, or mobility limitations. Code without pain.
🌍
Cross-Platform
Linux, macOS, Windows. Uses native audio tools already on your system.
📖
Open Source
MIT licensed. Fork it, extend it, contribute. The codebase is small and clean.
How It Works
Microphone → PCM Audio → Voice Activity Detection → Moonshine ASR → Text → VS Code Chat
—
Downloads
27MB
Tiny model size
0
Cloud dependencies
3
Platforms supported
MIT
Licensed
Get Started
Install, press Ctrl+Alt+V, and start talking. That's it.