🎙️ VoxPilot

Talk to your IDE coding assistant. 3 model families, 90+ languages, streaming transcription. 100% on-device.

CI Open VSX Downloads GitHub Stars MIT License Telemetry-Free No Cloud
Install from Open VSX View on GitHub
Ctrl+Alt+V
🎙️ "Create a REST API endpoint for user authentication using JWT"
📝 Transcribed locally — auto-capitalized, auto-punctuated
💻 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.

🧠

3 Model Families

Moonshine (fast), Whisper (90+ languages), Parakeet (real-time streaming). Pick the right tool for the job.

🤖

Works With Any Assistant

GitHub Copilot, Continue, Kiro, Cody — any VS Code chat participant. Just configure and talk.

⚡

Real-Time Streaming

See partial transcripts appear as you speak with Parakeet. Like live captions for your voice.

✨

Smart Text Processing

Auto-capitalize, auto-punctuate, voice commands, noise gate. Your transcripts arrive clean and ready.

🎯

Flexible Output

Send to chat, insert at cursor, copy to clipboard, or choose each time. You control where text goes.

♿

Accessibility First

Voice input for developers with RSI, carpal tunnel, or mobility limitations. Code without pain.

🌍

Cross-Platform

Linux, macOS, Windows. VS Code and Kiro. Uses native audio tools already on your system.

Models

Browse, download, and switch models from the built-in Model Manager panel.

ModelSizeStrength
Moonshine Tiny~27MBFastest, quick commands
Moonshine Base~65MBFast, better accuracy
Whisper Tiny~75MB90+ languages, fast
Whisper Base~150MB90+ languages, balanced
Whisper Small~500MB90+ languages, high accuracy
Whisper Large v3 Turbo~3GB90+ languages, best accuracy
Parakeet TDT 0.6B~150MBReal-time streaming, live captions

How It Works

Microphone → Noise Gate → Adaptive VAD → ASR Model → Post-Processing → Delivery

🛡️ Privacy & Trust

🚫Zero telemetry — No usage tracking, no analytics, no phone-home
🔒Zero cloud — Audio processed entirely on-device via ONNX Runtime
🙅Zero data collection — No accounts, no sign-ups, no personal info
🔍Fully auditable — MIT-licensed, open source. Read every line
🎤Minimal permissions — Only microphone access. No network beyond model download
📜Privacy policy — Clear, human-readable policy with no legalese
—
Downloads
7
ASR models
90+
Languages
0
Cloud dependencies
MIT
Licensed

Get Started

Install, press Ctrl+Alt+V, and start talking. That's it.

Install from Open VSX View Source