Claude Voice

Talk to Claude instead of typing. Press Ctrl+Alt+V (Windows/Linux) or Control+Option+V (Mac), speak your prompt, and it appears in Claude Code's chat input — ready to send.

No API key. No cloud. No subscription. Runs 100% offline on your machine.

Why Claude Voice?

No API key required — just install and speak
Your voice never leaves your computer — speech is processed locally on your machine
Works offline — no internet connection needed after the initial model download
Free to use — no per-request costs, no subscriptions

Setup

Install the extension. That's it.

On first use, if Python dependencies are missing, the extension will prompt you to install them automatically. Look for the 🎤 Voice button in your status bar.

The first use downloads a ~140 MB speech recognition model. After that, everything runs fully offline with no internet connection required.

How to use

Press Ctrl+Alt+V (Windows/Linux) or Control+Option+V (Mac) — or click 🎤 Voice in the status bar
Speak your prompt naturally
Pause for ~1 second when done — your words appear in Claude Code's chat input
Press Enter to send

Press Ctrl+Alt+V again at any time to cancel.

Requirements

Claude Code extension installed
Python 3.9 or higher
A microphone

Settings

Setting	Default	Description
`claude-voice.focusTarget`	`claude`	`claude` = always focus Claude Code input before pasting. `none` = paste wherever focus already is (works with any input field).
`claude-voice.language`	`en`	Spoken language. Pick your language from the dropdown for best accuracy and speed. Changing this setting restarts the voice backend automatically.

Also available: vtype

For voice input outside VS Code — in any terminal, browser, or app — check out vtype, the standalone companion tool:

pip install vtype
vtype

Same offline Whisper engine, types into whatever window is focused.

Telemetry

Anonymous usage data is collected (transcription count, latency, word count, platform) to help improve the extension. No audio or transcribed text is ever sent. Respects VS Code's global telemetry setting — disable under Help → Privacy → Telemetry.

Troubleshooting

macOS — pynput requires Accessibility permissions: System Settings → Privacy & Security → Accessibility → enable VS Code.

Linux — Requires xdotool: sudo apt install xdotool

Slow first transcription — Whisper loads on first use (~5s). Subsequent transcriptions are faster.

Claude Voice

Jaspal Singh Saluja

Claude Voice

Why Claude Voice?

Setup

How to use

Requirements

Settings

Also available: vtype

Telemetry

Troubleshooting