Voice mode and dictation for Claude Code in VS Code
The heart of Verbative: your voice drives the Claude Code CLI, and you stay in control of every step.
Approve or deny each permission out loud, dictate prompts in any language, and keep every word on-device — no keyboard, no loss of visibility.
The real thing
Not a mockup — the actual extension
The Verbative panel as it runs in VS Code — not a render.
One panel, completely hands-free
Wake by voice, dictate your prompt, and watch the live equalizer react as you speak. The whole loop — listen, send, approve, hear the result — lives in a single VS Code side panel.
- ✓ On-device or cloud transcription, switchable in a tap
- ✓ Spoken summaries, permission prompts, and progress in your ear
- ✓ Works on your existing Claude Pro or Max plan
Eyes-free, hands-free
Code from anywhere you can talk — no screen, no keyboard, just your voice driving the CLI.
Always in the loop
Every permission, decision, and summary is spoken aloud, so going hands-free never means going blind.
Your own subscription
Runs on your existing Claude Pro or Max plan through the Claude Code CLI — no API key, no SDK.
A full voice vocabulary
Every part of the loop has a spoken command — listen, stop listening, approve, deny, explain, update, stop claude and more. Advanced users can rename any trigger to whatever feels natural.
Real-time, on-device
Every millisecond runs on your machine's GPU — measured, not estimated.
Speech → text
≈ half a second, however long you talk.
Text → speech
A steady ~23×, at any length.
~65 ms to first sound on a short cue · MacBook Advanced, Apple M1 Max · whisper large-v3-turbo + Kokoro, fully on-device.
Advanced: tap ✎ to rename any phrase to whatever feels natural
No more blind auto-accept
Hear what Claude will do before it does it, and answer by voice — the safety of manual review at the speed of hands-free.
“Explain” before you decide
Unsure about a request? Say “explain” and Verbative reads back the reasoning so you can make the call with full context.
Built for parallel agents
When several agents run at once, each request is queued and announced in order so you always know which agent is asking.
Speak any language · power feature
Speak in your language. Claude gets a clean English prompt.
Just dictate in German, Spanish, Japanese, French — whatever you think in. Verbative translates your prompt to English on your machine with whisper.cpp and types it straight into the Claude Code CLI. No audio, no text, ever leaves your machine — the same privacy story as local dictation. There's nothing to switch on: it's always there.
- ✓ Any language in, a clean English prompt out — nothing to set up per language.
- ✓ 100% on-device translation, so your voice never leaves your machine.
- ✓ Always on, on every plan — local transcription is free and on by default.
- ✓ Your voice commands always stay English — only your prompt is translated.
- ✓ On the full Large v3 model it even names the language it heard.
Speak in ~99 languages — translated to English on-device.
Quality is strongest for the major languages above; lower-resource languages still work but translate less cleanly.
Think in your language
Dictate naturally in your mother tongue; Claude receives clean English. No mental translation, no broken prompts.
On-device and private
Translation happens locally with whisper.cpp — your voice never leaves your machine just to be understood.
~99 languages, zero setup
From Spanish to Hindi to Korean, it's on by default. The voice commands themselves stay English so nothing gets ambiguous.
Local dictation · power feature
See your words appear as you speak. Edit them and attach visual context.
In Local mode your prompt is transcribed entirely on your machine with whisper.cpp — and it streams the text live as you talk, word by word, into an editable box. Caught a wrong word, a missing “not”, a misheard file name? Click and fix it before it ever reaches Claude. No re-recording, no “undo, try again” — just correct it and hit send.
- ✓ Streaming partials from a warm whisper-server — no per-prompt model reload
- ✓ Click any word to fix it before it's sent — a misheard name, a missing “not”
- ✓ Paste an image to attach visual context to your prompt
- ✓ Pick the model (tiny → large-v3) for the accuracy you want
- ✓ 100% on-device — your voice never leaves your machine
Local transcription is available — and on by default — on every plan.
Private by default
Local mode keeps every word on-device. We only ever see usage counts — never audio, never transcripts.
Live transcript
Watch your words appear in real time from a warm whisper-server, so you know it heard you right.
Your model, your tradeoff
Pick your whisper model on any plan — tiny for speed, large-v3 for accuracy and translation.
Read the deep dives
- Claude Code voice mode in VS Code: from dictation to fully hands-free
How the built-in /voice dictation works, where it stops, and how the hands-free loop goes the rest of the way.
- Get a sound or a spoken summary when Claude Code finishes
The terminal bell, a Notification or Stop hook that plays a sound, and a voice that says what actually happened.
- Claude Code permissions: what auto mode still asks you, and how to answer it by voice
Auto mode is the default now; what the modes and allow rules really do, and how to answer the prompts that remain without the keyboard.
- Claude Code on Windows — voice, dictation and hands-free setup
Built-in dictation on Windows 10 and 11, the WSL caveats, the microphone toggle, and going hands-free on-device.
Frequently asked
Does Claude Code have a voice mode in VS Code?
Yes — push-to-talk dictation. Turn it on with /voice, hold Space (or tap to start and tap again to send), and your words land in the prompt. It works in the terminal and in Anthropic's VS Code extension, needs a Claude.ai sign-in, and streams your audio to Anthropic's servers for transcription. What it doesn't do: listen for a wake word, speak replies back, or let you answer permission prompts by voice — you're still at the keyboard. Verbative adds that hands-free loop on top of the Claude Code CLI in VS Code: say “listen”, dictate, say “stop listening”, and hear the summary spoken back.
What does Verbative add on top of the built-in dictation?
The whole loop, not just the input. A wake word so your hands stay off the keyboard; every permission prompt read aloud so you can say “approve”, “deny”, or “explain”; replies, progress, and summaries spoken back in a natural neural voice; “update” for a spoken status check while Claude is working; “stop claude” to abort; and a team of agents you switch between by voice. In Local mode (the default), dictation itself runs on your machine with whisper.cpp in ~99 languages, translated to English before it reaches Claude; Cloud mode uses the Claude Code CLI's own dictation instead.
Is my voice sent to the cloud?
Not with Local mode, which is on by default on every plan: wake-word detection and the full prompt are transcribed on your machine with whisper.cpp, so no audio leaves it. If you prefer the Claude Code CLI's own cloud dictation, switch to Cloud mode — Verbative then just drives it for you. Either way our servers never see your audio, your code, or your prompts.
Can I keep using the Claude Code CLI's built-in dictation with Verbative?
Yes. Cloud mode uses the Claude Code CLI's own dictation for the transcript while Verbative handles the wake word, the spoken replies, and the voice-answered permissions around it. Local mode replaces the transcription with on-device whisper.cpp — your pick of model, from tiny to Large v3, on every plan.
Does it work on Windows and in other languages?
macOS and Windows, inside VS Code. Dictate in roughly 99 languages — Verbative translates what you say to English on-device before it reaches the Claude Code CLI, with nothing to switch on. The voice commands themselves stay English so nothing is ambiguous.
Code like it's the future.
Install the extension, say "listen", and watch your hands fall idle.
Get Verbative