Verbative

Talk to your code — voice control for Claude Code CLI

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
Default Channel · Agent 1
Idle — waiting for voice command
Speed 1.3×

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 Mac's GPU — measured, not estimated.

Speech → text

you spokeprocessed invs real time
5 sec0.4 s12×
15 sec0.5 s30×
30 sec0.6 s48×

≈ half a second, however long you talk.

Text → speech

reply lengthprocessed invs real time
5 sec0.22 s23×
15 sec0.65 s23×
30 sec1.3 s23×

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.

Voice commandson-device
Listen & dictate
listenWake — start a promptstop listeningSend the prompthold onCancel listening
Approve by voice
approveAllow the pending tooldenyBlock itexplainHear what it would do firstopen queuesRe-hear the open permission cue
Stay in flow
updateLive progress recapstop claudeInterrupt the running taskrepeatReplay the last cueskipSkip the cue playing nowpausePause the cue · resume to continue
Toggles
advisory boardSix-advisor design reviewproject roadmapLive spec → build → ship board
resumerepeat review+ more

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.

Default Channel · Agent 1
Listening — any language…local
Deutsch detected→ English
Orange = your words, any languageCancelSend ↵

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 Macwith 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 Mac.
  • 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.

SpanishFrenchGermanItalianPortugueseDutchRussianPolishUkrainianChineseJapaneseKoreanHindiArabicTurkishVietnameseIndonesianCzechSwedishGreek+ dozens more

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.

Default Channel · Agent 1
Transcribing on-device…local
Orange = still being transcribedCancelSend ↵
Speed 1.3×

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 Macwith 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 Mac

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.