VS Code Extension
Your code in your ear.
Just start talkingbuilding.
Verbative is an agentic development extension for VS Code — a truly hands-free voice layer that drives the Claude Code CLI. Right inside your editor.
Put on your headphones and Claude is in your ear, ready to build. Code completely hands-free — from the couch, on a walk, eyes closed mid-thought. Wherever you can talk, you can ship. Verbative keeps you in the loop on every permission, every decision, every line — without your hands ever touching the keyboard.
It drives the Claude Code CLI in your terminal and runs on your existing Claude Pro or Maxsubscription — no API key, no SDK, nothing extra to set up.
Free forever for 10 hands-free loops a day. Advanced from €4.99/month.
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
Channels · parallel agents
Operate multiple CLI agents at once. One voice conducts them all.
Real work isn't one thread. Group your Claude sessions into channels and run several agents inside each, all in parallel — every agent in its own terminal split, sharing one memory. Your dictation and the voice key always go to the agent you've selected: it's highlighted in the panel and wears the orange status bar inside its terminal, so you always know where your next prompt lands. And the purple bar pulses on whichever agent is speaking aloud right now.
Each channel runs its own Claude agents in parallel. Your voice goes to the selected agent.
One window: the Verbative panel on the left, each agent's live terminal on the right. Every agent carries a status bar right inside its split — channel, agent, time, tokens, and context used.
Parallel agents, one voice
Each agent is its own live Claude session in its own terminal, working at the same time as the others. Your voice and dictation route to whichever agent you've selected — switch the active agent with a click and your next prompt lands there.
Shared memory per channel
Every channel keeps a shared notes file that's injected into each agent's prompt. Note a decision, file change, or convention there — or ask an agent to — and every other agent sees it on their next turn. No re-explaining context to each session.
Survives a restart — resume in one click
Channels are organized by project, feature, or concern and saved with your repo, so every agent stays bound to its own Claude session. Close VS Code and reopen it — your whole layout comes back, and a single click relaunches an agent straight into its exact conversation, not a blank one. Start over anytime with New session.
Lives in the Verbative panel — pick the active channel and agent, and your voice follows. The layout and each agent's bound session persist in .verbative/workspaces.json in your repo, so reopening VS Code is one click from right where you left off.
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
≈ 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
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.
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.
Quality is strongest for the major languages above; lower-resource languages still work but translate less cleanly.
Verbative Shot · power feature
Show Claude exactly what you see. Every region, one paste.
The fastest way to give Claude visual context. Hit ⌃⌘S or the panel button and drag over whatever Claude can't see — a design you want built, a render that looks wrong, an architecture sketch to scaffold from. Keep dragging, region after region; press Esc when you're done. They're stacked into a single image on your clipboard, so one paste drops the whole picture into Claude. No screenshot files, no digging through a folder, no attaching one image at a time.
- ✓Drag anywhere on screen — straight to your clipboard
- ✓Several in a row stack into one image — paste once
- ✓Captured on-device by macOS — nothing is ever uploaded
Free includes 10 captures a day · Advanced is unlimited.
⌃⌘S · drag, drag, drag → paste once
Project Roadmap · power feature
A map and a board that build themselves as Claude works.
Hands-free, you lose the screen — so you lose the thread of what's done and what's next. Project Roadmap is a live map of your project plus a Spec → Build → Review → Ship board that Claude keeps in sync as it goes. Each card carries its own git lifecycle: a branch when work starts, WIP commits as it builds, a diff to review, a merge and a tag when it ships. As Claude moves cards, Verbative speaks each milestone aloud — so you stay oriented without looking.
Git lifecycle per card
Moving a card isn't cosmetic. Build branches off, commits land as the work progresses, Review surfaces the diff, and Ship merges and tags — so the board and your repo never drift apart.
Kept in sync, hands-free
Claude updates the board as it works — no dragging cards yourself. Each move is spoken aloud (“Updating the roadmap.” … “Roadmap updated.”), so you know what shifted in Spec, Build, Review, or Ship without looking.
A living project map
Beyond the board, Verbative maintains a high-level map of your project so a fresh session — or a fresh you, after a walk — picks up with the full picture instead of a cold start.
Lives in the Verbative panel and in .verbative/ in your repo — kept on your machine (Verbative gitignores it by default). Open it from the panel, or say “project roadmap” by voice.
Advisory Board · power feature
A standing design-review panel for every idea. One Tech Lead writing the code.
When you're reaching for a new feature or rethinking your architecture, you want a guiding second look before you commit. Flip Advisory Board on and every prompt is reviewed in parallel by a panel of domain advisors — so a fresh design is held up against the standards each discipline cares about: correctness, security & compliance, UX, testability, scope, operability. They speak their concerns aloud in distinct voices, your Tech Lead does the work, then the same panel reviews the result and forces one revision if anything was missed. Bounded at exactly one revision pass — no infinite back-and-forth. And the board is yours: deactivate any advisor or add your own with its own focus and voice.
- { }BackendAdvisor · Haiku · own voice
API design · DB schema · scalability
- <>FrontendAdvisor · Haiku · own voice
UX · a11y · perceived latency
- ⛨Security & ComplianceAdvisor · Haiku · own voice
GDPR · CCPA · vulnerabilities
- ✓✗QA EngineerAdvisor · Haiku · own voice
Edge cases · regression risk · coverage
- ◐Product ManagerAdvisor · Haiku · own voice
Scope · alternatives · brand trust
- ↻DevOps / SREAdvisor · Haiku · own voice
Deploy · observability · rollback
In their lane
Each advisor only speaks when the concern is in their domain. Security flags GDPR risk. Product flags brand exposure. Backend doesn't pile on legal — it focuses on the API surface. Out-of-lane piling-on is explicitly forbidden.
Spoken in distinct voices
Every role gets its own neural voice via Kokoro. You instantly know who's talking — no need to look at the screen. All synthesis runs locally.
Your board, your standards
Activate or deactivate any advisor, or add your own — give it a name, a focus, and a voice, and it joins the review. Click any advisor to see, read-only, the exact instructions it's given. Bounded at one revision pass: review, work, review, one fix — then the loop ends.
Each advisor is a separate, lightweight Haiku call, all running in parallel. Toggle the board in the Verbative panel, or say “advisory board” by voice.
Mechanics · power feature
The commands you run all day, one click away.
Every project has the same handful of shell commands you keep retyping — start the dev server, spin up a browser, reset the database, kick off a build. Mechanics are reusable shell scripts you save once and run from the Verbative panel. Organize them into groups you create, rename, and delete; write each script in a built-in editor or import an existing .sh file. Every Mechanic runs in its own terminal — so it gets your real shell and PATH, streams its output live, and stops with one click.
Each Mechanic runs in its own terminal — your real shell and PATH, live output, one-click stop.
Runs in its own terminal
Each Mechanic launches in a real VS Code terminal, so it inherits your login shell and PATH (the thing a bare command usually trips on), shows live output, and stops cleanly when you hit the button.
Organized in groups
Group related Mechanics together — a Dev group, a Chores group, whatever fits how you work; create, rename, and delete them freely. They live with your project, so the whole team gets the same toolbox.
Write inline or import a script
Type a quick one-liner in the built-in shell editor, or import an existing .shfile to pull its contents in. Edit any Mechanic anytime — it's saved as plain text in your project.
In the Verbative panel, below the Advisory Board. Free includes up to 2 Mechanics; Advanced is unlimited.
The whole loop is voice-first.
Wake, dictate, listen, approve, interrupt, recap — every step of working with Claude Code CLI has a voice command. No keyboard required.
Wake & dictate
Say "listen" — Claude Code CLI starts recording. Speak your prompt naturally; "stop listening" submits it. Not happy with what you said? "hold on" cancels the flow without touching Claude.
Hear Claude back
When Claude finishes a turn, a Tech Lead summary plays through your headphones in a neural voice. A subtle pulse keeps playing while a tool runs, so you always know whether it's still working or waiting on you.
Approve by voice
Every permission prompt is spoken aloud — what tool, what file, what command. Reply "approve", "deny", or "explain" for a 1-2 sentence Haiku-generated breakdown of the pending tool call before you decide.
Stay in flow
"update" gives a live progress recap mid-task; "repeat" replays the last cue (and "repeat review" the last advisor batch). "stop claude" interrupts a running task. "skip", "pause" and "resume" control whatever cue is speaking. "advisory board" toggles a customizable design-review panel; "project roadmap" toggles a live spec→build→review→ship board.
Built for people who actually code all day.
Privacy-first: your voice never leaves your Mac
Local transcription is on by default on every plan — the entire prompt is converted to text on-device with whisper.cpp. No audio, ever, to any cloud. Fully hands-free, completely private. Pick the model (tiny → large-v3) for the accuracy you want on any plan, or switch to Cloud anytime.
Speak any language — translated on-device
Dictate your prompt in German, Spanish, Japanese, French — whatever you think in. Verbative translates it to English entirely on your Mac with whisper.cpp, then types the clean English prompt into the CLI. No audio leaves your machine. It's always on, on every plan, and your voice commands always stay English. On the full Large v3 model it even names the language it heard.
Wake-word runs on-device
whisper.cpp speech recognition is bundled inside the extension. Your microphone stays local — in Local mode it never leaves at all; in Cloud mode it stays put until Claude Code CLI itself starts recording the prompt.
Bluetooth headsets, properly
We use AVCaptureSession (the path FaceTime and Zoom use) so AirPods and HFP headsets actually deliver audio instead of silence.
Plug in, it just switches
Plug in AirPods or headphones and Verbative auto-switches input and output to the new system default, flips mic-mute off for headphones (audio stays in your ear, no self-trigger risk), and speaks a confirmation naming the device. Pin a specific input or output in the panel to override.
Status-bar awareness
A single status-bar item tells you at a glance: armed, recording, or off. The side panel shows a live waveform when actively capturing.
Cloud accuracy or full privacy — your call
Cloud mode triggers Claude Code CLI’s built-in dictation — same accuracy, same model, no extra cost. Local mode (available and on by default on every plan) transcribes entirely on-device with whisper.cpp — nothing leaves your Mac. One toggle, your choice.
No per-command server calls Advanced
Advanced subscribers get a signed license token cached locally for 48 hours — Verbative itself never pings our server during normal use. (Claude Code CLI still needs the internet to reach Anthropic.)
Free to try. Cheaper than your coffee.
10 hands-free loops a day for free, forever. When you need more, Advanced unlocks unlimited from €4.99/month — 50% off for your first 3 months, or save 30% annually.
See pricingFrequently asked
- How is this different from Claude.ai’s voice mode?
- Claude.ai voice is chat-only — a spoken conversation in the browser, no tools, no files, no commands. Verbative is an agentic development extension for VS Code that drives the Claude Code CLI — the agent that actually edits your repo and runs commands in your terminal — by voice. Crucially you don’t have to flip on auto-accept and lose visibility: every permission Claude Code CLI asks for is spoken aloud with what it’s about to do, and you say “approve”, “deny”, or “explain” to act on it. Full information, you stay in the loop, no keyboard.
- What does this actually do that Claude Code CLI doesn’t already?
- Claude Code CLI has built-in dictation, but you have to press a key to start and stop it, and there’s no voice path for permission prompts, status checks, or aborting a run. Verbative adds the wake word, voice-driven permission approval with full spoken explanations, “update” for a spoken status check while Claude is working, and “stop claude” to abort. The keyboard becomes optional, not required.
- What's Advisory Board?
- An opt-in design-review panel for your ideas. When you’re adding a feature or rethinking your architecture, every prompt is reviewed in parallel by a panel of domain advisors — by default Backend, Frontend, Security & Compliance, QA, Product Manager and DevOps — before your Tech Lead session even responds, so a fresh design gets a guiding second look against each discipline’s standards. Each runs as a one-shot Haiku call, each gets its own distinct voice via Kokoro, and each only speaks when the concern is genuinely in their lane. After the Tech Lead does the work, the same panel reviews the result; if anything was missed they force exactly one revision pass, then the loop ends. The board is fully customizable: deactivate any advisor, or add your own with its own name, focus and voice — and click any advisor to see, read-only, the exact instructions it’s given. Toggle in the Verbative sidebar or say “advisory board” by voice.
- Is my voice sent to your servers?
- Never to ours. And with Local mode, not to anyone’s. You choose how the prompt is transcribed: Cloud mode uses Claude Code CLI’s own dictation on Anthropic’s infrastructure (we only ever see usage counts — no audio, no transcripts), while Local mode — privacy-first, available and on by default on every plan — transcribes the entire prompt on-device with whisper.cpp. Your voice never leaves your Mac. (Your pick of whisper model, tiny → large-v3, is available on every plan.) Either way, wake-word detection is always local.
- What languages can I speak?
- Roughly 99. Just speak — Verbative translates whatever you dictate to English on-device with whisper.cpp before it ever reaches Claude. It's always on, on every plan, with nothing to switch on. The major languages — Spanish, French, German, Italian, Portuguese, Dutch, Russian, Polish, Ukrainian, Chinese, Japanese, Korean, Hindi, Arabic, Turkish, and more — translate cleanest; lower-resource languages still work but a little less smoothly. The voice commands themselves always stay English, and on the full Large v3 model Verbative also names the language it heard.
- What gets metered?
- Only the Free tier — and only with daily caps. On Free, each successful "listen" wake is one hands-free loop (10 a day, resetting 00:00 UTC), and Advisory Board reviews, Project Roadmap updates, and Verbative Shot captures get 10, 10, and 10 a day respectively. On Advanced, nothing is metered, counted, or capped: it's unlimited.
- Does it work without internet?
- Claude Code CLI itself always needs the internet — that's Anthropic's API. What 'offline' means here is our licensing: Free has to ping our server per hands-free loop (so it goes down if we do); Advanced caches a signed license for 48 hours so our backend can be unreachable without locking you out of Advanced features.
- Which platforms?
- macOS only at launch. Windows and Linux are on the roadmap — vote on the docs page.
- Cancel anytime?
- Yes. One click in the customer portal. You keep Advanced until the end of the billing period, then drop back to the free tier with the same license.
Code like it's the future.
Install the extension, say hey to Claude, and watch your hands fall idle.
Get Verbative