For Claude Code

Claude Code's voice mode
is great. For Claude Code.

Voca is what you use everywhere else.

Anthropic shipped /voice for Claude Code in March 2026. It's good. Inside the Claude Code session, prompting by voice is now trivial. Outside it, the rest of your day is still typed: commit messages, PR descriptions, Slack threads with the engineer reviewing your branch, Linear tickets the agent's just unblocked, the doc you're updating because the feature shipped.

Voca is a system-wide voice layer that picks up where /voice stops. Same hotkey wherever your cursor sits. Works on Windows, macOS, and Linux.

Try it in your browser Download desktop

No install for the demo, no card required.

01 · Where /voice stops

Inside Claude Code,
the prompt is the easy part.

/voice is the right tool for one job: turning your speech into the prompt you're sending Claude Code in this session. Push-to-talk, included in Pro/Max/Team/Enterprise plans, low friction.

What it doesn't do, by design:

01 · COMMITS

Write the commit message after the change lands.

/voice gave you the prompt. Now you need a sentence that explains the diff. Hotkey in the terminal, dictate, hit enter.

02 · PRs

PR descriptions for the reviewer.

Walk through the change in plain English. Why, what, what's left. Voca drops the prose into GitHub's PR body the same way you'd dictate it into a doc.

03 · REVIEWS

Reply to comments in GitHub or Linear.

The reviewer's left a question. Open the comment, hit the hotkey, answer the way you'd answer in person. Send.

04 · DOCS

Update the doc the agent should have updated.

Notion, Obsidian, README, internal wiki. Voca treats them like any other text field.

05 · SLACK

Tell the team the feature's live.

The Slack message that explains what shipped, who it affects, and what to look out for. Dictated in the time it takes to type the first sentence.

06 · OTHER PROMPTS

Prompt ChatGPT, Claude.ai, Cursor.

Other AI tools, other text boxes, other agents. Voca works in every one of them — including the apps that don't have a /voice equivalent of their own.

For everything that isn't a Claude Code prompt, you're back on the keyboard. That's the gap Voca fills.

02 · The loop

A voice-first day
with Claude Code.

A typical loop with Voca and /voice running together.

Same hand on the same modifier key for the entire loop. The keyboard's job becomes navigation and quick fixes. Everything that's prose is voice.

01

Hold spacebar in Claude Code.

Describe the change you want, release. Claude Code makes the change.

02

Voca hotkey in your terminal.

Dictate the commit message, hit enter. Done.

03

Switch to GitHub.

Voca hotkey, dictate the PR description. Done.

04

Voca hotkey in Slack.

Tell the team the PR is up. Done.

05

Back to Claude Code.

Hold spacebar, describe the next change.

03 · Linux

Voca runs
where Claude Code runs.

Claude Code ships for macOS, Linux, and Windows (via WSL). A meaningful share of Claude Code users are on Linux because Claude Code is a CLI tool and Linux developers do most of their work in a terminal anyway.

The dictation tools that pair well with that workflow: Voca. The dictation tools that don't ship for Linux: Wispr Flow, Willow, Voibe, VoiceInk, Superwhisper, Monologue, Weesper, every other commercial option. If you're on Ubuntu or Fedora or Arch and you want voice for the parts of your day that aren't inside /voice, Voca is the option that exists.

Dictation on Linux

04 · Privacy

Your codebase
isn't training data.

Code in private repos shouldn't end up in someone else's model. Voca's posture matches Claude Code's own zero-data-retention guarantees: audio is deleted on transcription, never used for training, and metadata for billing — duration, timestamp, model — is the only thing we keep. Transcripts are stored only if you opt in.

Read more on the trust page

Three steps

Hold. Speak.
Done.

01 · CAPTURE

Press the hotkey, anywhere.

Terminal, browser, IDE, Slack, Linear, your notes app, your git GUI.

CtrlShift;
02 · SPEAK

The commit message, the PR, the reply.

Talk normally. Filler words and false starts get cleaned up.

"Refactor the rate limiter so it short-circuits when the user is on the free tier…"
03 · RETURN

Text lands at your cursor.

0.4 seconds. Faster than you can switch tabs.

audio → transcript → ✓ pasted
Voca and /voice, side by side

Two halves of a
voice-first developer day.

Feature
Claude Code /voice
Voca
Works inside Claude Code CLI
Works in your terminal outside CLI
Works in your IDE
Works in your browser, Slack, GitHub
Hotkey
Spacebar (push-to-talk)
Configurable
Cost
Bundled with Claude Pro/Max/Team
$6/month
Runs on Linux

These aren't competitors. They're the two halves of a voice-first developer day. Also worth a look: Voca for Cursor, Voca vs Wispr Flow.

For teams

Built for teams
shipping with Claude Code.

If you've rolled out Claude Code to your engineering team, the next bottleneck is everything that happens outside the CLI session. Voca's team plan covers that for $6/seat/month with a credit pool for light users, per-member usage caps, and one invoice on the 1st.

See team pricing Individual pricing

Pair Voca with /voice today.

Free Voca tier gets you 30 minutes a month, no card. Plenty to test the loop on a real day of Claude Code work.

Try it in your browser
FAQ

Claude Code users,
the actual questions.

Do I still need Voca if I have /voice?

/voice works inside the Claude Code CLI only. Voca works in everything else on your machine, including your terminal, IDE, browser, Slack, and any text field. They complement each other.

Can I use Voca and /voice together?

Yes. They run independently and don't conflict. Most voice-first developer setups use both: /voice for prompting Claude Code, Voca for everything outside the CLI session.

Does Voca work with Claude Code on Linux?

Yes. Both Claude Code and Voca ship native Linux builds. Most other dictation tools don't ship for Linux at all. See dictation on Linux.

Will my Claude Code prompts be stored anywhere by Voca?

No. Audio is deleted as soon as transcription completes. We don't train models on your audio or your text. Transcripts are stored only if you opt in.

How fast is Voca for a tight prompt-edit-prompt loop?

0.4 seconds median latency from end-of-speech to text appearing at the cursor. Built on the fastest open inference stack we could put in production.

Do you have a free tier?

Yes. 30 minutes of transcription a month, no card required. Enough to test it on a real day's work before paying.

The other 80%
of your keyboard day.

$6/month flat or $0.10/hour pay-as-you-go. Same hotkey on Mac, Windows, and Linux.

Try it in your browser Create free account