Skip to content

voxtype — Local Voice Dictation

voxtype turns speech into text in whatever app has focus — your editor, browser, terminal, or a coding agent’s prompt box. Everything runs on your machine: no cloud, no accounts, no audio leaving your Mac.

One key to dictate

Hit the toggle hotkey (default Ctrl+;), speak as long as you like, hit it again — the whole take is transcribed with full sentence context and typed in one go (a single edit to undo, in most apps). No chopping at pauses, sub-second results.

Or go hands-free

Prefer no keys at all? Say “hey claude” (configurable, with alias spellings) to start dictating; say “stop listening” or go quiet to re-arm. The hotkey still works as an override.

Spoken submit

Say “go”, “over”, or “submit” as a standalone utterance and voxtype presses Enter — dictate a prompt to a coding agent and send it without touching the keyboard.

Clean transcripts

Standalone fillers (uh, um, …) are stripped and 3+ word stutters collapse (“I I I think” becomes “I think”) — on-device regex, no LLM involved.

Visible when it matters

A little glowing-blue ghost appears ONLY while recording — its mouth opens as you speak. Ghost on screen = mic live; no ghost = not listening.

Nothing is ever lost

Dictated into the wrong window? A paste-again hotkey re-types the last session’s transcript at the cursor; optional clipboard mirroring too. Escape cancels a recording outright.

  1. Install (the best engine for your machine is included automatically — see engines):

    Terminal window
    uv tool install voxtype
  2. Grant your terminal Microphone, Accessibility, and Input Monitoring permissions (System Settings → Privacy & Security) when prompted.

  3. Start dictating:

    Terminal window
    voxtype --segmentation hold

    Press Ctrl+;, speak (watch the ghost), press Ctrl+; again — the whole take types at your cursor. Esc cancels a take.

  4. Make it yours: run voxtype setup for an interactive walkthrough — it asks a handful of explained questions (engine, mode, hotkey, …) and writes your ~/.config/voxtype/config.toml. (Prefer editing by hand? voxtype init drops a fully commented sample instead.) After that, plain voxtype starts with your settings.

Everything above is a choice, not a default you’re stuck with: how dictation activates (hotkey, wake word, or always-on), how speech becomes text (whole-take vs. per-pause), which local engine runs it (Apple-GPU Parakeet, CPU Parakeet, or Moonshine), plus hotkeys, sounds, clipboard behavior, and more. The complete reference — every config key with its default, the engine comparison, and all CLI flags — lives in Configuration & CLI.

Prefer to have your agent do the install? voxtype skill installs a short guide skill into both Claude Code and Codex (each reads its own marketplace in this repo):

Terminal window
voxtype skill

It sets up whichever of the two agents is on your machine and skips the other. Afterwards, just ask your agent “help me install voxtype” (or “set up voice dictation”) and it walks you through uv tool install voxtypevoxtype setup → launch, including the macOS permission steps.

ActionDefaultConfigurable as
Toggle recordingCtrl+;hotkey
Cancel recording (discard)Esc (only while recording)cancel_hotkey
Re-type last transcriptoffpaste_hotkey
Submit (press Enter)say “go” / “over” / “submit”submit_phrases
Stop dictatingsay “stop listening”stop_phrase

Not sure how to spell a chord for the three hotkey settings above? Run voxtype hotkey, press the combo you want, and it prints the exact line to put in your config (e.g. hotkey = "<ctrl>+;").

Full reference: Configuration & CLI.