One Tap Transcribe GitHub ↗

Talk. It types.

Push-to-talk dictation for macOS that runs entirely on your Mac. Hold a key, speak, release — transcribed on-device and inserted wherever your cursor is.

Download for macOS
Free & open source · macOS 26+ · Apple Silicon
Release notes, source & build-it-yourself on GitHub ↗

Fully on-device

No accounts, no API keys, no network at inference. Your voice never leaves the Mac.

Push-to-talk

Hold a modifier key, speak, release. Text pastes at your cursor in any app.

OpenAI Whisper, locally

WhisperKit (Core ML) or Apple's built-in on-device speech engine — your choice.

Optional AI cleanup

Tidy filler words and punctuation with Apple Foundation Models, Ollama, or MLX — with a fully editable prompt.

Live overlay

A floating waveform shows your words appearing as you speak, then “Transcribing…”.

Yours to change

MIT-licensed and open source. Build it, fork it, tweak every prompt and default.

Private by design

Everything — recording, transcription, and cleanup — happens on your Mac. There are no analytics and no servers. The only network use is a one-time model download, or a local LLM you run yourself.

Get started
  1. Download the .dmg and drag One Tap Transcribe to Applications.
  2. Launch it — a waveform icon appears in the menu bar.
  3. Grant Microphone and Accessibility when asked.
  4. Hold Right ⌘, speak, release. That's it.

Requires macOS 26 (Tahoe) or later on Apple Silicon. First dictation downloads the speech model (~600 MB), cached for next time.