Private, on-device dictation for macOS, and now Windows in early beta. Hold one key, yap, release. Your words at your cursor, in any app, and your voice never leaves the machine.
the invoices are draggable. the prices are not.illustrative of common dictation app pricing as of july 2026. exact numbers vary by vendor and change often; the zero does not. much of that transcription happens in a data center. yours happens in the metal you already paid for.
bars float above your dock and dance with your voice. release, they fade. no window, no chrome.
cleanup prompts you can read and edit. styles per app. your names spelled right. zero setup by default.
history shows raw and cleaned side by side. if the AI ever changes your meaning, you'll see it. raw words win on doubt.
Double-tap the globe key to talk without holding. Say "send it" and the message fires with zero keypresses.
Select text, hold the key, say "make this more formal". Rewritten in place, or left alone if the model fumbles.
Audio streams into the recognizer while you talk. Text lands the moment you release, first word included.
Apple's on-device model cleans your transcript out of the box. Ollama and custom endpoints for the tinkerers.
Dictating to Claude or ChatGPT stays terse and keeps file paths, flags, and identifiers exactly as spoken.
Transcribe whatever your Mac is playing: lectures, podcasts, the other side of a call. Live, on-device, saved to a file when you stop.
Drop an audio or video file on the menu bar icon and get the transcript many times faster than real time.
Correct yourself mid-sentence and only the final version survives. Like the demo above, which was one take.
Build from source (zero Gatekeeper friction) or grab the zip from releases.
The setup assistant walks you through mic, input monitoring, and accessibility with live checkmarks.
That's it. That's the manual. There is no step four.
A dictation app hears everything. That's why this one can't phone home.
complete list of network connections: localhost (your Ollama, if you use it) + the GitHub API, only when you click Check for Updates. the windows beta also downloads its speech model from Hugging Face, once. read the source and verify.
macOS 26 on Apple Silicon, or 64-bit Windows 10/11 for the beta. On the Mac, cleanup works out of the box with Apple's on-device model; Ollama and OpenAI-compatible endpoints are there for tinkerers. Without any of them, yapping pastes accurate raw transcripts.
Releases are not notarized; that requires paying Apple $99 a year, and this app costs $0 forever. Allow it once under System Settings, Privacy & Security, or skip the warning entirely by building from source. The code is public; read it first if you like.
It's a fresh beta, rebuilt in Rust around the same idea. Hold Ctrl+Win, speak, release; the raw transcript pastes at your cursor. Transcription runs fully on-device (the speech model downloads once on first run, about 640 MB). The recording overlay, cleanup, per-app styles, and history from the Mac app are on the way. The installer isn't code-signed yet, so SmartScreen will warn once: choose More info, then Run anyway, or read the source first.
Audio is never written to disk; it streams from the mic straight into the on-device recognizer. Your last 20 dictations are kept in a local history file so you can inspect what cleanup changed, and you can clear it any time.
Anywhere you can type: browsers, editors, chat apps, terminals. Terminals and code editors get verbatim mode by default so cleanup never touches your commands.
It sits in the corner doing almost nothing, your thumb already knows where it is, and holding it feels like a walkie-talkie. Set "Press globe key to: Do Nothing" in System Settings and yapping takes it from there. Or double-tap it and go hands-free. On Windows the chord is Ctrl+Win: same walkie-talkie, different corner.
One download, one permission screen. Then just hold the key.
macOS 26 on Apple Silicon · 64-bit Windows 10/11, early beta