Tappy

Overview

A native macOS assistant that turns speech into action on the Mac in front of you. Hold two keys, say what you want in ordinary words, and let go: apps open, windows arrange themselves, notes get written, selected text comes back rewritten. The panel grows out of the notch while you hold and shrinks back into it when it is done. Typical command: under a second.

The problem

A Mac user's day is full of small mechanical tasks that break concentration without being difficult: finding the right window among fifteen and dragging it to half the screen, opening the four apps a piece of work needs one at a time, copying a paragraph somewhere to be reworded and pasting it back. None of these are hard. They are just constant, and the interruption outlasts the task. macOS already has Voice Control and Siri, but Voice Control is an accessibility tool built around describing the screen, and Siri has no spoken command for moving a window. The gap is an assistant that operates the machine rather than talking about it.

Use case / workflow

1. 1

   Hold two keys: Control and Option, from anywhere. No window to find and no click. The panel grows out of the notch while you hold, or drops out of the menu bar on a Mac without one.

2. 2

   Say it normally: not commands, just words. "Chuck some music on" and "play something" land in the same place, because it matches meaning rather than phrasing. There is no syntax to memorise.

3. 3

   Let go: it happens, usually before you have finished thinking about it. Every action reports what ran and how long it took, rather than leaving you to guess whether it worked.

Key features

• 21 capabilities in the words you would actually use: open or quit an app, quit what you are in, close or hide everything, fullscreen, maximise, minimise, and snap a window to a half or a corner.

• "Open Spotify in fullscreen and put Chrome on the left half" is two instructions in one breath: it splits them, runs them in order, and waits for each app to actually be there before touching its window.

• Rewrite selected text in place, in any app. Select text anywhere, say how you want it, and it comes back changed where it was. Say "format this" and it picks the structure itself: numbered for steps, bullets for parallel points, headings when there are several topics.

• Routines: a sequence you define once and trigger by speaking. You describe the moment rather than the words, so "focus block", "going heads down" and "let me concentrate" all reach the same one. Thirteen kinds of step, including running any macOS Shortcut you already have.

• "Undo that": anything Tappy did, it can put back. Quitting every app is recoverable with two words, and anything with unsaved work asks first.

• An optional wake word, off by default, because leaving a microphone open should be a decision rather than a surprise.

• One model call decides four things at once: whether the speech was even addressed to the computer, whether it is one action or several, which capability handles it, and how hard it would be to undo. Asking separately would mean four round trips per command.

• Extraction is skipped 74% of the time. "Quit Spotify" needs no second model call to work out what "Spotify" is, so only commands that genuinely need language understanding pay for one.

• Native macOS APIs rather than scripted UI clicks: quitting an app takes 16 ms and fullscreening a window 257 ms.

• The app ships no API key. Requests go through a proxy that meters usage per user, so credit can be granted and revoked without shipping a new build, and nothing extractable from the binary is worth stealing.

• Your voice never leaves the Mac: speech is transcribed on-device, no audio is uploaded or saved. Only the command text and the name of the app you are in leave, which is what lets "put this on the left half" mean anything. No account, no tracking, no analytics.

• Eleven notch themes, drawn to match the notch they come out of, with the timing and easing of native macOS animation.

Tech used

Outcomes

• Median command 1,285 ms end to end, with the fastest quarter under 630 ms, measured over 184 real commands on a MacBook Air rather than estimated.

• 136 of those 184 commands needed no second model call, finishing in a median of 792 ms.

• Quitting an app 508 ms, minimising a window 674 ms, fullscreening 754 ms, opening an app 1,040 ms.

• A 3.2 MB universal binary on macOS 13 and later, live in limited early access.