How to let an assistant control your Mac with your voice

Jude Mercer, SEO and Content, Memoe — 19 October 2026

Hold one key from any app, say what you need — "open the invoice I was sent yesterday and forward it to Dan" — and let go. Moe works the app itself: it opens the file, finds the right menu item, clicks what it needs to click. You don't learn a command syntax and you don't say an app's name first; you say what you want in one ordinary sentence, the way you'd ask a person.

What "controlling your Mac" actually means here

Moe can see your screen and use your Mac — open an app, click a button, fill a field — through the same accessibility machinery a screen reader uses. Clicks are delivered straight to the target window in the background, so your cursor doesn't move, your keyboard focus doesn't change, and you can keep typing in whatever you were doing while Moe works in another window.

It tries the screen last, not first

Driving a window by clicking is the last resort, not the first thing Moe reaches for. Asked to open a meeting link, Moe reads the join address off the calendar event and opens it directly — no screenshot, no clicking, nothing that can miss. The order it works through is: the data it already has, then the app's own scripting, then a menu item or a keyboard shortcut, then its own browser for anything on the web, and only then a click.

It reads menus, not just pixels

Ask Moe to do something in an app and it can read that app's menu bar directly, the items and their shortcuts, and invoke the one it needs by name rather than hunting for it on screen. That's faster and more reliable than clicking, and if the item doesn't exist Moe is told so plainly rather than guessing. It also works where looking at the screen doesn't: music software, CAD, 3D tools and games draw their main window as one canvas Moe can't read, but their menus are ordinary. An item that's greyed out is reported as greyed out — the difference between "not available right now" and "does not exist".

For anything on the web, its own browser

When the job is a web page — look something up, fill a form, work through a site — Moe drives a browser of its own rather than yours. It reads the page as text, so it knows what the buttons and fields actually are instead of guessing from a picture. Nothing appears on your screen while it happens, nothing takes focus, and your own tabs are untouched. Full detail on signing in, passwords and "are you human?" checks is in the docs, Driving your Mac.

Stopping it is something you do

Double-tap the talk key and Moe stops, whatever it is doing. Stop beside the notch does the same while it is working your screen: no further click or keystroke is sent, and whatever Moe was part way through is abandoned rather than finished behind your back. It does not try to guess that you have taken over: it cannot tell your hand on the mouse from its own typing, so stopping is always yours to do.

What it needs

Hold one key from any app, say it, and Moe answers — see using Moe from any app for the four ways to start a turn. Nothing it does outside your Mac goes out without a separate approval step first; see the approval step for what that covers. This page describes the mechanism, not a version number.