Hold a key, say it badly, and the sentence you meant lands at your cursor.

So the app watches what happens to the text after it lands. When you replace a word it inserted with one that sounds like it, that is evidence it misheard, and your spelling becomes a candidate term. Recognition is biased toward it from then on.

Every term is listed with where it came from, and any of them can be edited or thrown out. Reject one and it is not proposed again.

When it does learn something a panel says so, on screen, at the moment it happens: the term, where it came from, and a countdown that runs in the open before it dismisses itself. Hovering it stops the clock, because reading a list should not be a race.

Nothing to opt out of

There is no telemetry, no account, no sync and no crash reporter. By default three things leave the Mac: your license, when the app opens and about once a day (the key goes to typingoptional.com for its paid-through date, and iCloud keeps one record of which subscription your Apple Account holds); a check for a new version; and the speech model, downloaded once on the first run. Everything else is off until you turn it on. Turn off Wi-Fi after that first run and dictation is unchanged, which is the only demonstration of a privacy claim worth anything.

Memory you can actually get back

Every capability that costs memory can be switched off on its own, and switching it off releases the memory rather than hiding the feature. Somebody under memory pressure drops a tier instead of dropping the app.

Screen context is off until you turn it on

There is an optional mode that glances at the screen to pick up unusual words. It is off by default. When it is on, a panel names each word it learned and counts itself down, captures are held in memory and never written to disk, and a password manager or an app you excluded is skipped.

There is a window when you want one: the dictations, the dictionary, everything it listens for, how much you have been dictating, and the settings. Most days there is a menu.

The gesture is yours to set. Out of the box a double tap of Left Shift starts dictation and a single tap finishes it, which lets you begin talking with nothing focused and put the cursor where the text should land while you are still speaking. The other mode is hold to talk, on ⌃⌥. Both are modifier keys held on their own, deliberately: a letter key held down auto-repeats into the very field you are dictating into.

⌃⌥V pastes the last transcript again, from anywhere.