The useful details.

Find your build.

Distributed alpha.3: the current private ZIP is 0.1.0-alpha.3. Its controls live in the menu. It needs macOS 26 or later and Apple Silicon.

Newer source builds: Settings groups controls into General, Writing, Appearance and Diagnostics. Per-app tone and the native Saved spellings editor are newer source features. The existing alpha.3 ZIP predates this window and these additions.

The sections below call out the differences. Source screenshots or instructions aren’t a promise that your alpha ZIP already contains them.

A key that suits you.

With the default Fn shortcut, hold to record and release to finish. Double-tap Fn or use Fn+Space for hands-free recording; tap Fn to stop. Esc cancels, with a five-second Undo offer.

Alpha.3: choose Change Dictation Shortcut… in the menu. Newer source: open Settings → General and change the shortcut there. Click the recorder, press your new key or combination, release all keys, then Save. Cancel keeps the previous choice.

Cleanup and tone do different jobs.

Level chooses how much processing happens. Off keeps recognition output. Basic uses local formatting rules. Fast adds the optional S1-mini model, roughly 1.4 GB. Thorough uses the optional Gemma model, roughly 5.2 GB. Model downloads need internet access; processing runs locally. When a cleanup model is unavailable or misses its deadline, Mouthtype uses Basic instead.

Tone controls capitalization and ending punctuation. Formal keeps sentence capitals and punctuation. Casual drops the ending full stop. Very Casual also relaxes sentence capitals while protecting names and technical spellings. Questions keep their question marks. Tone does not authorize paraphrasing.

Alpha.3: use the Cleanup menu for Level and Tone. Newer source: General contains Level; Writing contains Tone and per-app rules. Those rules start empty. The application where recording starts determines the tone for that take; other apps use the default. A browser rule applies to the browser, not individual websites.

Cleanup can use limited surrounding field text for boundary formatting and spelling hints, excluding secure fields. It doesn’t read previous messages as conversation history. Names and context can still be wrong, so read the result.

Keep the things you repeat.

Saved spellings, newer source builds: open Saved spellings from the Settings sidebar. “Heard as” is the word or phrase that comes back wrong; “Write as” is the spelling you want. Use specific phrases for ambiguous common words. These are exact whole-word or phrase rules, not a promise that every similar-sounding name will be corrected.

Phrase replacements: save a spoken trigger and the exact text it should insert. For example, “my work email” can expand to an address you choose. In alpha.3, open Cleanup → Phrase Replacements…; in newer source builds, use Phrases in the Settings sidebar.

The phrase library starts empty. Matching ignores capitalization and prefers the longest whole phrase. Replacements expand after cleanup so their wording and line breaks survive. {date} inserts the current long date; {clipboard} uses the text captured from the clipboard for that take. Cleanup Off also turns replacements off.

Save or cancel a draft before switching entries. If a file is unreadable or changes outside the editor, keep your draft and follow the repair guidance rather than overwriting the original.

If the text needs another way in.

Paste Last uses ⌃ ⌘ V by default. Copy Last uses ⌃ ⌘ C. These actions keep the latest saved transcript available after restart, unless a conflicting dictation shortcut takes precedence.

If a take didn’t land, inspect the target first. An app’s unknown delivery status is not proof that the field stayed empty. Use the recovery card’s Copy action when needed, and avoid pasting the same text twice.

Saved Recordings lets you recover retained interrupted or failed takes. Recovery doesn’t automatically paste into another app. Recovery pauses new recording until it finishes, and a failed recovery stays available to retry.

What stays on your Mac.

History, saved words and retained audio live in ~/Library/Application Support/Mouthtype. Text history is kept indefinitely. App preferences are saved separately by macOS. Audio cleanup runs at launch: files older than 90 days are removed, then the oldest remaining files until the archive fits within 2 GB.

Removing the app does not remove this data. Quit Mouthtype before removing the application. Delete the data folder only when you intend to erase the history and recordings inside it. Model downloads need a network connection; dictation doesn’t need a Mouthtype account.

When something needs attention.

Microphone access lets Mouthtype capture your voice. Accessibility access lets it insert the finished text. In System Settings → Privacy & Security, check both permissions for Mouthtype.

Alpha.3: the menu shows permission and model status and provides repair links. Newer source: open Settings → Diagnostics for status, model retry, shortcut health and the same repair actions. An attention message in the menu opens Diagnostics.

If nothing appears, confirm a text field is selected and the speech model is ready. Report the exact warning, Mouthtype version, macOS version, destination app, what you said and what appeared. Mention whether it appeared once, twice or not at all. Share only audio and text you choose to disclose.

Browser, terminal and Electron compatibility still need wider testing. A fresh install on another Mac and physical device changes remain part of alpha testing. Linux support is planned, with no released build yet.