Set the default in Dictation Settings → Style → Default cleanup level, and override it per app in App profiles.
Verbatim
Exact transcript, with punctuation from the speech engine only. For quotes, legal work, and anyone who'd rather not have an AI touch their words at all. Filler words stay in. List detection is off.
Light — the default
Removes filler words and false starts
Fixes punctuation and capitalization
Applies self-corrections — "Wednesday, actually Tuesday" becomes "Tuesday"
Collapses stutters and repeated words
Formats numbers, dates, emails, and URLs sensibly
Never reorders your ideas, substitutes your vocabulary, or changes your register.
Standard
Everything in Light, plus:
Sentence-boundary repair for rambling speech
Paragraph breaks in long dictations
Per-app writing style (casual / formal / excited) if you've set one
Standard runs an on-device model in the background after the instant insert, then offers a refined version — so you're never waiting on it.
Still forbidden at every level: paraphrasing, changing your tone beyond a style you explicitly chose, and adding content you didn't say.
Spoken formatting
At all levels, spoken commands are honored: "new line", "new paragraph", "bullet point" / "next bullet", "quote … end quote". When it's ambiguous, Amlin favors the literal text.
Automatic lists
At Light and Standard, clear enumerations become lists. Amlin is deliberately conservative: two items never become a list, and parallel adjectives inside a sentence stay inline. A wrong bulleting is worse than a missed one.