Voice to text in Apple Notes

Does Apple Notes have voice-to-text?

Not on its own. There's no microphone button inside Apple Notes that turns your speech into typed text. What you're looking for is a system feature called Apple Dictation, and it's built into macOS itself. Because it works anywhere you can type, it works inside a note without Notes needing to know anything about it.

This catches people out because they expect the button to be in the app. It isn't, and that's by design. Apple Dictation is one tool that types into Mail, Messages, Pages, your browser's search bar, and Notes, all the same way. One feature, every text field. So the answer to "does Apple Notes have voice-to-text" is: no, but your Mac does, and it reaches into Notes just fine.

A quick note on hardware, since the search hides it. This is a Mac story. Whisper runs on Windows and on Macs with Apple silicon, not on iPhone or iPad, so everything below assumes you're on a Mac at a desk, not dictating into Notes on a phone.

Apple Dictation: the free built-in option

Turning it on takes about a minute. Open System Settings, go to Keyboard, find Dictation, and switch it on. The first time, macOS asks to download a speech model, which is what lets it run on-device later. You can pick a keyboard shortcut to start dictation, or use the dedicated microphone key if your Mac has one. After that, click into any note, trigger dictation, and start talking. The words appear as you speak.

The honest part: for casual notes, Apple Dictation is good. It handles everyday sentences well, it adds punctuation automatically in supported languages, you can say "new line" or "comma" out loud, and it covers more than 40 regional language variants. On a recent Mac it processes your voice on-device, so your dictated grocery list or reminder doesn't leave the laptop. For a quick thought dropped into a note, it does the job and costs nothing.

Where a dictation app does more

So why would anyone add a separate app? Three reasons, and they're specific. First, accuracy on the hard words. Names, product names, acronyms, code, medical or legal terms, the things built-in dictation tends to guess at. A Whisper-based model gets more of those right, and Whisper's local mode lets you add custom vocabulary so it learns the words you actually use. Second, cleanup. Spoken language is full of "um," half-restarted sentences, and trailing-off. Whisper has an optional AI step that trims the filler and tidies the phrasing before the text lands in your note.

Third, choice. Apple Dictation is one engine. With Whisper you pick your path: local Whisper models, whose multilingual variants cover 99 languages and whose English-only builds cover exactly one; NVIDIA's Parakeet, about 600 MB and 5 to 10 times faster than Whisper on CPU, covering English plus 24 European languages; or, on Pro, OpenAI's cloud models. None of that is necessary for a shopping list. It starts to matter when the note is long, the vocabulary is specialized, or you want the transcript clean enough to paste somewhere serious.

The fastest way: a system-wide hotkey

Here's where a dedicated app changes the feel of it. Whisper by Remskill is a desktop app that works like a keyboard: press a hotkey, speak, release, and the transcript is pasted at your cursor, in any app, the Apple Notes window included. There's no button to find inside Notes and no separate window to copy text out of. You're in the note, you hold a key, you talk, the words appear where you were already typing.

Setup is short:

That's the whole loop. A second or so after you let go, the transcript is sitting in the note, ready for you to keep going or to format.

Speak, and the note fills in

Once it's running, the experience is unremarkable in the best way. You put your cursor in the note, hold the key, talk, let go. About a second later the text is there as if you'd typed it. No copy-paste dance, no fishing the words out of a dictation window, no second-guessing whether you triggered the right shortcut. The note just fills in.

Because Whisper's local transcription runs on your machine, pure-Rust, no Python sidecar, no server in the loop, it works offline. On a Mac without a network connection, you can still dictate a full note. Apple Dictation runs on-device too on recent Macs, so both keep your casual notes local; the difference is what each does with the longer, harder ones.

What the full Whisper app looks like

The hotkey is the part you'll use most, but there's a settings surface behind it. You pick your transcription engine: Whisper models, with multilingual variants covering 99 languages and English-only .en builds covering one, or NVIDIA's Parakeet, about 600 MB and 5 to 10 times faster than Whisper on CPU, covering English plus 24 European languages. You set your hotkey, manage a history of past transcriptions, and save presets. None of it is required to dictate one note. It's there when you want to tune.

Cleaning up dictated notes with AI

Spoken notes are messy in a way written ones aren't. You start a sentence, abandon it, say "um," circle back. Whisper has an optional AI enhancement step that trims that filler and tidies the phrasing before it pastes. So "uh, yeah, so for the meeting, the, the main thing is we need to, to ship the thing by Friday" becomes "For the meeting, the main thing is we need to ship by Friday." For a note you'll actually reread later, that's the difference between a transcript and a usable sentence.

That cleanup runs locally through Ollama, free, on your own machine. Pro users can route it through the cloud instead, but the filler-cleanup benefit doesn't require Pro; it's there in the free local pipeline. You can also turn it off and paste the raw transcript, which for a quick scratch note is often exactly right. Apple Dictation gives you the raw spoken words; the cleanup pass is the thing it doesn't do.

When to just use Apple Dictation

Let me be straight, because the honest guides skip this part. If you mostly drop short, casual notes into Apple Notes, don't install anything. Apple Dictation is free, it's already on your Mac, it runs on-device, and for a one-line reminder or a quick idea it works fine. Press the mic key, say it, done. Paying for or installing a separate tool to capture "buy milk, call the dentist" is solving a problem you don't have.

Where a dedicated app pulls ahead is the longer and more demanding notes: the meeting summary, the research note full of names and jargon, the draft you'll paste into a doc, the note you want clean rather than verbatim. That's where the better accuracy on hard words, the custom vocabulary, and the AI cleanup start to matter. Built-in dictation gives you the spoken words; Whisper gives you the spoken words, sharpened.

Pick the smallest tool that solves your problem. For a quick note, that's the dictation your Mac already ships with. For the long, technical, paste-it-somewhere notes you write all day, the dedicated app stops feeling like overkill around the second paragraph you didn't have to clean up by hand.

What Whisper costs

The local dictation pipeline, transcription and the AI cleanup over Ollama, is free for any signed-in user, with no card at signup. So getting your voice into Apple Notes with Whisper costs nothing. Whisper Pro adds the cloud features (OpenAI transcription, cloud AI enhancement, voice web search), and it carries a separate trial. The exact numbers live on the pricing page rather than here, because prices move and a blog post is a bad place to keep them current.

Apple Notes will probably never grow a dictation button of its own, because it doesn't need one: macOS already hands you the feature everywhere. So the real question was never "does Notes do this." It was "how good do I need the result to be." For a quick note, your Mac's built-in dictation is the answer. For the notes you reread, share, and care about, an app exists for exactly that. Pick the smaller one until it stops being enough.