Voice to text in Bear

Does Bear have built-in dictation?

No. The Bear Mac app has no built-in speech-to-text, dictation, or voice-typing feature for writing into a note by voice. There's no microphone button in the editor, no voice command, no hidden preference. If you've been combing the menus for it, you can stop. It isn't there, and Bear's whole design leans the other way — it's a clean markdown editor, not a recorder.

The voice features Bear does have all live on the Apple side, not in the Mac editor. On iPhone and iPad you can ask Siri to make a note, and there's an Apple Watch shortcut that opens Bear straight into a speech-to-text note. Those are real, and they're useful on a phone or a watch. But they're not a Mac dictation button, and they aren't live "talk into the note I'm editing right now" on the desktop. People find the Watch feature in a help article, assume the Mac has the same thing, and lose an afternoon looking for a button that was never built into the Mac app.

Worth one sentence so you don't chase it on the wrong device: on an iPhone, the keyboard's own microphone already dictates into Bear, the same as into any app, so the mobile case is handled by the phone. On the Mac that most Bear writing actually happens on, you need a tool that sits on top of Bear. There are really two honest categories, and the rest of this guide covers them.

Hold a hotkey, talk, text lands in the note

This is the whole mechanic, and it's boring in the best way. You hold a hotkey, you speak, you release, and the transcript pastes at your cursor, in whatever text field has focus. Whisper keeps a short tail after you let go of the key, so your last word doesn't get clipped. Because it pastes at the macOS cursor, a Bear note is just "any text box." The desktop app, a markdown line, a search field — same behaviour.

That's the part the landing pages overcomplicate. There's nothing to install into Bear, no extension, no API token to paste, no sync job to babysit. Your cursor is in a note, you talk, the words appear in the note. A small capsule shows up while you speak so you know it's listening:

The hotkey is the one thing worth getting right up front. On a Mac it's Command+Option — a modifier-only push-to-talk you hold while speaking and release to stop. (On Windows the same tool uses Ctrl+Space, which matters only if you also dictate into other apps on a PC; Bear itself doesn't run on Windows.) It's changeable in Settings if it clashes with something you already use. My younger daughter once told me a hotkey "didn't work" in her drawing app. It was a conflict, not a bug — which is how I learned the average person has no idea what a hotkey conflict even is. So now every hotkey is customisable. If you've ever set up dictation on a Mac, this is the same muscle memory pointed at a different app.

Set it up on your Mac in two minutes

You need a Mac on Apple Silicon, a working microphone, and Bear open in the desktop app. The whole local pipeline is free for any signed-in account, with no payment method asked for at sign-up. Here's the sequence.

The slow part is the model download, not the setup. Everything else is the four steps above. Once it's running, dropping a thought into a Bear note stops being a typing task and starts being a talking task.

voice to text on a Mac

Voice gets the words, Bear's markdown gets the structure

Bear's whole appeal is its markdown shortcuts — a #tag to file a note, # for a heading, - for a list, the slash menu for the rest. The honest division of labour is simple: voice gets you the words, and Bear's own syntax gets you the structure. Dictate the sentence, then type the # for a heading or the - for a bullet the way you always do. No dictation tool conjures Bear's tag-and-heading syntax into existence on command. Anyone promising "say tag project alpha and watch it file itself" is selling you a demo, not a Tuesday.

In practice this is faster than it sounds, because the typing you keep is the cheap typing. A # is one character; a paragraph is a hundred. You speak the hundred-character part and tap the one-character part. Hold the hotkey, talk out the body of the note, release, then add the #tag and the heading marks by hand. The slow part of writing was never the markdown symbols. It was the prose between them, and that's exactly the part you've just handed off to your voice.

This is also why a system-wide hotkey beats anything bolted into a single app. The same key that fills a Bear note fills your Mail compose box, a Slack message, and a commit message. One tool, every text field on the Mac. You don't relearn anything when you switch from Bear to your email, and Bear stays the tidy markdown editor it was built to be instead of growing a recorder it never wanted.

Local or cloud: which mode for private notes

For Bear, try local mode first. A lot of what lands in a notes app is the kind of thing you'd never want on someone's server — a half-formed idea, a meeting recap, a journal line. It would be a strange choice to route your voice through a cloud just to get a sentence into a note on your own Mac. If your Mac is Apple Silicon — and on a Mac that runs Bear, it very likely is — local handles everyday dictation without complaint, and cloud becomes the escape hatch rather than the default.

Here's how the three paths differ, because the app makes you pick and I'd rather you pick well:

• Local Parakeet — NVIDIA's TDT engine, around 600 MB, and the fastest local option — 5 to 10 times faster than Whisper on CPU. Covers English plus 24 other European languages, 25 in total. No translate-to-English. If you write notes in English or another European language, this is the quick, fully offline pick.
• Local Whisper — slower than Parakeet on the same machine, but the multilingual builds cover 99 languages and can translate to English. The English-only builds are English-only, not 99. Pick this for Chinese, Japanese, Korean, or any translation work, which Parakeet can't do. The default English model is around 480 MB.
• Cloud (OpenAI, BYOK) — best accuracy and web access, using your own OpenAI key billed straight by OpenAI. Transcription runs on gpt-4o-mini-transcribe by default. Needs internet, so it's the one path that leaves your machine. The Cloud surface is part of Whisper Pro.

The boring truth is that for the kind of text most people put in Bear, local is plenty. Both local engines run fully on your Mac with nothing sent to a server, pure-Rust under the hood, no Python sidecar. Cloud earns its place when you want top-tier accuracy on a hard recording or you need the model to pull a fact off the web mid-sentence. For a daily note-taking habit, start local and only reach for cloud when local leaves you wanting.

Punctuation and cleanup, before it lands in the note

Raw dictation comes out as a run-on. You say "okay so draft the launch note tag it product and remind me to send it Thursday," and that's the unpunctuated wall any speech engine hands you. Cleaning it up is where the paths diverge.

macOS Dictation handles basic punctuation when you say "comma" or "period" out loud, and it adds some automatically. For heavier cleanup — stripping the "ums," fixing the run-ons, turning a spoken paragraph into something you'd actually keep in a note — Whisper can run an AI pass. Say the activation phrase "Hey whisper" and the text gets enhanced before it lands. On a local model that runs through Ollama, free, on your own machine; in cloud mode it's gpt-5-mini by default.

Notice what the cleanup does and doesn't touch. It fixes the punctuation and trims the filler, but it leaves the #tag to you — it writes "tag it Product," not the literal #product Bear needs. That's the right division again: the AI pass gives you a clean sentence, and you add Bear's markdown the way you always do. For a note you'll reread next week, a clean sentence beats a verbatim transcript every time, and it's the one thing the built-in dictation won't do for you.

That same speak-then-clean flow pays off well beyond your notes — you can also dictate clean prose into any app with the one hotkey, so a long note becomes a few spoken sentences instead of a paragraph you type out.

When to skip a dictation tool for Bear

Sometimes the right tool is the free one already on your Mac, and pretending otherwise would be dishonest. If you only drop short captures into Bear — a quick line, a two-word reminder — macOS covers it for nothing.

Open System Settings, go to Keyboard, and switch on Dictation. The first time, your Mac downloads a small speech model, which is what lets it run on-device afterward. After that you click into a Bear note, press your dictation shortcut or the microphone key, and talk — the words appear as you speak, anywhere you can type. On Apple Silicon, general text is processed on-device, so a quick note doesn't leave the laptop. It punctuates reasonably and is genuinely fine for short bursts. For a one-line reminder, that's the answer, and I'm not going to tell you to install an app for it.

Reach for a dedicated, system-wide tool when the built-in starts hurting: long notes, multilingual work, technical vocabulary the built-in keeps guessing at, an AI cleanup pass, or wanting one hotkey that behaves the same in Bear, your email, and your editor. Below that bar, use what's free. The line I draw, roughly, is the second paragraph: anything you'd reread or paste somewhere is worth the cleaner transcript; a grocery list isn't.

The same trade-off shows up if you also keep notes elsewhere — the logic in dictating into Apple Notes is identical, because both lean on macOS for the voice and on the app for the structure.

Bear never shipped a dictation button on the Mac, and after writing this I'm fairly sure it never will. It doesn't need to, because on a Mac the cursor is the integration. Talk into the note, get text, shape it with the markdown you already know. I dictated most of this guide into a text box that wasn't Bear, with a tool that doesn't care which box it is, then pasted the lot into a note and added the headings by hand. That's the whole trick.