Prototype first, then ask the team what breaks.
Spoken in 4 secondsYour voice,
already text.
Free dictation for Mac that runs entirely on your machine. Hold one shortcut, say the sentence, let go — the words land in the field you were already typing in.
Apple SiliconmacOS 14+Free, no account
Launch checklist
Landing copy is done. The icons need one more pass.
Three seconds from thought to text.
No window to open, no button to find. The app waits in the menu bar and answers to one shortcut.
Hold ⌃⌥Space
Put the cursor where you write. The shortcut is yours to change if this one is already taken, and you can switch to press-once mode instead of holding.
Say the sentence
Your Mac listens through the model you downloaded. Nothing is streamed to a server, because there is no server of ours to stream to.
Let go
The text is inserted at the cursor and stays on the clipboard as a backup. Enter is never pressed for you, so nothing gets sent by accident.
Wherever you already write.
Notes, mail, chats and prompts. The same shortcut everywhere, because the app types into the field you are in instead of asking you to switch apps.
Thanks for the draft — comments coming before Thursday.
Spoken in 5 secondsRunning ten minutes late, order me a coffee.
Spoken in 3 secondsDraft a launch plan from the notes I dictated this morning.
Spoken in 5 secondsIf a field cannot take the text — a password box, a protected input, an unusual editor — the result is already on your clipboard, waiting for one paste.
Your voice never leaves the Mac.
Speech is recognized on-device by the model you downloaded. There is no account to create, and no server of ours for audio to travel to.
- No account, no subscription, no limit on how much you dictate.
- The recording is temporary and removed once recognition ends.
- No transcript history: the text goes to your cursor and clipboard.
- After the one-time model download, dictation works with the network off.
Free · Works offline
Choose how your Mac hears you.
Download one model inside the app. It comes from Hugging Face once; after that you can dictate on a plane.
Parakeet TDT 0.6B v3
Fast everyday dictation with a short pause between letting go and seeing the text. 25 languages, English and Russian among them.
Whisper Large v3 Turbo
Wider multilingual coverage for people who switch languages often or dictate names and terms the faster model trips on.
Both run locally and can be switched in settings. Model weights are not bundled into the app, and their licences are listed inside it.
A few minutes, then just talk.
One download and two permissions stand between the DMG and your first dictated sentence.
Install the app
Open the DMG and drag Bocha Voice into Applications. Launch it from there.
Prepare your Mac
Pick Parakeet or Whisper and let it download. Allow the microphone, and Accessibility if you want the text inserted for you.
Say your first sentence
Choose a shortcut, put the cursor in any text field, hold it and speak. The app walks you through one practice round.
Fair questions.
What people ask before installing an app that listens to them.
Do I need the internet?
Twice: to download the app, and to download a model the first time. After that recognition happens on your Mac, and dictation keeps working with Wi-Fi off.
Which Macs are supported?
Apple Silicon — M1 and newer — on macOS 14 or later. There is no Intel, Windows or phone version. Keep about 630 MB free for the model.
Where can I dictate?
In the text fields of ordinary apps: notes, mail, chats, editors, AI prompt boxes. Automatic insertion needs the Accessibility permission and works while the field you started in is still focused.
If a field cannot take the text, the result waits on the clipboard for you to paste.
Why does macOS warn me when I open it?
This build is signed ad-hoc and has not been notarized by Apple, so Gatekeeper asks before the first launch. The standard way to allow it is System Settings → Privacy & Security, and only if you trust the source.
There are no scripts here that switch off macOS protections.
Is it really free?
Yes. No account, no subscription, no payment and no dictation limit. There is no cloud processing to bill for.
What language is the app in?
Dictation handles 25 languages, English included. The app’s own interface is in Russian at the moment; an English interface is in progress. This website is available in both.
Is my audio or text stored anywhere?
The recording exists only while recognition runs and is deleted afterwards; after a crash a temporary file may remain. The app keeps no transcript history and sends nothing to us. Your settings and downloaded models stay on your Mac.
Is the source available?
Bocha Voice is built on Pantela Voice, an open-source app under the MIT licence; that licence and the third-party notices ship inside it. Our own repository is not public yet.
Give your thoughts a voice.
Install it, pick a model, and dictate. Nothing to configure in the cloud, because there is no cloud.
Apple SiliconmacOS 14+Free, no account