Be heard without your voice.
Mouth the words you would have said. Unspokn carries them the rest of the way — as text on screen, or as speech other people can hear.
Silent speech interface · iPhone & Mac · Beta
Unspokn translates silent lip movements into text or natural-sounding speech — so you can be heard without using your voice. On iPhone, and now on your Mac.
Speech disabilities. Temporary voice loss. Environments where speaking aloud isn't possible or desirable.
Existing speech-to-text tools require audible speech. Many assistive alternatives rely on typing, selecting predefined phrases, or specialized hardware — slow, conspicuous, and often unusable in an everyday conversation.
Confirmed words are spoken in a natural voice. Tap a phrase to hear it out loud.
The kind of phrases people save in the app for one-tap use. Lip reading happens in Unspokn on your iPhone or Mac — not on this page.
Tap a phrase to hear it
Separate, explicit permissions. Both states stay visible on screen, so you always know what's listening — and that nothing is.
Mouth a short phrase while facing the camera. Unspokn can start and stop on its own when your lips move, or you can press a button when you'd rather be deliberate.
Unspokn reads your lip movements and suggests the words. You can edit them before or after they're spoken, or turn off automatic speaking to review every message first.
A natural voice speaks the confirmed text — or it stays as text you can display, share, or send.
Lip reading is a best guess, so Unspokn keeps you in charge of what gets said.
Every reading appears as text on your screen, so you always know what Unspokn heard.
Wrong word? Edit it or say it again. Playback stops the moment you tap.
Automatic speaking is on by default. Turn it off and nothing is said until you tap Speak.
Unspokn for Mac lives in your menu bar. Hold a shortcut and talk, or switch to Silent and just mouth the words to your camera. Let go, and your text appears in whatever app you're using.
Speak, let go, done. Or tap once to go hands-free, and tap again when you're finished.
Silent keeps the microphone off and reads your lips through the camera. Lip reading on Mac is in beta.
Mail, chat, docs, the browser. Spoken punctuation and filler words are tidied up before your words arrive.
The camera and microphone switch on only while you dictate, and the overlay shows which one is live. Speech recognition runs on your Mac by default, so your audio stays there unless you allow cloud speech. Your history stays on your Mac too.
Builds installed from TestFlight or the Mac App Store copy your text instead of typing it — press ⌘V to paste.
Mouth the words you would have said. Unspokn carries them the rest of the way — as text on screen, or as speech other people can hear.
Every transcript is editable, and you can stop playback at any time. Turn off automatic speaking to review each message before it's said.
A camera you already own. On your iPhone and your Mac, so it's wherever the conversation is.
The microphone stays off in silent mode. Processing stays on-device where feasible, remote processing is disclosed, and raw video isn't retained by default. Your history stays on your device.
Another way to express yourself
— without requiring you to speak aloud.
Motor-speech conditions, ALS, apraxia, dysarthria, and other conditions that make reliable audible speech difficult.
Surgery and recovery, laryngitis, vocal strain — the weeks when your voice isn't available to you.
A quiet carriage. A shared office. A room where someone is sleeping. A factory floor too loud to be heard in anyway.
This is an accessibility product in development. Overstating it would cost the people who need it most.
Many sounds look identical on the mouth. Open-vocabulary silent speech is not dependable for every user or every phrase.
Published visual-only error rates come from research datasets recorded under good conditions. They are not a promise about your room.
Face angle, lighting, occlusion, frame rate, camera quality, accent and individual articulation all move results, sometimes a lot.
Models trained on typical speech can perform poorly for people with atypical articulation or limited mouth movement — exactly the people we most want to serve. We're testing with intended users, not around them.
Free during beta · paid plans launch soon. Everyone gets Plus limits while Unspokn is in beta. These are the plans we'll offer at launch, and we'll tell you before anything changes.
$0, no account needed.
Typing, saved phrases and Show mode, unlimited. Speak with your device's voice as much as you like. 20 lip reads a day, a taste of our natural voices, 10 translations a day and 3 share clips a month.
$9.99 a month or $79.99 a year. Try it free for 7 days.
Unlimited lip reading, natural voices all day, translation into 8 languages, 100 share clips a month, and your phrases on iPhone and the web.
$129.99 a year for up to 6 people.
Everything in Plus for each person, with their own limits. Nothing one person says or types is shared with the others.
$59.99 per seat a year, minimum 5 seats, invoiced.
Ask us about a pilot. Can't afford Plus? Ask us about free Access. Nobody should lose their voice over money.
Same plans and prices on iPhone and the web. Cancel any time. Prices in US dollars; local prices shown at checkout.
Only when you ask it to. The iPhone app never uses the microphone. On Mac, voice dictation turns the microphone on only while you dictate, and Silent keeps it off. The overlay shows you which one is live. Camera and microphone are separate permissions you control independently.
No. A standard camera on a phone or laptop. Unspokn is in beta on iPhone and Mac.
Only to be read. The live camera preview and face tracking stay on your device. To read your lips, short silent clips go to our server and are deleted as soon as they've been read. They're never kept and never used for training. Saved recordings, if you turn them on, stay on your device. The Privacy Policy has the details.
Unspokn is in a private beta on iPhone and Mac. Join the waitlist, tell us which device you use, and we'll invite people in small groups as we're ready for them.
Yes, in private beta. It lives in your menu bar: hold a shortcut to dictate into any app by voice, or switch to Silent and mouth the words to your camera, with the microphone off. It needs macOS 15 or later.
English first. A few other languages are in early beta and are much less accurate. Each language needs its own evaluation before we'd claim it works.
Yes. Typing, saved phrases and speaking with your device's voice will always be free. Everything is free during the beta; when paid plans launch, Plus pays for the expensive parts: lip reading at scale, natural voices and translation. Same prices on iPhone and the web, and free Access for anyone who can't afford it.
Then you still need to communicate, so Unspokn keeps a no-camera path: typing, saved phrases, and one-tap responses. The camera is an option, not a requirement.
We're building Unspokn with privacy, accessibility and user control at its core. Join the beta on iPhone or Mac — we're letting people in a few at a time.
We'll email you a link to confirm. Every email has a one-click link to remove yourself.