Questions, answered plainly.
About privacy, accuracy, languages, speed and licences. Something missing? The app shows a hint at every step.
Is my video uploaded anywhere?
No. Your browser opens the file, the AI models run in your browser's memory, and the transcript is saved to your downloads folder when you export it. There is no server component: we couldn't see your video if we wanted to. How to check it yourself.
Which languages does it read?
English, and Spanish in beta. Pick the spoken language in the app before reading: it's the language spoken in the video, and it's separate from the interface language (English, Spanish, German, French or Chinese). Spanish is a little less accurate than English for now.
How accurate is it?
On varied real-world English clips it gets about two words in three right; on a clear, front-facing studio speaker, about 85%. Spanish (beta) gets about 65% right. Results vary a lot with the footage, which is why every word carries a probability and you can see the other likely readings of each word and each line. Expect the gist rather than a verbatim transcript, and expect trouble with names, numbers and rare words. The full numbers.
Can it use the sound as well?
Yes: tick “Also listen to the sound” and a larger model (286 MB for English, 298 MB for Spanish) reads the lips and the voice together. That gets close to 9 words in 10 right, even in a crowd. The English model also keeps to the speaker when someone talks over them; the Spanish one may write that other voice down instead. For a clear voice with nobody else talking, an ordinary speech-to-text tool does as well.
What do the colours and percentages mean?
Each word's percentage is its chance of being right, estimated from what the model saw around that word. White words are likely (80%+), amber ones unsure, and underlined coral ones doubtful (under 50%). Line readings show how the probability is shared among the readings the decoder kept. On our test set, words shown at 80–100% were right about 93% of the time.
What videos work best?
One person facing the camera, face reasonably large, good light, 25–30 fps. MP4, MOV and WebM all work in recent browsers. Several people in the shot are fine — you pick whose lips to read.
Why is the first run slower?
The first time you read a language, your browser downloads its lip-reading model (English 264 MB, Spanish 169 MB; lips + sound: English 286 MB, Spanish 298 MB) and keeps it in its cache. After that it starts right away, even offline. On a laptop CPU, reading runs about 1.6× faster than real time — a one-minute clip takes about 40 seconds; phones and older computers take several times longer.
Is it free? Can I use it at work?
It's free. The open lip-reading models it uses are licensed for research and non-commercial use only, so LipScribe is too: personal, educational and research use are fine; commercial use would need models trained on rights-cleared video (credits & licences). If LipScribe helped you, there’s a pay-what-you-want donation jar.