Chrome extension · Open beta · Free
EyeStill shows speech one word at a time, right at the speaker's lips — so you read the subtitles and see the face in the same glance. AI answers are read through the same point of focus, right under the message. Your eyes stay where they are; the words come to them.
Captions sit at the bottom of the frame; the person — expression, lips, emphasis — is in the middle. Your eyes shuttle between the two several times a sentence and lose a little of both each trip. AI answers have the opposite problem: five paragraphs land at once, and you skim for the point while the details you came for slide past.
EyeStill finds the speaker and puts the subtitle line just above their lips, a word at a time, as it is spoken. When two people talk, it follows whoever is speaking; when the shot cuts, it moves with it.
YouTube · word-timed captions · translation
ChatGPT, Claude, Gemini, DeepSeek. A button under each answer reads it to you right there, word by word at one point of focus — no scrolling, no hunting for the paragraph you were on.
Alt + Q in any conversation
More about ai answers →Open an EPUB, FB2 or TXT in the EyeStill reader, in any browser. Your library and your place are kept in the browser. A 90,000-word novel becomes a few evenings instead of a few months.
EPUB · FB2 · TXT · pasted text
More about books →Placing a word at someone's lips sounds simple. Doing it on any video, through cuts, gestures and two-person shots, in the speaker's rhythm and in your language, takes a few models working together — most of them right in your browser.
Two on-device models check the video every second: a face detector for close-ups and a body-pose model that still finds people turned to each other in a wide two-shot.
With two people in the shot, EyeStill compares how much each mouth moves against the rest of the head. A nod is not speech; a sentence is. The line moves to the speaker and ignores the listener's “uh-huh”.
A scene change is caught from the frame itself, so the line jumps to the new face at once — while hands, gestures and head turns within a shot don't shake it.
Captions arrive with a timestamp per word, so each one appears the moment it is said — no lag, no repeats from YouTube's rolling caption lines. Where Chrome's on-device AI is available, it restores missing punctuation.
A language model translates the full transcript ahead of playback — consistent terms, natural phrasing, filler words like “you know” left out — and each line still lands at its original's time.
Word-frequency data for the 30,000 most common words of Russian and English give rare words a beat longer and common ones less — the same effect eye-tracking studies see in natural reading.
Reading a page is a sequence of small leaps — about four a second — each landing on a new cluster of letters, each a chance to drift, re-read or lose the line. A good part of reading time goes into moving the eye rather than understanding.
EyeStill takes that part away. Every word arrives at the same point, shifted so that the letter your eye recognises first sits exactly in the centre — the red one.
No jumps between lines, no lost place, no re-reading loops. The eye stays still; the words do the moving.
On video that point sits at the speaker's lips, so expression and articulation stay in view while you read what they say.
Each word appears as it is spoken. Rare words get a little longer, frequent ones less, commas breathe — the rhythm follows the language.
Try it — space to pause, arrows for speed
An interview, an answer, a chapter — read it where your eyes already are.