Features
Captions that are right, on time, and yours to style.
AutoCap does one job — getting speech onto the screen — and every feature exists to make that faster, more accurate or better looking.
Transcription
Speech to captions, timed word by word.
Upload a clip and AutoCap transcribes the speech automatically. Every word comes back with its own start and end time, and the words that carry a sentence are marked for emphasis so highlight styles work straight away.
- English speech, with more languages on the way
- A start and end time for every word
- Key words marked for emphasis automatically
- Only the audio is sent for transcription
100:00:00,150 --> 00:00:01,200This is how 200:00:01,200 --> 00:00:02,600you go viral
Editor
A caption editor built around words, not lines.
Models slip on names, brands and jargon, so every word stays yours to correct. Edit text in place, reshape lines, and move one word's timing on the timeline without disturbing its neighbors.
- Correct any word in place
- Split and merge caption lines
- Drag a single word's timing on the timeline
- Recolor individual words for emphasis
- Edits never use transcription minutes
Styles
Caption styles that are ready to post.
Start from 32 built-in styles and a growing gallery of templates — clean subtitles, word pops, karaoke fills — then make them yours with fonts, colors, animation and position.
- 32 built-in styles, plus published templates
- Dozens of fonts, or upload your own on paid plans
- Colors, outlines, backgrounds and animation
- Drag the caption block anywhere in the frame
Export
A finished video, or the files to go with it.
Burn captions into an MP4 rendered right in your browser, at up to 2K and with your clip's frame rate and audio kept exactly as they were. Or download standard subtitle files from the same transcript.
- Burned-in MP4 up to 2K (1440p), never upscaled
- 9:16 for Reels and Shorts, 1:1 for feeds, 16:9 for YouTube
- SRT and VTT subtitle files on paid plans
- Unlimited exports on every plan
Privacy
Your footage stays on your device.
Rendering happens in your own browser, so a video never has to be uploaded just to have captions put on it. The only thing that leaves your device is the audio, and only so it can be transcribed.
- Video rendered locally, not on a server
- Audio sent only for transcription
- Your videos, audio and transcripts are not used to train models
Anywhere
Nothing to install. Works on desktop and phone.
AutoCap runs in the browser, with an editor laid out for phones as well as desktops. Add it to your home screen or dock and it opens like an app.
- Runs in a modern web browser
- Phone layout with bottom sheets for captions and styles
- Installable as an app on desktop and mobile
See it on your own video.
The free plan includes 2 minutes of transcription every month. No credit card, no expiry.