Add captions to your video, free.
Free, no signup, no watermark. Your video never leaves your device.
Captions that pop word by word, timed to your voice.
Caption my videoNo clip handy? Tap Try a sample in the editor.
How do I add captions to a video automatically for free?
Open the video in Cutmallow and tap Generate captions. OpenAI's open-source Whisper speech model writes the words and times each one to your voice, right in your browser, in any of 99 languages. Fix any word by typing, pick an animated style, and export an MP4 with the captions burned in, or download them as SRT or VTT subtitles. It is free, with no watermark and no upload.
Updated
- Languages
- 99
- Timing
- Word by word
- Exports
- MP4, SRT, VTT
- Watermark
- None
How to do it in three steps
Drop your video into the editor. It opens on your device, nothing is uploaded.
Tap Generate captions. They are written word by word and timed to your voice.
Pick a style, fix any word, and export a 9:16 MP4 with the captions burned in.
Then keep going in the same place: add captions, zooms and a style, so the Short is finished before you leave the page.
How it works
Cutmallow runs Whisper, the open-source speech recognition model from OpenAI, inside your browser. The model downloads once on first use and stays on your device, so later videos caption faster and even work offline. Your audio is never sent to a server.
Speech is split into short segments first, so long videos stay accurate and do not drift. Each word gets its own start and end time, which is what lets captions pop word by word and stay in sync when you trim the video.
Tips for a better result
- Cut pauses before captioning: you get tighter caption pages and less to fix.
- Proper nouns and brand names are the usual misses. Fix them once in the transcript.
- Keep captions inside the safe zone so TikTok and Reels buttons do not cover them.
One flow instead of three apps
Every free tool here opens the same Cutmallow editor, so the whole Short gets finished in one place.
- Pauses, noise and captions in one editor, instead of a different app for each job.
- Private: the video is processed on your device and never uploaded.
- Works on phones as well as laptops, in the browser you already have.
- No credits, no usage limits, no watermark.
Frequently asked questions
Something else? Write to [email protected].
Which languages does it understand?
Many. The speech model knows 99 languages and the common ones are in the picker, or it can detect the language for you.
Why does the first run take a moment?
The speech model downloads once, the first time you make captions, and is kept on your device afterwards. Your audio is never sent anywhere.
Can I fix a word it got wrong?
Yes. Every caption line is an editable field in the transcript: type the right word. Timing stays in sync, even after you cut pauses.
Does it work on my phone?
Yes. It runs in Safari on iPhone and in Chrome on Android, as well as Chrome, Edge, Safari and Firefox on computers. An older phone takes longer, because your own device does the work.
Is there a watermark or a paid plan for this?
No. The export is clean, in full quality, with no account. Cutmallow runs on your device, so there are no server bills to pass on.