Caption any video, free, without it ever leaving your browser.
Upload a clip, get an automatic word-by-word transcript, style animated captions, layer in b-roll, and export a vertical 9:16 MP4 — all processed locally on your machine.
Free · No sign-up required · No watermark · Nothing uploaded
How it works
Upload a video
Drop in an MP4, MOV or WebM up to 600 MB. The file is read and processed inside your browser — it is not sent to a server.
Auto-transcribe
The Whisper speech model runs locally via WebAssembly and produces a word-by-word transcript with timings. Fix any word, hide filler, or break lines where you want.
Style and compose
Animated captions highlight each word as it is spoken. Pick colors and emphasis, then layer b-roll clips over your main video on a timeline.
Export a 9:16 MP4
Captions are burned in and the video is encoded in your browser, ready to post to TikTok, Reels, or Shorts. No watermark.
What the captioner does well
Word-by-word animated captions
Each word lights up as it is spoken, in the style short-form viewers expect. Highlight and emphasis colors are yours to set.
Nothing leaves your browser
Video decoding, speech transcription, and export all happen locally. Your footage is never uploaded unless you sign in and choose to save a clip to the cloud.
A real transcript editor
Click any word to fix it, hide filler words, add emphasis, or move a line break. Caption timing follows your edits.
B-roll overlays
Add extra clips as channels over the main video, position and time them on the timeline, and control size, opacity, and audio per clip.
Free, no account, no watermark
The captioner and full exports are free. There is nothing to sign up for and no logo stamped on your video.
Honest export
The preview and the exported MP4 come from the same renderer, so the captions you see are the captions you get.
Your footage stays yours
Most online captioning tools work by uploading your video to their servers. This one does not. The video is decoded in your browser, the Whisper speech model transcribes it locally via WebAssembly, and the final MP4 is encoded on your own machine. As a guest, nothing you upload is transmitted anywhere. If you sign in, you can choose to save clips to cloud storage — and only the clips you explicitly save are uploaded.
Frequently asked questions
- Is the video captioner really free?
- Yes. Uploading, transcribing, editing, and exporting are all free, with no watermark and no account required. Because everything runs in your browser, there are no server costs to pass on.
- What video formats and sizes are accepted?
- MP4, MOV and WebM files up to 600 MB. Large files are compressed on the way in so the editor stays responsive.
- Does my video get uploaded anywhere?
- Not unless you ask it to be. As a guest, your video is decoded, transcribed, and exported entirely inside your browser — nothing is transmitted. If you sign in, you can optionally save clips to cloud storage, and only what you explicitly save is uploaded.
- How does the automatic transcription work?
- The Whisper speech-recognition model runs directly in your browser via WebAssembly, using model files served from this site. Audio is transcribed into words with timings, and you can correct any word afterwards in the transcript editor.
- Can I change how the captions look?
- Yes. Captions animate word by word with a highlight color you control, plus a separate emphasis color for words you mark. You can hide words, fix the text, and move line breaks — the burned-in output matches the preview exactly.
- Does it work offline?
- Mostly. You need a connection to load the app and the speech model, but once they are loaded, transcription, editing, and export are all local, so a dropped connection mid-edit does not lose your work.
- Where are my files stored?
- In your browser’s local storage (IndexedDB) on your own machine. Clearing site data removes them. Signed-in users can additionally save clips to cloud storage — that is the only case where a file leaves your device.
- What browser do I need?
- A recent desktop browser — current Chrome, Edge, or Safari work well. The editor checks your browser’s video capabilities when it opens and tells you plainly if something required is missing.
Caption a video now
No account, no watermark, no upload. Drop in a clip and export a finished vertical video.
Upload a video