Put the words
where people can see them.
Generate captions from your clip’s speech, correct the phrases and choose a style that fits. ClippyTag processes speech on your device, so your audio is not sent to a transcription service.
Add subtitles to a clip ↗Three looks, one clear message
- Studio: a complete phrase stays visible for easy reading.
- Highlight: a color follows the measured word timing.
- Punch: the active word animates for a more expressive clip.
Adjust text and highlight colors, size, capitalization and height. Your spoken language and caption style are remembered in this browser.
How to add automatic subtitles
- Import a video up to 3 minutes and 150 MB. MP4 with H.264 video and AAC audio is the most compatible starting point.
- Open Captions, choose the spoken language and enable Auto captions. English, Italian, Spanish, French and German are available.
- Wait for transcription, review names and slang, and choose your look. Export the SRT transcript or sign in to export an MP4 with burned-in captions.
Choose the model for your device
The More accurate option uses Whisper Small, with an initial model download of approximately 250 MB. The lighter Whisper Base option downloads approximately 80 MB. Processing can take several minutes, especially on a phone. Model files may be cached for later use.
Correct before you publish
Automatic speech recognition can mishear names, slang, music and overlapping voices. Word effects use measured timing. If a correction changes the word count, that phrase uses static text until you regenerate it. Avoid adding a second set of captions to a clip that already has them.
Free includes 10 completed editor exports per account, total, with the ClippyTag mark. You can also add a saved signature or start with the free TikTok downloader.