Video
Add captions
Transcribe a video and add captions, burned in or as a subtitle file.
Use this skill in a chatOpens a new chat with it attached.
What it asks you for
- Videorequired
- The video to caption.
- Deliver as
- Burned-in pixels or a separate file.
- Style
- Caption look.
What it tells the AI to do
The full instructions, exactly as they run.
Caption {{ video }} — deliver: {{ mode | default("burn") }}, style: {{ style | default("clean") }}.
1. `inference transcribe` the video to get timed text.
2. Write a proper `.srt`/`.ass` with those timings. Do not guess timings from
the transcript's line breaks — the timing IS the transcription's output.
3. For burned-in captions, re-encode ONCE with the subtitle filter:
```bash
ffmpeg -i /tmp/input/in.mp4 -vf "subtitles=/tmp/input/subs.srt:force_style='FontSize=22,Outline=2,MarginV=48'" \
-c:a copy /tmp/output/captioned.mp4
```
Keep lines under ~42 characters and 2 lines maximum on screen — longer lines are
unreadable at the speed people scroll. Deliver the `.srt` alongside the burned
version whenever both were asked for, since only the file is editable later.
## Delivery
Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.- video
- captions
- subtitles
- accessibility
More video skills
Run it on your own work
idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.
Use Add captions