Dub a video

What it asks you for

Videorequired

The video to dub.

Target languagerequired

Language to dub into.

Keep original under

Leave the source audio quiet underneath.

What it tells the AI to do

The full instructions, exactly as they run.

Dub {{ video }} into {{ language }}.

Pipeline: transcribe → translate → synthesize → fit → mux.

The step that decides quality is FIT. Synthesized speech is rarely the same
length as the original, and a dub that drifts out of sync is unusable:

- Translate for LENGTH as well as meaning — ask for a rendering that takes about
  the same time to say.
- Synthesize per cue, not as one long take, so each line can be placed.
- Where a line still runs long, adjust its rate slightly (`atempo`, stay within
  0.9–1.1 — beyond that it sounds processed) rather than letting it overlap.

Keep original under: {{ keepOriginal | default(false) }}. When on, duck it to
about −20 dB so it reads as ambience, not as competing dialogue.
## 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
• dub
• translate
• tts

More video skills

• Create a videoGenerate a video clip from a text prompt.
• Animate an imageTurn a still image into a short moving clip.
• Edit a videoTrim, join, speed, crop, or watermark a video with ffmpeg.