AI Video Translation creates a localized version of an existing project video. It can translate speech, match the original speakers’ voices, and optionally synchronize mouths or add translated captions. It is not the same as translating captions only; use the Transcript and Captions tools for subtitle-only work.
What do I need before writing the prompt?
- Import the complete source video into My Assets and identify it with
@. The job processes and bills the full source duration. - Choose the target language and decide whether to translate spoken audio or captions only.
- Decide whether you need lip sync, burned-in translated captions, and the exact original duration or a slightly flexible duration for natural pacing.
- Confirm that you have rights to the footage and its speakers. For a close-up or polished deliverable, you may request more precise lip sync, but the confirmation will show a higher credit estimate.
Prompts you can copy
Translate @Mandarin-presenter into English, preserve the original speaker's voice, and synchronize the mouth movements. Add translated captions and allow the duration to change slightly for natural pacing. Save the result to My Assets without replacing the source.
Translate the speech in @screen-recording into Japanese. Replace audio only: do not redraw or otherwise change the picture, and do not burn in captions. Keep the output duration identical to the source.
Generate a translated video
- Import the source video into My Assets, open the AI panel, and switch to Agent mode.
@mention the source in the prompt and state the target language, lip-sync choice, caption choice, and duration requirement.- Send the request. If you only say “translate this video,” the Agent asks whether you want captions only or translated spoken audio as well.
- For lip-sync translation, review and edit the detected source transcript, then confirm it. The confirmed timed text is used for the translation. Audio-only translation can continue without this transcript-review step.
- Review the paid confirmation, including the treatment, source duration, and credit estimate, then allow generation.
- Follow progress in the conversation and My Assets. The result is a new localized video asset; the source is not replaced.
- Review translation, pronunciation, multiple speakers, captions, and lip sync. Drag the result to the timeline when you are ready to use it.
To process only part of a source, trim and export that section as a separate asset first. Lip sync re-renders the picture, so do not expect alpha, HDR, codec, bitrate, or frame rate to remain identical. Choose audio-only translation when the picture must remain unchanged.
See Transcript and Captions, Talking Head Edit, and Generation Credits.