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.
To start from a form on the web, use the AI video translator page.
What do I need before writing the prompt?
- Import the complete source video into the Media Pool 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.
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 the Media Pool 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 the Media Pool, 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.
- Review and edit the detected source transcript, then confirm it. The confirmed text is used for both lip-sync and audio-only translation.
- Review the paid confirmation, including the treatment, source duration, and credit estimate, then confirm it. For an integrated translation, the button is Confirm and generate.
- Follow progress in the conversation and the Media Pool. 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. When the picture must remain unchanged, ask for translated audio only, and specify that choice when starting an AI dubbing project.
For audio-only requests, the Agent usually dubs the speech separately: it clones the original speaker’s voice and generates the translated speech, which keeps the picture and generally costs less. It uses the integrated audio-only translation when you ask for it. If you want to choose or audition the voice before any video is rendered, the Agent can generate the speech first and then apply Lip Sync to the approved audio. Narration in a cloned voice requires a paid plan.
Depending on your plan, video translation may require an upgrade; if it does, ChatCut says so before generating, and your credits are kept. The number of video generations that can run at once is limited and can depend on your plan (see Free and Paid Plans); video translation shares it with video generation, AI avatar videos, and Lip Sync. When you reach it, ChatCut either queues the request or asks you to wait.
See Transcript and Captions, Talking Head Edit, and Generation Credits.