AI Lip Sync
AI lip sync adjusts one front-facing presenter’s mouth movements to translated speech. Use a video longer than 1 second and up to 210 seconds.
Start dubbingPreview the first 30 seconds before you spend any credits.
Illustration
0:00Hola, bienvenidos a nuestro canal.
0:03Hoy les muestro cómo empezar.
0:06¡Vamos a ello!
Lip sync for translated video
A translated sentence uses different mouth shapes from the original. Lip sync adjusts the visible mouth region after the translated voice has been generated. It is an optional part of video dubbing, rather than a standalone animation or live translation tool.
How it fits into dubbing
- Upload a video. Sign in and upload an authorized MP4, MOV or WebM file up to 200 MiB. Lip sync requires video longer than 1 second and no longer than 210 seconds.
- Preview the voice. Choose one of 13 target languages and listen to a free preview of up to 30 seconds. The preview checks speech and translation; it does not include lip sync.
- Generate the full dub. Enable lip sync and review the total quote before starting. The background is separated and mixed with the translated speech; separation can leave artifacts.
- Review and export. Check the mouth alignment and audio. Download the dubbed video, mixed audio, voice-only audio and separate source/translated SRT/VTT subtitles.
After a full dub, editing a translated sentence can redo the affected lip-sync window. Review that edit's quote before regenerating; editing is not free or part of the preview.
When to use it
Use a single, clearly visible, front-facing presenter. Side profiles, small faces, fast head movement and occlusion can reduce quality. Review the generated video; mouth alignment is not guaranteed.
Skip lip sync for screen recordings, slides, voice-over on B-roll and group conversations. Audio-only uploads and videos longer than 210 seconds cannot enable it. Ordinary dubbing accepts recordings up to 10 minutes.
Pricing and failure handling
Lip sync adds a per-language charge to dubbing. See pricing for current plans and review the workspace quote before generation. A lip-sync failure can still deliver the dubbed audio while releasing the lip-sync reservation; review the reported result before publishing.
Related workflows and permissions
Start with the video translator or prepare your own channel file with the YouTube video translator.
You must own or have permission to use the video, voices, music and images. Optional voice cloning also requires the speaker's consent. Review AI transcription, translation, pronunciation and mouth alignment before publishing. Read the terms.
From upload to dubbed video in four steps
No studio and no voice actors, and you stay in control of every sentence.
- 1
Upload your video
Upload recorded video or audio, up to 10 minutes and 200 MiB, and choose your target languages.
- 2
Preview 30 seconds free
Hear the first 30 seconds in your target language before you spend any credits.
- 3
Edit any sentence
Fix a translation and regenerate just that line; the rest of the dub stays as it is.
- 4
Export the dubbed video
Download the full video with the translated voice and subtitles.
Frequently asked questions
After the video is translated and re-voiced, lip sync edits the speaker's mouth movements so they match the new audio instead of the original language.
A single speaker facing the camera, with the face clearly visible and well lit. This first version is designed for one front-facing speaker.
No. This version is designed for one front-facing speaker. Use dubbing without lip sync for interviews and group scenes.
Lip sync is an optional extra on top of dubbing, charged per target language by video length. The total is shown before generation starts.
Yes. Leave the lip-sync option off to generate a dub without mouth adjustment. Audio-only uploads cannot enable lip sync.