1. Upload an MP4
Choose a video up to 10 minutes and 2 GiB. Keep the face unobstructed and avoid rapid turns or cuts.
AI Lip Sync
ExampleMake your script speak on screen
Use a clear view of one person facing the camera. The result follows your script and selected voice.
2. Write and choose a voice
Enter your script and choose from 17 voices. Check the script language and the estimated credits before generating.
3. Review and download
Review pronunciation, mouth movement and face detail, then download the MP4. Speech length determines output duration; the source may loop.
Lip sync FAQs
Does this translate the original audio?
This tool speaks the script you enter in the chosen voice. Use AI Video Translator when you want to translate the original spoken content.
Which voices and languages can I use?
There are 17 voices with Chinese, English, Japanese, Korean, Spanish and Portuguese options. Four multilingual voices support additional languages. Choose a compatible voice for the writing system in your script.
How long is the generated video?
Output duration follows synthesized speech, with a minimum billing estimate of 3 seconds. If the source clip is shorter, it may loop. The 1,800-unit script limit is roughly 113 seconds of speech; actual speaking speed varies.