AI lip sync video with Kling Lip Sync
Lip sync takes a video you already have and reshapes the mouth movements so they follow new audio.
In shuut this runs on Kling Lip Sync, and the sound can be a file you upload or a voice you make in shuut.
Models for this
| Model | Made by | Price | Lowest price | Length |
|---|---|---|---|---|
| Kling Lip Sync | Kuaishou | 17 credits per generation | 17 credits per generation | 2–60 seconds |
Prices are in credits (1 credit = US$0.01) and are deducted from your shuut balance per use. You see the exact price before each generation.
Where to find Lip sync in shuut
Lip sync is not a separate tool in shuut but a mode inside “AI Avatar”.
Open “AI Avatar”, switch to the “Lip sync” mode, and the screen asks for a video and a piece of audio.
If you start from a still picture instead of a clip, the “Talking photo” mode in the same tool is the one to pick.
The model behind Lip sync: Kling Lip Sync
Lip sync uses a single model, Kling Lip Sync, so there is no model to choose.
Kling Lip Sync keeps your footage and changes the mouth to match the audio, which is different from a model like Kling 4.0 that makes a brand-new clip with its own sound.
The table on this page lists Kling Lip Sync with its maker and the clip lengths it accepts in the “Length” column.
The cost of a lip sync job grows with the length of your video in fixed short steps, so a shorter clip costs less.
Before you upload a Lip sync video
Use a video that shows a single person, since Kling Lip Sync matches one mouth to the audio.
Prepare the audio first: either your own recording or a voice made in the sound tool of shuut.
The person in the video must be you or someone who gave consent, and the same goes for a voice that belongs to a real person.
Check whether the place you post it needs an AI-generated label.
How to make an AI lip sync video in shuut
- Open “AI Avatar” and choose the “Lip sync” mode.
- Upload a video of a single person who is you or who gave consent.
- Add the audio: upload your own file or pick a voice made in shuut.
- Press “Generate” to get the same video with the mouth moving to the new audio.
Frequently asked questions
- How long can a lip sync clip be?
- Lip sync runs on Kling Lip Sync, and the “Length” column in the table on this page shows the clip lengths it accepts.
- Can lip sync handle a video with several people talking?
- No. Lip sync needs a video with a single person in it.
- Whose face and voice am I allowed to use for lip sync?
- The person in the video must be you or someone who gave consent. Real people appear in the results, so consent from anyone shown or heard is required.
- How is the lip sync price worked out?
- The price is per run and rises with the length of your video in fixed short steps. shuut shows the price as a quote before you press “Generate”.
- Do I need my own recording for lip sync?
- Not necessarily. You can upload your own audio file or use a voice made in shuut.
What you can make
- Image to video AI: turn a photo into a moving clip
- Text to video: write a scene, get a video clip
- AI shorts maker: vertical clips, captions and resizing in shuut
- AI video upscaler: enlarge clips and photos to 4K
- AI talking avatar video from a photo and a voice
- AI UGC video from a presenter photo, a product photo and a script
Updated November 17, 2026
Before you start
You pay per result, with a quote before you press “Generate”; subscriptions are optional.
Motion shots, captions and resizing are free once you sign up.
Section 9 of the Terms covers commercial use; scope varies by model and agreement, and checking rights, ad rules and AI labels is up to you.
shuut isn't affiliated with the model makers.