Dubbing into another language
Record or generate the translated voice, and the speaker's lips follow the new words instead of the original ones, so the dub no longer looks dubbed.
AI lip sync
AI Lip Sync Video Generator
Upload a video and the audio you want it to say. The speaker's mouth is redrawn to match every word, while the face, the background and the camera move stay as filmed. Choose Sync 3 for the hardest shots, or Lipsync 2 Pro to spend less.
Re-sync the lips in an existing video to new audio while keeping the rest of the face and the scene intact. Works on live action, animation and AI-generated footage, including side angles, close-ups, partly covered faces and shots with several people.
Priced per second of the finished video, rounded up. The video runs as long as your audio, so the price below shows the exact total once your audio is attached.
27 credits/s
The synced video opens in a session you can come back to, ready to download or use in another tool.
How it works
How to lip sync a video in three steps
- Step 1
Upload your video
Add a clip of up to 60 seconds in which the speaker's face is clearly visible. Live action, animation and AI-generated footage all work.
- Step 2
Add the new audio
Add the voice track the speaker should say, between 1 and 60 seconds long: a translation, a re-recorded line or a generated voice. Then pick a model.
- Step 3
Generate and download
The finished video runs as long as your audio and opens in a session that belongs to you, ready to download or carry into another edit.
What it is for
What people use AI lip sync for
Fixing a line without a reshoot
A wrong product name, a changed price, a stumbled word: record the corrected line and sync it to the take you already have.
Ads and explainers in several versions
Film one take of a presenter, then make versions for different offers, markets or audiences by changing only the voiceover.
AI and animated characters
Give a generated or animated character a voice. Both models work on AI-generated footage and animation as well as live action.
What happens to your video
How AI lip sync changes a clip
Only the mouth changes
The lips and jaw are redrawn to match the new audio. The rest of the face, the background, the lighting and the camera move stay as they were filmed, and the finished video plays with your new audio.
When the audio and the video are different lengths
The finished video is always exactly as long as your audio. If the audio is longer than the clip, the clip plays forward, then backward, and repeats until the audio ends. If the audio is shorter, the clip is cut where the audio stops. Either way, you pay for the length of the audio.
Two models to choose from
Sync 3 is the default and the one for difficult shots: side angles, close-ups and faces that are partly covered. Lipsync 2 Pro costs less per second, keeps details such as teeth and facial hair, and follows whoever is speaking when several people are in the shot.
Pay per second, not per month
Lip sync is priced by the second of the finished video, so a short clip costs what a short clip should. Every plan includes credits, and they work on every other tool on YouArt.
Basic
For hobbyists and explorers
$9.99/mo
Select Plan- 1000 credits
- Up to ~200 images/month
- Up to ~332s video/month
- Intelligent creative agent
- Video editor
- Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
- Latest video models, including Seedance 2
- Realistic face uploads
- Voice generation with ElevenLabs
- No watermark
- Unlimited template access
Pro
PopularFor creators and pro users
$29.99/mo
Select Plan- 3300 credits
- Up to ~1000 images/month
- Up to ~1100s video/month
- Intelligent creative agent
- Video editor
- Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
- Latest video models, including Seedance 2
- Realistic face uploads
- Voice generation with ElevenLabs
- No watermark
- Unlimited template access
Max
Best ValueFor power users and teams
$149.99/mo
Select Plan- 18000 credits
- Up to ~6000 images/month
- Up to ~6000s video/month
- Intelligent creative agent
- Video editor
- Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
- Latest video models, including Seedance 2
- Realistic face uploads
- Voice generation with ElevenLabs
- No watermark
- Unlimited template access
Team
For teams and studios
$329.99/mo
Select Plan- 36300 credits
- Up to ~12000 images/month
- Up to ~12100s video/month
- Realistic face uploads
- Share canvas, workflows, and assets with your team
- Up to 10 members per team
- Up to 5 teams
- Role-based management
- Team credit management and spending caps
- Per-member usage tracking
Questions
AI lip sync FAQ
It is a way to make the person in a video say something new. You give it a clip and an audio track, and AI redraws the mouth frame by frame so it matches the words in the audio. The face, the background and the camera move stay as filmed, so the result looks as if the speaker said those words on camera.
More tools
More tools for your project
Choose another tool to edit, enhance or transform your images and videos.
Tool recommendations, page 1 of 4
Beyond one clip
Need more than one lip sync?
This page runs one step at a time. Open the workflow editor to generate the voice and sync it in one workflow, add lip sync to a clip you generated, or run a batch of videos through the same steps.