Recut
How to lip sync a video to new audio with AI
Attach the video of the person and the new audio, and ask Recut to "lip sync this to the audio". It runs a lip-sync model that redraws the mouth so it moves along with the new voice track.
What to type
Lip sync this clip to the new voiceover.
Step by step
- Attach the video and the audioA clear, front-facing face works best. The audio can be a recording, a dub or a voice Recut made.
- Ask for lip syncSay "lip sync", "sync the lips" or "match the mouth to this audio".
- Pick the modelRecut puts the strongest lip-sync models side by side, such as Sync Lipsync v3 and v2, Lipsync-2-Pro and LatentSync, with their prices.
- Run and compareLip-sync runs are priced by length. Compare the result with the original and try another model if the mouth looks off.
What Recut does
A lip-sync model keeps the rest of the video and regenerates the mouth area frame by frame to fit the sounds in the audio. Recut handles the parts in between: it uploads both files to the provider, fills in the model's settings and saves the result next to your original.
It fits naturally after a voiceover or a dub in one plan: make the new voice, then lip-sync the video to it.
Tips
- Have the audio and video the same length, or trim one to match, before syncing.
- To make a still photo speak, use a talking avatar model instead; lip sync needs a video.
What it doesn't do
- Side profiles, hands over the mouth and fast head movement are hard for every lip-sync model.
- Only make videos of real people saying things with their consent.
Try it on your own video
Recut runs in your browser, on Mac, Windows and Android. Start free, attach a file and say what you want.
Open Recut in your browserRelated guides
- How to dub a video into another language with AIRecut runs an AI dubbing model, such as ElevenLabs dubbing, that translates a video's speech into another language in the same voice.
- How to make a photo talk with AIAttach a portrait and a voice track, and Recut runs a talking-avatar model, such as OmniHuman or Kling AI Avatar, to make the photo speak or sing.
- How to add an AI voiceover to a videoPaste a script, pick a voice, and Recut reads it with an AI voice model and lays the voiceover on your video, with music turned down under it.