How to Lip Sync a Video with AI: Match the Mouth to New Audio

What AI lip sync does

Upload a video of someone talking and a new voice — a script read by a built-in voice, or an audio file. BunCho's lip sync tool redraws the mouth so it matches the new voice. The face, body and background stay as in the original video.

The result is as long as the shorter of the video and the new voice. Videos can be up to 60 seconds and the voice up to 30 seconds, so split longer videos into 30-second parts.

• Replace a line in a video you shot with a new recording
• Dub your own video into another language
• Add dialogue afterwards to an AI avatar or a generated character clip

What to prepare (video and voice)

• Video: up to 60 seconds, MP4, MOV or WebM. A large, front-facing face works best
• Scenes where the mouth is hidden (hands or a microphone in front, long side views) may not match well
• Voice from a script: up to 300 characters, read by the voice you choose
• Voice from a file: up to 30 seconds of clean speech
• Permission: if anyone other than you appears in the video, you need their permission

How to lip sync a video

1. 1Open the video tools

   In the studio, open Video tools and choose Lip sync.

2. 2Add the video

   Upload the video to re-sync (up to 60 seconds).

3. 3Set the new voice

   Type a script and choose a voice, or upload an audio file of up to 30 seconds.

4. 4Pick a model and estimate

   Choose a model, press Estimate and compare the credits.

5. 5Confirm rights and generate

   Tick the rights box and press the generate button.

6. 6Download

   Download the result and finish it in your video editor.

See also: Lip sync tool overview

Models you can choose, and approximate credits for 5 seconds

sync-3 also handles side views and partly covered mouths, and uses more credits. sync lipsync-2-pro draws the mouth in more detail. Kling Lip-Sync is priced in steps (up to 5 s, up to 10 s) and is the lowest-credit option for 5 seconds. PixVerse LipSync also uses few credits and is fast.

Fixing common problems

• Some shots do not match: for videos with many side views or covered mouths, choose sync-3 or cut those shots out
• The result is shorter than expected: the length is the shorter of the video and the voice. Check the voice length
• The voice is hard to hear: use an audio file with only speech, without music or noise
• The video is longer than 60 seconds: trim it to 60 seconds or less in your editor first

Rights and AI disclosure

Only use images, audio and video that you own or have permission to use. Real people's faces and voices may only be used with that person's permission. Before generating, you tick a box confirming you have the rights.

You may not make videos that show someone saying something they did not say in a misleading way, or that impersonate someone. When you publish, label the video as AI-generated or AI-edited according to the platform's rules (for example, YouTube's altered or synthetic content setting).

Model names in this guide and in the product are listed because you can choose them in BunCho. Listing them does not imply any partnership with or endorsement by their makers.

Plans and credits

The video tools are available on paid plans (Watering, Seed, Feast, Full Course, Team & Business) with an active subscription. They are not available on the free plan or during a paid plan's free trial.

They use your studio's monthly AI credits, the same balance as novels, manga and video. You see an estimate before generating and nothing is made until you agree. No credits are used if a job fails or if you cancel it before it starts.

See also: Plans and pricing / All five video tools