Upload or generate the audio
Bring your own MP3/WAV, or switch to Generate voiceover: type the script, choose a voice, and the audio is produced in place.
TOOL · LIPSYNCAFFOGATO TOOLS
Make any video say anything.
Lipsync re-times a speaker's mouth to a new audio track. Upload a video and an audio file — or type a script, pick a voice and generate the voiceover right inside the tool — and the output is the same clip, saying the new words, with lips that match.
VIDEO + AUDIO IN · OR TYPE A SCRIPT · VOICE LIBRARY INCLUDED
01WHAT YOU GET
Built for the job, not a generic prompt box.
Full voice library
Pick from the Audio Studio's voices — many languages and accents — or a custom voice you designed. The right engine is chosen for the voice automatically.
Flagship sync model
Runs on the current best lip-sync engine in the catalogue (Sync v3 by default), swappable as better models land.
Works on generated video
Any clip you make in Affogato can be sent straight to Lipsync — talking heads, UGC-style ads, avatar episodes.
Separate, visible pricing
The voiceover is priced per character and the lipsync per render; both estimates show before you generate.
No reshoot
Change a line, translate a script or swap the message without going back to camera.
02HOW IT WORKS
How to lip-sync a video to new audio with AI, in three steps.
- 01
Upload the video
MP4, MOV or WebM up to 200 MB with a visible speaker. A generated clip from the Video Studio works too.
- 02
Add the audio
Upload MP3, WAV, M4A, OGG or WebM up to 50 MB — or choose Generate voiceover, type what the speaker should say and pick a voice.
- 03
Generate
The estimate shows the cost; click Generate and the lip-synced video lands in your assets, ready to download or send to Upscale.
VIDEO MP4 · MOV · WEBM ≤ 200 MBAUDIO MP3 · WAV · M4A · OGG ≤ 50 MBSCRIPT TYPE IT · UP TO 5,000 CHARSVOICES LIBRARY + CUSTOMOUTPUT 1 VIDEO
03EXPLAINED
What is AI lipsync, and when should you use it?
AI lipsync re-animates a speaker's mouth so it matches a different audio track. Give it a video of someone talking and a new recording — or a script you want voiced — and it produces the same footage saying the new words, with mouth shapes that follow the speech. It's how you dub, re-voice and correct video without a reshoot.
Affogato's Lipsync lives in the Video Studio. The audio can be a file you upload or a voiceover generated on the spot from a typed script and a voice from the library, so a single screen takes you from words to a finished, synced clip.
It pairs naturally with the rest of the studio: generate a presenter in the Talking Head Studio, a creator clip in the Video Studio or a persona in the Influencer Studio, then send the result to Lipsync to change what they say.
04USE CASES
What people make with it.
Dub into another language
Translate the script, generate the voiceover in a matching voice, and sync the original footage.
UGC ads from a script
Type the pitch, pick a voice, and turn a creator-style clip into a testimonial that says exactly what you need.
Fix one line
A flubbed word or an outdated price — re-voice just the clip that needs it.
Personalised outreach
One talking video, many names and messages, without recording each one.
Avatar and character videos
Give generated presenters and characters new dialogue whenever the message changes.
05FAQ
Questions, answered.
Can I generate the voiceover instead of uploading audio?
Yes. Switch the Audio Track slot to Generate voiceover, type the script (up to about 5,000 characters depending on the voice model), choose a voice and generate. The audio is created in place and then synced to the video.
Which voices are available?
The full Audio Studio library — dozens of voices across languages and accents — plus any custom voices you've designed. You pick the voice; the right text-to-speech engine is chosen automatically.
What video works best?
A clip with a clearly visible, front-facing speaker and steady framing. Generated clips from the Video, Influencer and Talking Head studios all work.
How is it priced?
The lipsync render is priced per run and the generated voiceover per character; both credit estimates are shown before you generate. Failed renders are refunded.
Can I use it for dubbing into other languages?
Yes. Write or translate the script, pick a voice in the target language, generate the voiceover and sync.
Can I use the output commercially?
Yes. Every plan includes a commercial license and there are no watermarks. Use your own footage or footage you have rights to, and label AI-altered video where platforms require it.
New words.
Same video.
Sign in, upload a clip, type the script and generate. The synced video is ready in minutes.
NO WATERMARKS · CREDITS ROLL OVER · COMMERCIAL LICENSE INCLUDED · CANCEL ANYTIME