Upload a video of someone speaking and give it new words: your own recording, or a script read by one of 22 AI voices. The mouth in the video is reshaped to match every word.
Need something else? More AI Video tools or all 29 tools
Lip Sync is a tool that changes the mouth movements of a person in a video so they match new audio. You upload a clip up to 2 minutes where one face is clearly visible. Then you either upload a new recording up to 60 seconds or type a script of up to 800 characters and pick one of 22 AI voices. The AI redraws the lips frame by frame to fit the new words. It's for videos of yourself or of people who gave permission.
The workshop starts on the twelfth of March, not the tenth. Doors open at six, and the first session begins at half past.
Voice (for the script): RachelQuality: StandardUse this example →New offerThis week only, every order ships the next day. Tap the link below and pick your size before Friday.
Voice (for the script): ChrisQuality: StandardUse this example →Close-up introHi, I'm glad you're here. In the next few minutes I'll show you the three steps I use to plan a whole week of meals on Sunday.
Voice (for the script): SarahQuality: ProUse this example →Sign in and upload an MP4, MOV or WEBM up to 2 minutes and 200 MB, with one face clearly visible. Use only videos of yourself or with the person's permission.
Upload a recording of up to 60 seconds, or type what the person should say and pick a voice. Choose Standard, or Pro for close-ups.
Press Sync the lips. The price is on the button. The lip sync video is usually ready in a few minutes and is saved in My Videos.
The AI works on the mouth area of the existing footage, so the person's face, clothes, background and camera move stay as they were. Only the lips and jaw change to fit the new sound.
Upload an MP3, WAV or M4A of the new line, up to 60 seconds, or type up to 800 characters for the AI to read. If you do both, the typed script is used.
Scripts are read in one of 22 built-in AI voices, from Rachel's calm narrator voice to Charlie's natural Australian male or Bill's older, trustworthy tone.
Standard gives accurate lip sync for most talking-head clips. Pro costs more and gives sharper detail around the mouth, which shows in close-ups and on large screens.
You pay for the length of the new speech, not the video. Standard is 600 credits for anything up to 14 seconds of new speech, then 43 credits a second, even on a 2-minute clip.
Changing a line on camera usually means setting up the shot again and getting a new take. Here you keep the footage and change the words.
| Feature | Lip Sync | Reshooting the scene |
|---|---|---|
| What you need | The original clip and the new line, recorded or typed | The person, the location, the lights and the camera again |
| Voice | Your own recording, or one of 22 AI voices | A new recorded take |
| Matching the take | Same face, framing and background; only the mouth changes | Match light, outfit and framing to the first take |
| Versions | Type another script and run it again | Another take for every version |
| Price | Priced on the new audio: from 600 credits on Standard | A shoot day, or a crew's time |
You filmed a 40-second piece to camera and said the wrong date in the middle. The light is gone and you can't film it again.
You have one clip of yourself presenting your brand's product and want three openings for different offers.
You have a voiceover of your own video in another language, and the mouth movements no longer match.
Correct a mistake, update a date or change a call to action in a talking-head clip without setting up the shot again.
Make several versions of one presenter clip of yourself, each with a different line for your brand's ads or pages.
Update one sentence in a recorded lesson when a fact changes, and keep the rest of the video.
Line up your lips with a voiceover you recorded in another language, so the dubbed clip looks natural.
It depends on the new audio's length and the quality. Each job has a minimum of 600 credits on Standard and 1,000 on Pro, which covers up to 14 seconds of speech; above that it is 43 or 71 credits a second, up to 2,550 and 4,250 for a full minute. A typed script also includes the AI voice.
Upload the video of the speaker, then upload the new recording or type a script and pick a voice, and press Sync the lips. The result is saved in My Videos.
The video can be up to 2 minutes and the new audio up to 60 seconds. A typed script can be up to 800 characters, about a minute of speech.
Yes. Upload a recording of your own voice as MP3, WAV or M4A, up to 60 seconds. If you also type a script, the script is used instead.
Pro gives sharper detail around the mouth, which shows in close-ups. Standard is about 40% cheaper and works well for most clips.
The result is cut to the shorter of the two. Use a video at least as long as the new audio so no words are lost.
Only with their permission. Public figures aren't allowed, and the tool must never be used to mislead people about what someone said.
It works best with one clearly visible face. With several faces, the AI may change the wrong person's mouth.
Yes. Sign in with Google or email; each job costs credits from your balance, and the result is saved in My Videos.
If a job can't finish, the credits it used go back to your balance automatically.
Make the person in a video say new words, with matching lips. from 600 credits, and the result is saved in My Videos.
