Create AI Lip Sync Videos Online for Free

Use AI lip sync to match any video with new audio. Upload your footage along with an MP3, WAV or typed script, and HeyGen adjusts the speaker's mouth movements to match every word, in any language.

Smiling woman beside an audio player displaying the text "Hello, this is how I sound. Voice - Custom voice."
  • 18,23,50,931 Videos generated
  • 15,78,47,846 Avatars generated
  • 2,69,73,782 Videos translated
Trusted by millions worldwide to bring their stories to life.
Key features

AI Lip Sync Features

Sync lip movements in any video with new audio

An incorrect line once meant booking the presenter again and reshooting. Upload the original MP4, MOV, or WEBM, add a corrected MP3, WAV, or typed script, and the model redraws the mouth frame by frame. Short clips are ready in two to five minutes.

Text or audio to lip-sync video workflow with voice and language options

Your voice, in over 177 languages

Re-recording a voiceover for each new market increases costs and turnaround time. Clone your voice from a 15-second sample with voice cloning, translate the script into 175+ languages and dialects, and get every translated version lip-synced in your own tone.

Instant voice cloning retained across languages

Create talking photos from one image

Some projects begin with no footage at all. Upload a portrait along with an audio file or script, and the AI photo avatar animates the face with synchronised lip movements, head movements and expressions. Turn a headshot into a talking or singing video without a camera crew.

Talking photo speaking in multiple languages

Precision mode for side profiles and group scenes

Basic lip sync goes out of sync as soon as a speaker turns, a microphone obscures their mouth, or the camera cuts away. Precision mode tracks changes in speakers, camera angles and side profiles, and syncs every visible face, so interview and panel discussion footage remains usable.

Multi-speaker lip sync with automatic speaker detection

AI avatar lip sync with Custom Motion

When a presenter is not available, choose from over 1,100 stock avatars or Avatar 6 to deliver your script. Custom Motion uses prompts to guide gestures, posture and expressions, so the same script can work as a calm explainer or an engaging social media hook.

Studio-quality realistic AI avatars with customised motion
Use cases

Practical applications of AI Lip Sync

Illustration of video dubbing in 177+ languages

Dub videos in 175+ languages

A localisation manager uploads each track dubbed by voice actors alongside the original video. HeyGen adjusts the speaker's mouth movements for each language, so dubbed versions look natural rather than visibly out of sync.

Illustration for personalised videos at scale

Personalised videos at scale

A sales representative records a single take, then uses variables from a Google Sheet or HubSpot to change the prospect's name, company or offer. Each personalised video is generated with matching lip movements, with hundreds of videos per campaign.

Illustration for YouTube and Shorts localisation

Localisation for YouTube and Shorts

A YouTube creator who posts weekly in English pastes each link into the video translator, selects up to 10 languages, and publishes natural-sounding, lip-synced versions with a cloned voice and captions on the same day.

Illustration showing how to update training videos without reshooting

Refresh training videos in minutes

An L&D manager updates a compliance module whenever a policy changes. They edit the relevant paragraph in the script, regenerate the video with lip sync, and republish it without having to book a presenter or studio time again.

Illustration of UGC ad localisation at scale

Localise UGC ads at scale

A performance marketer using the same UGC hook across regions can dub each variant into the local language with matching lip movements, or generate the creator using Veo 3.1 or Seedance 2.0 within HeyGen and sync the lip movements.

Illustration for daily product demos without a camera

Create daily product demos without a camera

A product marketer creating daily demos selects a stock avatar, pastes the day's script and generates a video. When a feature changes, they edit a single line and regenerate the video, with the avatar's lip movements matching the updated script.

How it works

How to create an AI lip-sync video from a video or photo

Create your video in four steps using a video or a single photo with audio. Short clips take two to five minutes to render.

step icon

Upload your video or photo

Add an MP4, MOV or WEBM file up to 5 GB, paste a YouTube or Google Drive link, or upload a single photo. HD is the default, with 4K available for final edits.

step icon

Add the new audio

Upload an MP3 or WAV file, enter a script for AI narration, or use your cloned voice.

step icon

Choose Speed or Precision

Speed is suited to front-facing clips with a single speaker. Precision handles side profiles, multiple speakers, and hands or microphones near the mouth.

step icon

Preview and download

Check the synchronisation, adjust the timing, and export an MP4 in 16:9, 9:16, or 1:1 for social media, your LMS, or your team.

FAQs on AI lip sync

What is AI lip sync?

AI lip sync is a video technique that uses machine learning to align a speaker's mouth movements with an audio track. The model breaks the audio into phonemes, maps each sound to a mouth shape, and re-renders the face frame by frame, making new or translated speech look natural.

Is there a free AI lip sync tool I can try?

Yes. The Free plan includes 1 to 3 videos (depending on your region), each up to one minute long, with sharing at 720p resolution and a HeyGen watermark. No credit card is required. Paid plans remove the watermark, support videos of up to 30 or 60 minutes each, and offer 1080p and 4K exports.

How can I lip-sync a video with new audio or text?

Upload a video or photo, then add the new audio as an MP3 or WAV file, or type a script and select an AI voice. Choose Speed or Precision mode and generate. HeyGen re-renders the mouth movements to match the audio and provides an MP4 you can preview and download within minutes.

How is HeyGen different from other AI lip sync tools?

Many lip sync tools only match mouth movements to existing audio. HeyGen can also generate the audio from a script, your cloned voice or a translation into 175+ languages, then sync it as part of the same process. Speed and Precision modes let you choose the right balance of cost and accuracy for your footage.

Which AI tool can I use for lip-syncing?

The right lip sync AI depends on your starting material. To sync existing footage with new audio, choose a tool that redraws the speaker's mouth to match the new track and offers a higher-fidelity mode for side angles or multiple speakers; HeyGen's lip sync works this way. To animate a single photo with speech, use a photo avatar such as HeyGen's Avatar IV. If the audio also needs translation, use a video translator that recreates the speaker's voice and syncs their lip movements in the same process. Results vary depending on the camera angle, lighting and anything covering the mouth, so test a short clip of your own footage first.

Will AI lip sync look natural in my footage?

Yes, for most footage. For the cleanest results, the speaker should face the camera at an angle of no more than about 45 degrees, stand within 10 feet of it, and be evenly lit. For side profiles, changes of speaker, or hands and microphones near the mouth, use Precision mode, which is designed for these situations.

What is the difference between Speed and Precision mode?

Both use the same lip sync engine. Speed costs 6 credits per minute and works well for front-facing footage with a single speaker. Precision costs 10 credits per minute and handles side profiles, changes in camera angle, speaker changes, and objects obscuring the mouth. Start with Speed and switch to Precision if the lip sync becomes misaligned.

Does AI lip sync work in every language?

Yes. When you upload your own audio, the lip sync engine matches mouth shapes to sounds rather than words, so it works with any language, dialect or accent. If you type a script instead, AI voices support over 175 languages and dialects.

What is the maximum length of a lip-synced video, and which export options are available?

Video length depends on your plan: one minute on Free, 30 minutes on Creator and Pro, 60 minutes on Business, and 5 hours on Enterprise. Export videos as MP4 in 16:9, 9:16, or 1:1 to suit TikTok, Reels, Shorts, and YouTube, with resolutions up to 4K on Pro and higher plans. Add synchronised captions with the subtitle generator.

How does lip sync work when HeyGen translates a video?

With AI dubbing, HeyGen transcribes the speech, translates it and regenerates it in the speaker's own voice. Dynamic Duration stretches or compresses each line by up to 20% to match the original timing, then re-renders the lip movements to match the new words. Würth Group delivered a 65-minute presentation in eight languages in four days and reduced translation costs by 80%.

Can I use my own voice, and how is consent handled?

Yes. Clone your voice using a 15-second sample and use it for any script, in any language. Voice cloning requires the voice owner's consent. Uploaded footage is hosted on AWS in the US, is never shared with third-party vendors, and is covered by HeyGen's GDPR commitment and Data Processing Addendum.

Which video and audio file formats can I upload?

Videos can be in MP4, MOV or WEBM format, at least 2 seconds long and up to 5 GB in size, or shared via a YouTube or Google Drive link. Audio can be in MP3 or WAV format. You can also skip the audio file and type a script to use with an AI voice or your cloned voice.

Can I lip-sync a video with multiple speakers?

Yes. Precision mode detects changes in speakers and synchronises every visible face in the scene, not just the main speaker. It maintains synchronisation through camera angle changes, side profiles, and hands or microphones covering the mouth, keeping interviews, panel discussions, and dialogue scenes in sync.

Can I lip-sync an AI-generated clip or animated character?

Yes. A clip from Veo or another video generator is treated like any other upload. If a face is visible, HeyGen re-syncs the mouth movements with your audio. For still characters, HeyGen Video 1 animates cartoon, 3D, and stylised faces. Heavily stylised features can affect the accuracy of mouth movements, so test a short clip first.

Can I use AI lip sync to make a photo talk or sing?

Yes. Upload a portrait along with an audio file or script, and the face is animated with synchronised lip movements, head movements and expressions. Avatar 6 is optimised for real people, turning a headshot into a talking or singing video. Faces with near-human proportions produce the most accurate mouth shapes.

How long does it take to generate a lip-sync video?

Clips shorter than one minute take two to five minutes to render. Longer videos and high-resolution exports take 10 to 20 minutes. A multilingual batch with one script in ten languages takes roughly the same time as a single render plus translation.

Does HeyGen offer an API for AI lip sync?

Yes. The Lip Sync API (POST /v3/lipsyncs) accepts a video and an audio file and returns a synchronised MP4. Pay-as-you-go pricing starts at $0.84 per minute for Speed or $1.74 per minute for Precision, with no subscription required. Each batch call supports up to 100 videos.

Can I use AI lip sync videos for commercial and client projects?

Yes, with any paid plan. You can use lip-synced videos for adverts, client deliverables, paid social campaigns and published content. Avatar use is covered by the standard usage licence included with your plan, and any video using a cloned voice requires the voice owner's consent.

Can I lip-sync my own dubbed audio with a video or avatar?

Yes. Upload the dubbed MP3 or WAV as the new audio track, and HeyGen generates mouth movements from the audio itself, so a line dubbed into Spanish or Japanese syncs just as accurately as the original recording. Teams dubbing at scale can replace tracks through the Lip Sync API.

Do I need to download software or sign up?

No download is needed. HeyGen runs in your desktop browser, and a HeyGen mobile app is also available. You need a free account to save your projects, voices and avatars to your workspace.

Can I correct a single line in a video without reshooting it?

Yes. Record the corrected line, insert it into the original audio track, and upload the clip with the updated track. HeyGen re-syncs the lip movements with the revised wording, so the edit looks as though it was filmed that way.

Begin creating with HeyGen

Turn your ideas into professional videos using AI.