Manage All Models
1,000 
bonus on first purchase of $100 or more
Lipsync Re-sync any video's mouth to any audio with AI
AI Model
Each model has different source-video rules. HeyGen Precision and Sync require a speaking face; Kling is limited to 2–10s 720p–1080p. Check the description on the option you pick.
MuseTalk
4 /s
/s
LatentSync
5 /s
/s
Kling Lip Sync
6 /s
/s
HeyGen Lipsync Speed
7 /s
/s
PixVerse Lipsync
8 /s
/s
Sync Lipsync 2
10 /s
/s
HeyGen Lipsync Precision
13 /s
/s
Video ReTalking
16 /s
/s
Sync Lipsync 2 Pro
17 /s
/s
Source Video *
Use a clip where the person is already talking, face-on, mouth visible. Sync Lipsync 2 and Pro cannot open a shut mouth or still face — they only retarget existing speech. For a still portrait, use the Talking Head generator instead.
Choose File
No file chosen
— OR —
Audio Track *
Upload the speech or vocal track to drive the lip motion. Best with clean, dry audio.
Choose File
No file chosen
— OR —
Active Speaker Detection
Used by Sync Lipsync 2 and Pro to identify which face is speaking.
Match Audio Length
Used by HeyGen Lipsync Speed and Precision.
Remove Background Music
Used by HeyGen Lipsync Speed and Precision.
Enhance Speech
Used by HeyGen Lipsync Speed and Precision.
Privacy Mode
Output Language
Auto (Input Language)
English (United States)
Spanish (Spain)
French (France)
German (Germany)
Italian (Italy)
Portuguese (Brazil)
Arabic (Generic)
Bengali (India)
Bulgarian (Bulgaria)
Croatian (Croatia)
Czech (Czech Republic)
Danish (Denmark)
Dutch (Belgium)
Dutch (Netherlands)
Estonian (Estonia)
Finnish (Finland)
Greek (Greece)
Gujarati (India)
Hebrew (Israel)
Hindi (India)
Hungarian (Hungary)
Indonesian (Indonesia)
Japanese (Japan)
Kannada (India)
Korean (South Korea)
Latvian (Latvia)
Lithuanian (Lithuania)
Malayalam (India)
Mandarin Chinese (China)
Marathi (India)
Norwegian Bokmål (Norway)
Polish (Poland)
Romanian (Romania)
Russian (Russia)
Serbian (Cyrillic)
Slovak (Slovakia)
Slovenian (Slovenia)
Swahili (Kenya)
Swedish (Sweden)
Tamil (India)
Telugu (India)
Thai (Thailand)
Turkish (Turkey)
Ukrainian (Ukraine)
Urdu (India)
Vietnamese (Vietnam)
FREE AI Lipsync Generator
Take an existing video clip of a person and a separate audio track, and generate a new video where their mouth moves in sync with the audio. Perfect for dubbing, language localization, character voiceovers, and editing accurate dialogue into existing footage.
Perfect For
Content creators dubbing videos into new languages, marketers localizing brand campaigns, educators producing multi-language course material, indie filmmakers editing dialogue without reshoots, podcasters turning audio into talking-head video, and anyone who wants to put new words in an existing speaker's mouth.
Key Features
Three production-grade lipsync engines (PixVerse, Sync Lipsync 2, Sync Lipsync 2 Pro) at different price points, supports any video clip with a clearly visible face, accepts MP3/WAV/M4A audio, multiple sync modes (cut off, loop, bounce, silence, remap) for handling clips of mismatched length, optional active-speaker detection for multi-person scenes, and adjustable expressiveness for natural-looking results.
