Lipsync
Models that sync a face in a video to a track of speech.
The lipsync models that drive a face to match a voice track. Each entry shows its price and the inputs it takes, typically an image or clip and an audio track. Use one to make a portrait or a video speak a given line.
8 models
AI Avatar StandardLipsyncKling· via
WaveSpeed
WaveSpeed$0.28+/ s (dynamic)
August 2025
Released
50K tok
Context
HeyGen Video TranslateLipsyncHeyGen· viaWaveSpeed
WaveSpeed$0.0375/ s
September 2023
Released
50K tok
Context
InfiniteTalkLipsyncWaveSpeed
$0.15+ per 5 sec
2025
Released
LatentSyncLipsyncByteDance· viaWaveSpeed
WaveSpeed$0.15+
August 2025
Released
50K tok
Context
LTX-2 19B LipsyncLipsyncWaveSpeed
$0.15+
January 2026
Released
Omni Human 1.5LipsyncByteDance· viaWaveSpeed
WaveSpeed$0.25/ s
September 2025
Released
50K tok
Context
Sync Lipsync 2 ProLipsyncSync· viaWaveSpeed
WaveSpeed$0.08/ s
2025
Released
Sync Lipsync 3LipsyncSync· viaWaveSpeed
WaveSpeed$0.135/ s
2026
Released