Publisher
ByteDance
ByteDanceTypeLip Sync
Context Window2,000 tokens
ReleasedOctober 2026
Price$0.10/second
Provider
WaveSpeed
WaveSpeedReady to build with OmniHuman 2.0?
Get Started FreeConfiguration
Parameters & options
ImageImage URL
Portrait to animate into a talking video.
AudioAudio URL
The speech that drives the video. Only its first 300 seconds are used.
PromptPrompt
Optional directions for motion and style.
Related models
Explore similar models
ByteDanceOmni Human 1.5
Omni Human 1.5 is a lip sync model from ByteDance that animates a portrait image using an audio input.
ByteDanceSeedance 2.5 Talking Avatar
ByteDanceLatentSync
LatentSync is a lip sync model from ByteDance that synchronizes video facial movements to a provided audio track.
MiniMaxMiniMax H3 Max Lip Sync
LightricksLTX-2.3 Lipsync
SyncSync Lipsync 3
WanWan 2.2 Speech to Video
Start building with OmniHuman 2.0
No API keys required. Create AI-powered workflows with OmniHuman 2.0 in minutes — free.