BytedanceVideo

Latentsync

Bytedance LatentSync combines Stable Diffusion and TREPA for high-res end-to-end lip-sync, delivering precise, realistic mouth motions in generated videos.

Talking avatarsRealistic video

Type: digital-human
Output: Video
Input: Image, Audio
from: €0.30 per render

Examples

Specs

Typedigital-human

OutputVideo

InputImage, Audio

Model IDbytedance/latentsync

Similar models

All models →

BytedanceSeedance 2.5 Talking Avatar€2.20per render HeygenAvatar V Digital Twin€0.24per render HeygenAvatar V€0.30per render HeygenAvatar Iv€0.20per render Pruna AiP Video Avatar€0.05per render SyncLipsync 3 Avatar€0.27per render

Prices are per render and charged from your balance only when a render succeeds. Failed renders are refunded automatically. Examples show what the model can do; your result depends on your prompt and settings.