ReferenceAsk
Back to Remy
Remy Reference/models/Seedance 2.5 Talking Avatar
W

Seedance 2.5 Talking Avatar

Seedance 2.5 Talking Avatar, a lipsync model from WaveSpeed.
lipsyncModelOverride: { model: "seedance-2.5-talking-avatar" }
ByteDance·served viaWaveSpeed·Released 2026
Pricing
List price
$0.22-$0.44/second
Per generation
$0.00010
Specifications
Context window
2,000 tokens
Aspect ratios
2
Released
2026
Model string
bytedance/seedance-2.5/talking-avatar
Parameters
Model options, passed in lipsyncModelOverride.config.
ParameterTypeDefaultRange / options
image
Portrait to animate into a talking video.
Image URL——
audio
Speech to lip sync to. Only the first 120 seconds are used.
Audio URL——
prompt
Optional description of the expression and movement.
Prompt——
resolution
The resolution of the output video.
Select720p480p720p
Use this model
await mindstudio.generateLipsync({
  lipsyncModelOverride: {
    model: "seedance-2.5-talking-avatar",
    config: {
      image: "...",
      audio: "...",
      resolution: "720p",
    },
  },
});