W
Wan 2.2 Speech to Video
Wan 2.2 Speech to Video, a lipsync model from WaveSpeed.
lipsyncModelOverride: { model: "wan-2.2-speech-to-video" }
WWan·served viaWaveSpeed·Released August 2025
Pricing
- List price
- $0.03-$0.06/second
- Per generation
- $0.00010
Specifications
- Context window
- 2,000 tokens
- Aspect ratios
- 2
- Released
- August 2025
- Model string
- wavespeed-ai/wan-2.2/speech-to-video
Parameters
Model options, passed in
lipsyncModelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
imagePortrait to animate into a talking video. | Image URL | — | — |
audioSpeech to lip sync to, up to 10 minutes. | Audio URL | — | — |
promptOptional description of the expression and movement. | Prompt | — | — |
resolutionThe resolution of the output video. | Select | 480p | 480p720p |
seed | Seed | -1 | — |
Use this model
await mindstudio.generateLipsync({ lipsyncModelOverride: { model: "wan-2.2-speech-to-video", config: { image: "...", audio: "...", resolution: "480p", }, }, });