---
title: Wan2.2-S2V
emoji: 🗣️
colorFrom: indigo
colorTo: blue
sdk: static
pinned: false
license: apache-2.0
short_description: Reference for Wan2.2-S2V, audio-driven video generation
---

# Wan2.2-S2V

A reference page for **Wan2.2-S2V**, the speech-to-video checkpoint in Alibaba Tongyi
Lab's Wan 2.2 family. It animates a single reference image from an audio track, driving
lip sync, head motion and gesture together.

- Weights: [Wan-AI/Wan2.2-S2V-14B](https://huggingface.co/Wan-AI/Wan2.2-S2V-14B)
- Code: [Wan-Video/Wan2.2](https://github.com/Wan-Video/Wan2.2)
- Hosted inference: [wan-2.2/speech-to-video](https://wavespeed.ai/models/wavespeed-ai/wan-2.2/speech-to-video)

Wan2.2-S2V is developed and released by Alibaba Tongyi Lab. This Space is maintained by
WaveSpeed AI, which provides hosted inference for the model.