BREAKING
Alibaba unveils Wan-Streamer model
One Transformer listens, watches, speaks
Replacing the cascade pipeline
1VAD + ASR
2LLM
3TTS
4Video gen
0ms
Model latency
0ms
Total latency
0ms
Streaming unit
v0.2 sharpens the output
v0.1 width192
v0.2 width640
v0.2 fps25
Open weights still undecided
AI NEWS BLITZ
Alibaba's Tongyi Lab has revealed Wan-Streamer, a model generating synced speech and video.