Tongyi Lab releases Wan-Streamer v0.2 with 550ms end-to-end response latency
Original title:Wan-Streamer v0.2:响应延迟仅550ms,让 AI 真正与你"面对面"
AI summary
Tongyi Lab has released Wan-Streamer v0.2, an end-to-end omni-modal model that unifies listening, seeing, speaking, and acting into a single Transformer. Its end-to-end response latency is only 550ms, and output resolution has increased from 192×336 in v0.1 to 640×368 @ 25FPS. It uses a Thinker-Performer dual-path architecture to improve image quality while maintaining extremely low latency.
Key Takeaways
- Tongyi Lab has released Wan-Streamer v0.
- 2,an end-to-end omni-modal model that unifies listening,seeing,speaking,and acting into a single…
- Its end-to-end response latency is only 550ms,and output resolution has increased from 192×336 in…
- 1 to 640×368 @ 25FPS.
- It uses a Thinker-Performer dual-path architecture to improve image quality while maintaining…
Quick Facts
- Published
- Updated
- Source
- 公众号:通义实验室(千问)
- Category
- Model Releases
- AI score
- 69
通义实验室把实时视频交互延迟压到550ms,同时提升了分辨率,不是刷榜而是解决实际问题,对做数字人和实时助手的团队是个值得跟进的信号。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Tongyi Lab releases Wan-Streamer v0.2 with 550ms end-to-end response latency. July 17, 2026. https://new.nat6.net/en/news/cmrolz26304oqbito42v7oeaz/