Shengshu Technology releases Vidu S1, pushing video generation into a new era of real-time interaction
AI summary
On July 3, Shengshu Technology released the Vidu S1 real-time interaction model at the 2026 Global Digital Economy Conference. It supports real-time video calls and voice-controlled video direction, enabling unlimited continuous interaction. The model uses an autoregressive diffusion approach, continuously predicting subsequent content based on generated frames and voice instructions. It requires no traditional modeling: a single image can create a character with a customizable voice. Vidu S1 achieves real-time generation at 25 FPS (up to 42 FPS) at 540P resolution, reduces computing costs through technologies such as TurboDiffusion, and has entered internal testing.
Key Takeaways
- On July 3,Shengshu Technology released the Vidu S1 real-time interaction model at the 2026 Global…
- It supports real-time video calls and voice-controlled video direction,enabling unlimited…
- The model uses an autoregressive diffusion approach,continuously predicting subsequent content…
- It requires no traditional modeling: a single image can create a character with a customizable…
- Vidu S1 achieves real-time generation at 25 FPS (up to 42 FPS) at 540P resolution,reduces…
Quick Facts
- Published
- Updated
- Source
- 公众号:生数科技(Vidu·视频)
- Category
- Model Releases
- AI score
- 70
Vidu S1 把视频生成从离线拉到了实时通话级交互,语音控制无限时长是质变,但只有540P,内测阶段实际延迟和稳定性待看,做虚拟陪伴和直播的可以跟。
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: Shengshu Technology releases Vidu S1, pushing video generation into a new era of real-time interaction. July 3, 2026. https://new.nat6.net/en/news/cmr53vzsc07l3sll5x8mfscz3/