Alibaba research model for real-time conversational avatars using one transformer over text, audio and video.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Wan Streamer (also referred to as One Streamer) is an Alibaba research project in the Wan family that generates real-time conversational avatars. According to creator coverage, a single transformer interleaves text, audio and video streams, and the system communicates in duplex, so it can listen and respond at the same time.
The first version (v0.1) was described as a 192p proof of concept running at about 25 fps with roughly 200 ms latency. It was released as a paper only, with no code. The project website is a version router that redirects to the latest release, listed as Wan Streamer v0.3, titled "Video = World + Event Stream".
No public weights, code repository, pricing or product access were found in the provided material. It appears to be a research demonstration rather than a generally available product, and details beyond the version page are not confirmed here.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Real-time conversational avatar handled by a single transformer interleaving text, audio and video. Runs at 25 fps with ~200 ms latency and duplex communication; v0.1 is 192p proof of concept, paper only, no code.
Closest neighbours by meaning, not just by category.
Model · Alibaba
Alibaba's real-time audio-visual interactive character video model that renders speech and free-form actions.
Model
Research model for real-time, talking video agents with a single streaming Transformer; 640×368 output at ~200 ms latency.
Model · Alibaba
Alibaba research model for real-time, long-horizon streaming character audio-video generation.
Model · Alibaba
Alibaba's Wan video generation model, reported to produce clips up to about 30 seconds, available via the Wan platform.
Model · Alibaba
Alibaba's diffusion-transformer model that animates a character image from a driving video, with a real-time Lite variant.
Model
Research model for real-time, audio-driven talking-head video generation from a reference image, using one-step inference.
