ShengShu expands Vidu Q3 with reference-to-video and synced audio

ShengShu is expanding Vidu Q3 with a new reference-to-video capability designed to make it easier to combine characters, environments, props and visual style references inside a single video workflow. At the same time, the company is broadening both visual effects and audio generation, adding more of the creative control layer that AI video still often lacks.

According to the company, the update supports six types of cinematic effects and five categories of sound, including ambient audio, motion-driven sound and foley. Vidu Q3 can also generate up to 16 seconds of synchronized audio and video, with multi-shot composition and camera control.

That makes the launch notable because AI video is moving beyond simple clip generation and toward more controllable production. When reference handling, audio and camera movement sit in the same model, the tool becomes more useful for advertising, ecommerce, short-form series and other commercial production work.

ShengShu is also pairing the launch with a RMB 2 billion Series B led by Alibaba Cloud, giving extra weight to its ambition to build a broader world model platform.

Sources: ShengShu Technology via PR Newswire, "ShengShu Launches Vidu Q3 Reference-to-Video with Expanded Visual and Audio Capabilities," published April 13, 2026 at 09:00 ET.