Singapore – – October 07, 2026 -- Shengshu Technology's Vidu has launched Q4 Preview, a public preview of its next-generation flagship AI video and audio generation model, with launch pricing starting at $0.014 per second.
Launch pricing cuts costs to expand flagship video generation to independent creators
Vidu Q4 Preview enables up to five times more output for the same budget compared to prior comparable output specifications and billing conditions, the company said. Output resolutions span 540p, 720p, 1080p, 2K and 4K, with 10-bit color depth available at the higher tiers.
Model supports 15 image references and 3 audio clips for character consistency
The system accepts up to 15 image references to define characters, wardrobe, props, products and environments within a single creative setup, alongside up to 3 reference audio clips to maintain voice consistency and emotional delivery across a scene. Shengshu Technology positions the tool for independent creators, small studios and production teams working on narrative and commercial projects.
CEO says efficiency gains should let creators attempt more shot versions
"Advanced video models should prove themselves beyond carefully selected demos. Every improvement in efficiency should ultimately give creators the freedom to try one more shot or make one more version,