ShengShu Technology Lays Foundation for Scalable AI Video Generation with Launch of Vidu API Offering Instant Access and Industry-leading Speed for Enterprises & Developers

ShengShu Technology, a world pioneer in generative AI video, announces the API platform for its flagship video generation application, Vidu, marking a major advancement in scalable, seamless, and accessible AI video generation.

Vidu stands out with its groundbreaking U-ViT architecture and industry-first innovations, such as the ability to generate a clip in under ten seconds and Multiple-Entity Consistency—ensuring unmatched speed and high-quality AI video generation. Starting today, developers and enterprise partners can seamlessly integrate Vidu’s advanced multimodal tech stack, enabling their users to access high-quality AI-generated videos for film editing, mobile ads, social media visuals, and more.

Vidu’s API paves the way for widespread adoption. By making its technology accessible, Vidu empowers both startups and established enterprises to build AI-powered video applications without requiring vast financial resources. As AI drives a new digital gold rush, reminiscent of the early 2000s, businesses of all sizes are racing to integrate AI in transformative ways that will redefine industries and reshape operations.

Vidu API’s Comprehensive Model Support and Capabilities

Designed to support diverse needs from developers and enterprises, the Vidu API platform is powered by the latest version of Vidu 2.0 and offers a suite of advanced video generation tools to simplify video creation at scale. This means that Reference-to-Video, Image-to-Video and Text-to-Video features are all available in the latest API platform. Be it characters, objects or environments, related or not, different features work together to transform static images and text descriptions into cohesive and dynamic videos while maintaining subject consistency across multiple perspectives. Core to this capability is Vidu’s advanced semantic understanding and the Multiple-Entity Consistency feature that was first introduced in Vidu 1.5.

Furthermore, the Template feature offers a series of customisable pre-set prompt templates tailored to the needs of various industries, allowing developers to integrate and debug for different scenarios, such as hug, kiss, and Valentine’s Day-related templates. Each template is meticulously optimised for highly stable generation results, effectively eliminating prompt complexity. The Template feature enables small enterprises to automate video creation for various purposes, including personalised marketing campaigns, customer support videos, and product showcases.

Instant Access with No Application, Starting at Just $10

Vidu API is designed to offer immediate and frictionless adoption for smaller businesses and independent developers. Removing approval processes and restrictions on API access commonly seen in other platforms, Vidu API is made fully open for developers and businesses with no application required. Individual developers can instantly purchase API access with pricing starting at $10 without a high-tier subscription. Base pricing is $0.05 per credit (A four-second video costs 4 to 40 credits depending on applied aspect ratio and feature type).

The platform also dedicates a B2B service team to provide hands-on support for businesses integrating Vidu into their workflows.

The launch of the Vidu API platform aligns with a broader shift in AI-driven content creation. With efficiency breakthroughs in latest AI models, the AI boom will not only transform tech companies, but also become a more commonplace in marketing, customer experience and enterprise use across retail, education, e-commerce among other industries. As AI-driven content becomes more ubiquitous, businesses increasingly recognise video as a missing piece to keep up with content demands, and Vidu API will serve as a critical content automation tool to fill in the gaps.