Alibaba has launched Wan 3.0, its latest AI video-generation model, as the Chinese technology giant expands its push into generative artificial intelligence. The new model can create videos of up to 30 seconds using text, images, audio, existing videos and documents, including PDFs, presentations and spreadsheets.
Alibaba says Wan 3.0 can generate a 30-second clip in a single pass, doubling the 15-second limit of its previous Wan 2.7 model. It supports video output of up to 1080p and is designed to maintain consistency in characters, objects, backgrounds and spatial layouts throughout a clip.
The AI model also supports synchronised facial micro-expressions and multilingual voice output. One of its key features is the ability to convert information from documents and presentations into videos, potentially making it useful for content creators, businesses and educators.
Alibaba has also adopted an aggressive pricing strategy. Wan 3.0 is priced at $0.05 per second for 480p video, $0.10 for 720p and $0.20 for 1080p. The company is positioning the model as a lower-cost alternative to several competing AI video-generation platforms.
Wan 3.0 is currently available to public beta users through Alibaba Cloud’s Model Studio and Qwen Cloud, with wider API access being rolled out. The company is also preparing a consumer-focused version through its Wan video platform.
The launch follows Alibaba’s growing investment in AI after its Qwen models reported strong results in coding, reasoning and agentic benchmarks. Wan 3.0 now extends the company’s AI strategy beyond chatbots and coding into the rapidly expanding AI video-generation market.
Leave a Reply