Vidu

Vidu is a generative AI platform developed by ShengShu Technology, specializing in AI video generation. Its current Vidu Q3 model supports text-to-video, image-to-video and reference-to-video generation, with clips up to 16 seconds and native audio including dialogue, voiceovers, sound effects and music. Vidu also offers image generation, AI sound effects, templates, lip-sync, motion synchronization, video extension, upscaling and the Vidu S1 real-time digital-character system. Its reference-to-video technology is designed to maintain subject, character and style consistency across generated scenes. A public API allows developers to integrate Vidu into applications and commercial workflows. Vidu launched globally in 2024 and is currently active. The company states that its platform has reached 200+ countries and regions, so there is no general country restriction identified; however, individual services and features can vary according to country, regulations and platform availability.