Recently, an AI digital human of CCTV journalist Wang Bingbing created by SenseTime's "RuYing AI Video Generation Platform" made its debut at the "2024 China AI Summit".
AI Bingbing's performance on stage was both professional and natural, thanks to SenseTime's "RiRiXin SenseNova" large model technology, which allows her to fluently use multiple languages such as Turkish, Russian, and Spanish, showcasing the remarkable achievements of AI technology in language capabilities.
SenseTime's RuYing platform's AI video generation technology not only achieves a "hair-level" high-definition copy of Wang Bingbing but also achieves highly natural effects in expressions, mouth shapes, and actions. The multilingual capabilities demonstrated by AI Bingbing are achieved by inputting Chinese content, allowing the platform to synthesize videos in over 112 languages, achieving smooth voice and accurate mouth shape matching.
SenseTime RuYing provides powerful core technical support, including AI digital human video generation algorithms, voice large models, and AI text-to-image technology, enabling AI Bingbing to display realistic visual effects and fluent multilingual expression abilities on stage. This debut also showcases the application potential of digital humans in the media industry, which can bridge the gap between character IP and the audience.