Keling 2.6 model goes online, providing the ability to "sound and image come out together".

has launched the Video Generation 2.6 model. According to the introduction, this model provides a groundbreaking "syncing of sound and image" capability, completely changing the traditional AI video generation model that involves "silent visuals first, followed by manually adding voiceovers". The Video Generation 2.6 model is able to output complete videos in a single generation, including natural language, sound effects, and ambient sound, reconstructing the AI video creation workflow and greatly improving efficiency. This upgraded model includes two major functions: vocal generation and visual generation. Currently, the model supports generating videos in Chinese and English, with a maximum length of 10 seconds.