Keling launched the 2.6 model for video generation. According to the introduction, the model provides a landmark “sound and video output” capability, completely changing the workflow of the traditional AI video generation model “silent image first, then artificial dubbing”. It can output a complete video including natural language, motion sound effects, and ambient sound in a single generation, restructured the AI video creation workflow, and greatly improved creative efficiency. This model has upgraded the two major functions of Wensheng Audio and Video and Tucson Audio and Video. Currently, voice generation is supported in Chinese and English, and the length of generated video can be up to 10 seconds.

Zhitongcaijing · 2d ago
Keling launched the 2.6 model for video generation. According to the introduction, the model provides a landmark “sound and video output” capability, completely changing the workflow of the traditional AI video generation model “silent image first, then artificial dubbing”. It can output a complete video including natural language, motion sound effects, and ambient sound in a single generation, restructured the AI video creation workflow, and greatly improved creative efficiency. This model has upgraded the two major functions of Wensheng Audio and Video and Tucson Audio and Video. Currently, voice generation is supported in Chinese and English, and the length of generated video can be up to 10 seconds.