Kling AI launches Kling 4.0: up to 30-second video generation and MCP/CLI integration

Kuaishou's Kling AI announced on the evening of October 15 that its video generation model, Kling 4.0, is now fully available. The update increases the maximum length of a single generated video to 30 seconds, enabling long takes and continuous narrative development where emotions, actions, and camera movements evolve along a single storyline.

In terms of input control, Kling 4.0 supports combining up to 10 images, 5 videos, and 7 subjects in a single task. It also introduces prompt expansion features inspired by directorial thinking to reduce the cost of repeated debugging for creators. Additionally, the model's capabilities have been integrated with MCP (Model Context Protocol) and CLI, with API services for enterprise customers and developers expected to open soon.