Kling 2.6 Model Unveils 'Synchronized Audio-Visual Output' Feature
2025-12-04 / Read about 0 minute
Author:小编   

On December 3, Kling rolled out its video generation 2.6 model, which boasts the remarkable capability of 'synchronized audio-visual output'. This innovative model can craft a complete video in one go, seamlessly integrating natural language, action sound effects, and ambient sounds. By doing so, it not only reshapes the AI video creation landscape but also substantially boosts creative productivity. The upgrade focuses on enhancing two primary functions: converting text to audio-visual content and transforming images into audio-visual experiences. The model supports both Chinese and English voices, and is capable of generating videos that are up to 10 seconds in length.