Kling launched Kling 2.6 with native audio generation, producing synchronized visuals and sound in a single pass.
Key Details
Native audio integration - The model generates natural voice, action sound effects, and environmental ambience synchronized to visual motion, eliminating the separate audio-layering step most AI video tools still require.
Text-to-video and image-to-video support - Both input modes can produce complete audiovisual outputs, turning text prompts or static images into videos with dialogue, ambient sound, and effects audio matched to on-screen action.
Vocal and scene-aware sound - Kling 2.6 handles speaking, dialogue, narration, singing, rap, multi-character conversations, and environmental sounds like ASMR textures, composite scene audio, and action effects with timing designed to match visual rhythm.
