Kling AI releases version 4.0 with stereo audio, multilingual lip sync, and Flash variant

What happened

Kling AI has released version 4.0 with video generation up to 30 seconds, up to ten keyframe inputs, and prompt comprehension expanded to 8,000 tokens. According to the company, the update adds stereo audio and improved lip sync across more than ten languages, while Kling 4.0 Flash offers faster generation at lower cost with limits of 720p and 20 seconds. MCP and CLI access are available; API support, 10-bit HDR output, and video extension up to two minutes are listed as coming soon.

Reported by 2 sources

The story so far

Kling AI has released Kling 4.0 with video generation up to 30 seconds and a Flash variant, while API access and video extensions up to two minutes remain forthcoming. The model supports up to 15 combined reference assets, up to 10 keyframe inputs, and prompts of up to 8,000 tokens. MCP and CLI integration lets creators use AI agents to invoke reference-based and keyframe-based video generation. Kling AI said the update adds stereo audio, improves lip sync across more than ten languages, and improves handling of fast motion and complex camera movements. The company describes Kling 4.0 Flash as faster and lower-cost, with output limited to 720p and 20 seconds. Reports differ on HDR availability: Leiphone reported 10-bit HDR output as a launch feature, while The Decoder reported that Kling AI lists 10-bit HDR output at 4K and 1080p as “coming soon.” API access for enterprise customers and developers is also planned.

Keep reading