Kling 4.0 is now available on Higgsfield AI with longer generations, expanded reference support, and more control over each scene. Create videos from 3 to 30 seconds at up to 1080p with stereo audio. Use up to 10 keyframes to control key moments in a video, or combine up to 15 references to guide the scene. This guide explains its features, settings, workflow, and credit pricing.
What Is Kling 4.0?
Kling 4.0 is Kling’s latest video model, built for realistic motion, stable camera movement, and improved visual and audio quality. It handles fast action such as fights, sports, and large-scale scenes, and it keeps characters recognizable across scenes and variations. Higgsfield is an AI-native creative suite with 35+ models and tools, and Kling 4.0 is available there alongside Kling 3.0 and other video models.
Setting | Kling 4.0 on Higgsfield |
|---|---|
Modes | Text-to-video, image-to-video, first and last frames, multi-keyframes, Omni Reference, video editing |
Duration | 3 to 30 seconds |
Resolution | 720p and 1080p |
Aspect ratio | Auto, 21:9, 16:9, 9:16, and 1:1 |
Keyframes | Up to 10 |
Audio | Stereo, with two channels |
Voice languages | Chinese, English, Japanese, Korean, Spanish, Portuguese, German, French, Hindi, and others |
Accents and dialects | American, British, Indian, and other English accents; several Chinese dialects |
On-screen text | Nine languages, plus emoji and logos |
Prompt length | Up to 8,000 tokens |
References | Up to 15 |
Video editing input | Up to 5 clips (1 main), each 3 to 30 seconds, with a combined length of up to 30 seconds |






