Kling 4.0
Flagship AI Video with References and Audio
Kling 4.0 creates text-to-video and image-to-video clips with native audio, and it can follow up to 7 reference images and a reference video for consistent characters and motion.
Try Kling 4.0 NowSee It In Action
Click to play with audio
More Examples
Technical Capabilities
Input Type
Text & Image-to-Video
Max Duration
15 seconds
Resolutions
720p, 1080p
Aspect Ratios
1:1, 16:9, 9:16
Native Audio
Yes
References
7 images + 1 video
Price
24 credits for a 5-second 720p clip
Key Features
Text-to-video and image-to-video in one model
Up to 7 reference images for characters, outfits, and products
Reference video to copy motion and camera moves
Native audio with every clip
720p or 1080p output
Clips from 3 to 15 seconds
How It Works
Pick a Start
Write a prompt, or upload a start image
Add References (Optional)
Add characters, products, or a motion video to guide the result
Generate
Get a 1080p video up to 15 seconds
Perfect For
Frequently Asked Questions
Related Models
VideoKling 4.0 Flash
Fast, lower-cost Kling 4.0 at 720p with reference image and video support
VideoSeedance 2.5
Newest ByteDance Seedance with native audio, references, and clips up to 30 seconds
VideoWan 3.0
Alibaba Wan 3.0 with audio, up to 10 reference images and 5 reference videos
VideoKling 3.0 Pro
Top-tier Kling 3.0 with cinematic visuals, fluid motion, native audio, and up to 15 second duration