Kling 4.0 Text to Video

Kling 4.0 turns a text prompt into a cinematic video up to 30 seconds long in 720p or 1080p, with optional multi-shot storytelling.

📄 About Kling 4.0 Text to Video

Kling 4.0 Text to Video is the newest generation of Kuaishou's Kling video model, available on JAI Portal through a simple prompt box. You describe a scene and the model renders it as a continuous, cinematic clip between 3 and 30 seconds long, in 720p or Full HD 1080p. The 30-second ceiling is twice what most previous text-to-video models allowed, so a complete product reveal, a short narrative beat or a social ad can come out of a single generation instead of several stitched clips. Kling 4.0 also supports multi-shot generation. Instead of one long prompt you can write a short list of shots - for example an establishing wide shot, a close-up and a reaction - and give each one its own duration. The model builds them into one video whose length is the sum of the shots, which makes it practical for storyboards, trailers and ad sequences where the camera needs to cut. You can choose between 16:9 widescreen, 9:16 vertical, 1:1 square and 21:9 cinematic framing, so the same idea can be produced for YouTube, Reels and TikTok, feeds, or a letterboxed film look without cropping afterwards. 720p is the economical option for drafts and iteration; 1080p is the finishing resolution for client work. On JAI Portal you pay per second of video with credits, and the exact price for your duration and resolution is shown before you generate. Failed generations are refunded automatically, and videos made with paid credits can be used commercially.

✨ Key Features

Videos from 3 to 30 seconds in a single generation

720p or Full HD 1080p output

Multi-shot mode: up to 6 shots with their own prompt and duration in one video

Four aspect ratios: 16:9, 9:16, 1:1 and 21:9

Pay-per-second pricing with the exact cost shown before you generate

💡 Use Cases

⚡Social media ads and Reels / TikTok clips in vertical 9:16

⚡Product reveals and launch teasers up to 30 seconds

⚡Storyboards and trailers built from several shots

⚡B-roll and cinematic inserts for longer edits

🎯 Best For

🎯 Marketers, filmmakers and content teams who need longer, cinematic clips from a prompt - including multi-shot sequences - without stitching several generations together.

👍 Pros

✓Up to 30 seconds per generation

✓Multi-shot prompts for scenes that need cuts

✓Full HD 1080p output

✓Four aspect ratios including 21:9 cinematic

⚠️ Considerations

△Price grows with every second, so long 1080p clips cost more

△Only 720p and 1080p are available (no 4K)

△Very long, crowded prompts can blur details - shorter shots work better

📚 How to Use Kling 4.0 Text to Video

Write a prompt describing the subject, action, setting, camera move and lighting.

Pick the duration (3-30 s), resolution and aspect ratio.

Optional: open Multi-shot and add one prompt per shot instead of a single prompt.

Check the price above the Generate button and press Generate.

Download the video or send it to an editor or upscaler.

Ready to try Kling 4.0 Text to Video?

Get 10 free credits — no credit card required

Start Free →

Frequently Asked Questions

From 3 to 30 seconds per generation. In multi-shot mode the length is the sum of your shot durations, still capped at 30 seconds.

Instead of a single prompt you list several shots, each with its own prompt and duration. Kling 4.0 renders them as one video with cuts between the shots.

16:9, 9:16, 1:1 and 21:9, in 720p or 1080p.

You pay per second of video with pay-as-you-go credits. 1080p costs about 1.5 times as much as 720p, and the exact price for your settings is shown above the Generate button before you start. Failed generations are refunded automatically.