Kling AI releases version 4.0 with stereo audio and a Flash variant
Original title: Kling AI drops version 4.0 with stereo audio, multilingual lip sync, and a lighter Flash variant
Clips can run 30 seconds from up to ten keyframes; Flash is limited to 720p and 20 seconds.
Kling AI released video model version 4.0 with higher resolution, tighter controls, two-channel stereo audio, and lip sync across more than ten languages. A single pass can generate up to 30 seconds from as many as ten keyframe images, with prompts up to 8,000 tokens and an Omni Reference system that accepts up to 15 assets. A lighter Kling 4.0 Flash variant targets faster, cheaper output at up to 720p and 20 seconds. Access via MCP and CLI is available; API pricing and 4K HDR plus two-minute extension are listed as coming soon. The Decoder's comparison with Wan 3.0 and Seedance 2.5 did not show Kling clearly ahead.
Unconfirmed: Quality and gap-closing claims are Kling AI's; API pricing and the HDR and extension features are not yet available.
- Omni Reference accepts up to 10 images, 5 videos totaling 30 seconds, and 7 elements.
- Creative Recreation can swap products or characters in an existing video template.
- Lip sync covers German, English, Japanese, Korean, Spanish, and dialects.
- 10-bit HDR at 4K and 1080p, and extension to two minutes, are coming soon.
- API support is listed as coming soon, with pricing not announced.
- Vendors
- Kling AI
- AI models
- Kling 4.0Kling 4.0 Flash
From the original article
2 min read at the-decoder.com
Kling AI has released version 4. 0 of its video generator with support for clips up to 30 seconds, ten keyframe images as input, and prompt comprehension expanded to 8,000 tokens. In comparisons with Wan 3.
By Matthias Bastian · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.