Kling AI launches version 4.0 with stereo audio and multilingual lip sync
In brief
- Clips up to 30 seconds with 10 keyframe images as input.
- Prompt comprehension extended to 8,000 tokens.
- Stereo audio and multilingual lip sync features included.
Kling AI releases version 4.0 of its video generator, supporting clips up to 30 seconds and 10 keyframe images as input. Prompt comprehension reaches 8,000 tokens, though performance does not outpace competitors like Wan 3.0 or Seedance 2.5.
What it changes for you
- Media & EntertainmentContent creators can produce longer, better-synchronized videos, reducing post-production costs.
This summary gives you the essentials. The full article, its figures and quotes are on The Decoder.
Read the original articleAI-generated summary of the source, checked by rules. Report an error