Skip to main content
Kling 3.0 generates cinematic video from text or a source image, with native audio, multi-shot storytelling, and quality variants for different production needs. Default endpoint: POST https://api.higgsfield.ai/kling-video/v3.0/std/text-to-video Endpoint ID: kling-video/v3.0/std/text-to-video Try Kling 3.0Open Kling 3.0 in the Higgsfield Playground and generate a video interactively.

Available endpoints

Text to video

Image to video

Turbo

4K

Highlights

  • Generate from a prompt alone or animate a source frame.
  • Produce synchronized dialogue, ambience, and sound effects where enabled.
  • Use multi-shot prompting for connected scenes in a single generation.
  • Select Standard, Pro, Turbo, or 4K based on quality and latency requirements.