Kling 3.0 Omni - GENGEN API

Kling 3.0 Omni is the multimodal Kling endpoint for text, first and last frames, reference images, elements, and reference or base video. It supports native, original, or disabled audio depending on the selected input combination, with output up to 4K. GENGEN validates incompatible media and audio combinations before the request reaches Kling.

Model ID

kling-3.0-omni

Pass this exact public ID in the top-level model field. Do not substitute an upstream provider alias.

Supported modes

omni_video
text_to_video
image_to_video
video_to_video

Inputs

Text
Image
Video

Outputs

Video
Audio

Capabilities

Text-to-video
Image-to-video
Reference-to-video
Video-to-video

Additional capabilities

Text-to-video
Image-to-video
Multi-shot generation
First-frame control
Watermark control
Last-frame control
Reference images and elements
Reference and base video
Native or original audio
4K output

Technical details

Property	Value
Provider	`kuaishou`
Modality	`video`
Processing	`Asynchronous task`
Endpoint	`/api/gengen/v1/contents/generations/tasks`
Durations	`3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15`
Resolutions	`720P, 1080P, 4K`
Aspect ratios	`16:9, 9:16, 1:1`
Audio generation	`Supported`
Watermark control	`Supported`

Availability and final customer prices can change. Check the Dashboard model catalog before production use.

See the API reference overview for authentication, request conventions, and response schemas.