Kling 3.0 Omni

Multi-scene video with native audio: transfers a character's appearance and voice from a video sample into new scenes, though audio must be disabled when that video sample is used. Use it for coherent narratives with one hero.

Cost

from 6.4 tokens/s

VideoProvider: Kling
Run generation
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"kling-3.0-omni","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"9:16","resolution":"720p","duration":3,"audioEnabled":true,"referenceAssetUris":["asset://asset_..."]}}'

Input fields

* required
prompt*prompt

Scene / motion description.

Type
string
Default
Allowed
up to 2500 chars
aspectRatioaspectRatio
Type
string
Default
9:16
Allowed
9:16, 16:9, 1:1
resolutionresolution
Type
string
Default
720p
Allowed
720p, 1080p
durationduration
Type
number
Default
3
Allowed
from 3 · up to 15 · step 1 seconds
audioEnabledaudioEnabled

Omni can generate native audio without a video reference; turn audio off when using a video reference.

Type
boolean
Default
true
Allowed
boolean
Reference videoreferenceVideo

Asset input for the referenceVideo slot.

Type
string
Default
Allowed
video · asset, https, data
Reference imagesreferenceAssetUris

Optional reference assets as asset:// URIs, HTTPS URLs, or data URIs.

Type
array
Default
Allowed
image · up to 7 · asset, https, data

Cost

from 6.4 tokens/s
720pdefault6.4 tokens/s
720p · Audio9 tokens/s
1080p9 tokens/s
1080p · Audio12 tokens/s

The variant is selected automatically from request fields, so you do not need to send it.

Capabilities

Modestext_to_videoimage_to_videovideo_to_videoreference_to_video
Asset slotsreferenceVideo:videoreferenceAssetUris:image[]<=7

Run Kling 3.0 Omni

Get an API key and the same request shape will work across every model in the catalog.

Kling 3.0 Omni API - video generation · Givon AI