GIVON AI
← All models

Kling 3.0 Motion

Transfers recorded movement, dance, or gestures from a video sample to your full-body character while locking face identity and capturing complex motion. Use it when choreography fidelity and appearance consistency matter.

Cost

7 tokens/s

VideoProvider: Kling
Run generation
IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"kling-3.0-motion","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"9:16","audioEnabled":true,"referencePhoto":"asset://asset_...","motionVideo":"asset://asset_..."}}'

Input fields

* required
promptprompt

Generation prompt describing the scene, action and direction.

Type
string
Default
—
Allowed
up to 2500 chars
aspectRatioaspectRatio
Type
string
Default
9:16
Allowed
16:9, 1:1, 3:4, 4:3, 9:16
audioEnabled*audioEnabled

The model does not create new audio, but it can preserve sound from the motion video.

Type
boolean
Default
true
Allowed
boolean
Reference photo*referencePhoto

Asset input for the referencePhoto slot.

Type
string
Default
—
Allowed
image · asset, https, data
Motion video*motionVideo

Asset input for the motionVideo slot.

Type
string
Default
—
Allowed
video · asset, https, data

Cost

7 tokens/s

Capabilities

Modesvideo_edit
Asset slotsreferencePhoto:image*motionVideo:video*

Run Kling 3.0 Motion

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

Get API keyOpen in playground

Where to use this model

AI video generatorImage to video