Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://api.foxapi.cc/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kling-v3-motion-control",
  "image_url": "https://example.com/person.jpg",
  "video_url": "https://example.com/dance.mp4",
  "mode": "pro",
  "prompt": "The character follows the dance moves from the reference video, smooth and natural",
  "character_orientation": "image",
  "keep_original_sound": "no"
}
'
{
  "created": 1757165031,
  "id": "task-unified-1757165031-uyujaw3d",
  "model": "<string>",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 45
  },
  "type": "video"
}

Authorizations

​
Authorization
string
header
required

All APIs require Bearer Token authentication

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
string
default:kling-v3-motion-control
required

kling-v3-motion-control: V3 version kling-v2-6-motion-control: V2.6 version

Examples:

"kling-v3-motion-control"

"kling-v2-6-motion-control"

​
image_url
string
required

Public URL of the reference image (character appearance source)

Notes:

  • Format: JPG / PNG
  • Must be a publicly accessible URL
  • The character in the image will be animated with the motions from the reference video
  • The character should be unobstructed, and it is recommended that they occupy more than 5% of the frame area
Example:

"https://example.com/person.jpg"

​
video_url
string
required

Public URL of the reference video (motion source)

Notes:

  • Format: MP4 / MOV
  • Must be a publicly accessible URL
  • Maximum duration depends on character_orientation: image allows up to 10 seconds, video allows up to 30 seconds
  • The video should contain a full or half-body character with an unobstructed head
  • The video duration determines the output duration and billing
Example:

"https://example.com/dance.mp4"

​
mode
string
default:std

Generation mode

Available values:

  • std — Standard quality (default)
  • pro — High quality
Example:

"std"

​
prompt
string
default:""

Text prompt

Notes:

  • Optional, used to provide additional description of the desired video effect
  • Supports both Chinese and English
Example:

"The character follows the dance moves from the reference video, smooth and natural"

​
character_orientation
string
default:image

Character orientation control

Available values:

  • image — Keep the orientation from the image (default), input video max 10 seconds
  • video — Follow the orientation from the reference video, input video max 30 seconds

Do not pass this parameter unless necessary.

Example:

"image"

​
keep_original_sound
string
default:yes

Whether to keep the original audio from the reference video

Available values:

  • yes — Keep original audio (default)
  • no — Mute

Do not pass this parameter unless necessary.

Example:

"yes"

Response

Task created successfully

​
created
integer

Task creation timestamp

Example:

1757165031

​
id
string

Task ID

Example:

"task-unified-1757165031-uyujaw3d"

​
model
string

Actual model name used

​
object
enum<string>

Specific task type

Available options:
video.generation.task
​
progress
integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100
Example:

0

​
status
enum<string>

Task status

Available options:
pending,
processing,
completed,
failed
Example:

"pending"

​
task_info
object

Async task information

​
type
enum<string>

Task output type

Available options:
video
Example:

"video"