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": "vidu-q3-pro",
  "prompt": "A cinematic street food scene at night, sizzling skewers, neon reflections on wet pavement, handheld motion",
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "generate_audio": true
}
'
{
  "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 endpoints require Bearer Token authentication

Add the following to your request headers:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
string
default:vidu-q3-pro
required

vidu-q3-pro: Standard version, supports text-to-video, image-to-video, first-last-frame transition, and reference-to-video vidu-q3-turbo: Accelerated version, supports text-to-video, image-to-video, and first-last-frame transition, does not support reference-to-video

Examples:

"vidu-q3-pro"

"vidu-q3-turbo"

​
generation_type
enum<string> | null

Generation mode

Options:

  • text-to-video — Generate video from text only, do not pass image_urls
  • image-to-video — Single image to video, image_urls must contain exactly 1 image
  • first-last-frame — First-last frame transition video, image_urls must contain exactly 2 images
  • reference-to-video — Reference image to video, image_urls can contain 1-4 images

Notes:

  • If not specified, it will be automatically inferred based on input: 0 images → text-to-video, 1 image → image-to-video, 2 images → first-last-frame, 3-4 images → reference-to-video
  • vidu-q3-turbo does not support reference-to-video
Available options:
text-to-video,
image-to-video,
first-last-frame,
reference-to-video
Example:

"text-to-video"

​
prompt
string | null

Text prompt describing the desired video content

Notes:

  • Required for text-to-video and reference-to-video
  • Optional for image-to-video and first-last-frame, if not provided, generation is primarily driven by the input images
  • Supports both Chinese and English
Maximum string length: 2000
Example:

"A cinematic tracking shot through a rainy cyberpunk alley"

​
image_urls
string[] | null

List of image URLs, the number of images depends on generation_type

Notes:

  • text-to-video: Do not pass
  • image-to-video: Exactly 1 image
  • first-last-frame: Exactly 2 images, in the order of first frame, last frame
  • reference-to-video: 1-4 images
  • Image URLs must be publicly accessible
Example:
["https://picsum.photos/id/237/1280/720.jpg"]
​
duration
integer
default:5

Output video duration (seconds)

Notes:

  • Defaults to 5 seconds
  • Must be a positive integer
Required range: x >= 1
Example:

5

​
aspect_ratio
enum<string>
default:16:9

Output video aspect ratio

Options:

  • 16:9 — Landscape (default)
  • 9:16 — Portrait
  • 4:3 — Traditional landscape
  • 3:4 — Traditional portrait
  • 1:1 — Square
Available options:
16:9,
9:16,
4:3,
3:4,
1:1
Example:

"16:9"

​
resolution
enum<string>
default:720p

Output video resolution

Options:

  • 360p — Low resolution
  • 540p — Medium-low resolution
  • 720p — HD (default)
  • 1080p — Full HD

Notes:

  • first-last-frame does not support 360p
Available options:
360p,
540p,
720p,
1080p
Example:

"540p"

​
generate_audio
boolean
default:true

Whether to generate accompanying audio

Notes:

  • Enabled by default
  • Set to false to generate video only without sound
Example:

true

​
seed
integer | null

Random seed for improving result reproducibility

Not recommended unless specifically needed.

Required range: 0 <= x <= 2147483647
Example:

42

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 type of the task

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>

Output type of the task

Available options:
video
Example:

"video"