跳转到主要内容
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": "creatify-aurora",
  "image_url": "https://example.com/portrait.png",
  "audio_url": "https://example.com/speech.wav",
  "resolution": "720p"
}
'
{
  "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"
}

Documentation Index

Fetch the complete documentation index at: https://docs.foxapi.cc/llms.txt

Use this file to discover all available pages before exploring further.

授权

​
Authorization
string
header
必填

All endpoints require Bearer Token authentication

Add the following to your request headers:

Authorization: Bearer YOUR_API_KEY

请求体

application/json
​
model
string
默认值:creatify-aurora
必填

creatify-aurora: High-fidelity talking-head digital human video

示例:

"creatify-aurora"

​
image_url
string
必填

Public URL of the portrait image

Notes:

  • Must be a publicly accessible URL
  • A clear, front-facing, single-person portrait is recommended
示例:

"https://example.com/portrait.png"

​
audio_url
string
必填

Public URL of the driving audio

Notes:

  • Must be a publicly accessible URL
  • Maximum input audio length: 60 seconds
  • Output video duration follows audio length, up to approximately 60 seconds
示例:

"https://example.com/speech.wav"

​
prompt
string | null

Text prompt for controlling visual style and character performance

Notes:

  • Suitable for specifying camera angles, expressions, lighting, and scene style
  • When omitted, the model uses its default behavior
示例:

"4K studio interview, steady eye contact, ultra sharp."

​
guidance_scale
number | null
默认值:1

Text prompt adherence strength

Notes:

  • Range: 0 - 5
  • Higher values follow the prompt more strictly

Do not pass this parameter unless necessary.

必填范围: 0 <= x <= 5
示例:

1

​
audio_guidance_scale
number | null
默认值:2

Audio adherence strength

Notes:

  • Range: 0 - 5
  • Higher values follow the input audio rhythm more strictly

Do not pass this parameter unless necessary.

必填范围: 0 <= x <= 5
示例:

2

​
resolution
string | null
默认值:720p

Output video resolution

Options:

  • 480p
  • 720p
示例:

"720p"

响应

Task created successfully

​
created
integer

Task creation timestamp

示例:

1757165031

​
id
string

Task ID

示例:

"task-unified-1757165031-uyujaw3d"

​
model
string

Actual model name used

​
object
enum<string>

Specific task type

可用选项:
video.generation.task
​
progress
integer

Task progress percentage (0-100)

必填范围: 0 <= x <= 100
示例:

0

​
status
enum<string>

Task status

可用选项:
pending,
processing,
completed,
failed
示例:

"pending"

​
task_info
object

Asynchronous task information

​
type
enum<string>

Task output type

可用选项:
video
示例:

"video"