POST
https://octopusx.ai
/
v1
/
video
/
create
Create Video
curl --request POST \
  --url https://octopusx.ai/v1/video/create \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "images": [
    {}
  ],
  "prompt": "<string>",
  "aspect_ratio": "<string>",
  "audio": true,
  "voice_id": "<string>",
  "is_rec": true,
  "bgm": true,
  "duration": 123,
  "seed": 123,
  "resolution": "<string>",
  "payload": "<string>",
  "off_peak": true,
  "watermark": true,
  "wm_position": 123,
  "wm_url": "<string>",
  "meta_data": "<string>"
}
'
{
  "created_at": "2025-11-08T23:07:57.510141923+08:00",
  "status": "processing",
  "task_id": "48038932-0ff5-4251-8b4b-7a76c09fd114"
}

​
Create Video

The Vidu unified video entry uses POST /v1/video/create, and the request body is JSON. Unlike the official Vidu format, this endpoint uses fields such as images, aspect_ratio, resolution, and duration.
  • The route endpoint is POST /v1/video/create.
  • Reference images are passed as a URL list through the images array; text-to-video can pass an empty array.
  • A common model example is viduq3-pro; use the actually available model for the current channel as the reference.
  • After a successful submission, the task id and status are returned, and you can later use Query Task to poll for results.

​
Supported Models

  • viduq3-pro: Efficiently generates high-quality audio and video content, making video content more vivid, more lifelike, and more three-dimensional
  • viduq2-pro-fast: Lower price floor, stable results, generation speed 2-3 times faster than viduq2-turbo
  • viduq2-pro: New model, good results, rich details
  • viduq2-turbo: New model, good results, fast generation
  • viduq1: Clear visuals, smooth transitions, stable camera movement
  • viduq1-classic: Clear visuals, richer transitions and camera movement
  • vidu2.0: Fast generation speed

​
Method and Path

POST /v1/video/create

​
Request Example

curl -X POST https://octopusx.ai/v1/video/create \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq3-pro",
    "prompt": "一只猫在草地上追逐蝴蝶",
    "aspect_ratio": "16:9",
    "duration": 5,
    "audio": false,
    "images": []
  }'

​
Response Example

{
  "created_at": "2025-11-08T23:07:57.510141923+08:00",
  "status": "processing",
  "task_id": "48038932-0ff5-4251-8b4b-7a76c09fd114"
}

​
Authentication

Authorization: Bearer YOUR_API_KEY

​
Body

​
model
string
required
Model name. Supports viduq3-pro, viduq2-pro-fast, viduq2-pro, viduq2-turbo, viduq1, viduq1-classic, and vidu2.0.
​
images
array
required
Image array. Supports passing image Base64-encoded data or image URLs (ensure they are accessible). For text-to-video, pass an empty array []; for image-to-video, pass 1 image; for first-and-last-frame video generation, pass 2 images. Supported image formats are png, jpeg, jpg, and webp. The aspect ratio must be less than 1:4 or greater than 4:1, and the size must not exceed 50 MB.
​
prompt
string
Text prompt. The text description for the generated video, with a maximum length of 2000 characters. If you use the is_rec recommended prompt parameter, the model will ignore the prompt input in this parameter.
​
aspect_ratio
string
Aspect ratio. Default is 16:9. Optional values: 16:9, 9:16, 3:4, 4:3, 1:1. Note: 3:4 and 4:3 are supported only by q2 and q3 models.
​
audio
boolean
Whether to use direct audio-video output capability. Default is false. false: audio-video direct output is not needed, and a silent video is output; true: audio-video direct output is needed, and a video with dialogue and background sound is output.
​
voice_id
string
Voice ID. Does not take effect for q3 models. Used to determine the voice timbre in the video; if empty, the system will recommend one automatically.
​
is_rec
boolean
Whether to use recommended prompts. true: yes, the system automatically recommends prompts and generates the video using the prompt content, with the number of recommended prompts = 1; false: no, generate the video based on the input prompt.
​
bgm
boolean
Whether to add background music to the generated video. Default is false. true: the system will automatically select suitable music from the preset BGM library and add it; false: no BGM is added.
​
duration
integer
Video duration (seconds). The default for the viduq2 series is 5. Optional: 1-10.
​
seed
integer
Random seed. When omitted by default or set to 0, a random number will be used instead. If manually set, the specified seed will be used.
​
resolution
string
Resolution parameter. The default value depends on the model and video duration. Optional values: 540p, 720p, 1080p, 360p. viduq2 (1-10 seconds): default 720p, optional: 540p, 720p, 1080p.
​
payload
string
Passthrough parameter. No processing is performed; data transmission only. Maximum length: 1048576 characters.
​
off_peak
boolean
Off-peak mode. Default is false. true: generate video during off-peak periods; false: generate video immediately.
​
watermark
boolean
Whether to add a watermark. Default is false. true: add watermark; false: do not add watermark.
​
wm_position
integer
Watermark position. Default is 3 (bottom right). Optional values: 1: top left; 2: top right; 3: bottom right; 4: bottom left.
​
wm_url
string
Watermark content, where this is an image URL. If not provided, the default watermark is used: content generated by AI.
​
meta_data
string
Metadata identifier. A JSON-formatted string, passed through as-is.

​
Response

​
created_at
string
Creation time (ISO 8601 format).
​
status
string
Task status. Common values include processing, failed, and completed.
​
task_id
string
Task ID, passed as the id parameter in subsequent queries.