POST
https://octopusx.ai
/
vidu
/
ent
/
v2
/
text2video
Vidu Text-to-Video
curl --request POST \
  --url https://octopusx.ai/vidu/ent/v2/text2video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "style": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "seed": 123,
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "bgm": true,
  "audio": true,
  "off_peak": true,
  "watermark": true,
  "wm_position": 123,
  "wm_url": "<string>",
  "payload": "<string>",
  "meta_data": "<string>"
}
'
{
  "task_id": "48038932-0ff5-4251-8b4b-7a76c09fd114",
  "status": "processing",
  "created_at": 1774494511
}

​
Vidu Text-to-Video

The official Vidu text-to-video API, submitted as application/json.
  • The route entry is POST /vidu/ent/v2/text2video.
  • Currently submitted as application/json.
  • Supports pure-text video generation.
  • After a successful submission, the task task_id and status are returned. Use Query Task to poll for results.

​
Supported Models

  • viduq3-pro: Efficiently generates high-quality audio and video content, making the video more vivid, more realistic, and more three-dimensional
  • viduq2: Latest model
  • viduq1: Clear image quality, smooth transitions, and stable camera movement

​
Method and Path

POST /vidu/ent/v2/text2video

​
Request Example

curl -X POST https://octopusx.ai/vidu/ent/v2/text2video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq3-pro",
    "style": "general",
    "prompt": "A cat chasing butterflies on the grass",
    "duration": 5,
    "seed": 0,
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "bgm": false,
    "audio": true,
    "off_peak": false,
    "watermark": false
  }'

​
Response Example

{
  "task_id": "48038932-0ff5-4251-8b4b-7a76c09fd114",
  "status": "processing",
  "created_at": 1774494511
}

​
Authentication

Authorization: Bearer YOUR_API_KEY

​
Body

​
model
string
required
Model name. Supported viduq3-pro (efficiently generates high-quality audio and video content), viduq2 (latest model), viduq1 (clear image quality, smooth transitions, and stable camera movement).
​
style
string
Style. general: general style; anime: anime style. Note: this parameter does not take effect when using q2 or q3 models.
​
prompt
string
required
Text prompt. The text description for video generation, supporting Chinese and English.
​
duration
integer
Video duration (seconds). viduq2: default 5 seconds, optional 1-10 seconds; other models use the default value.
​
seed
integer
Random seed. If not provided or set to 0, a random number is used; if set manually, the specified seed is used.
​
aspect_ratio
string
Aspect ratio. Optional values: 16:9 (default), 9:16, 3:4, 4:3, 1:1. Note: 3:4 and 4:3 are only supported by q2 and q3 models.
​
resolution
string
Resolution. The default value depends on the model and video duration. viduq2 (1-10 seconds): default 720p, optional 540p, 720p, 1080p.
​
bgm
boolean
Whether to add background music. true: the system will automatically select suitable music from the preset BGM library and add it; false: do not add BGM. Note: the BGM parameter does not take effect when the duration of the q2 model is 9 or 10 seconds; it does not take effect in the q3 model.
​
audio
boolean
Audio-video direct output (supported only by q3 models). true: audio-video direct output is required, outputting a video with dialogue and background sound; false: audio-video direct output is not required, outputting a silent video.
​
off_peak
boolean
Off-peak mode. true: generate videos during off-peak periods, with lower points cost; false: generate videos immediately.
​
watermark
boolean
Whether to add a watermark. true: add a watermark; false: do not add a watermark. Note: the watermark content is fixed as “Content generated by AI”, and it is not added by default.
​
wm_position
integer
Watermark position. 1: top-left; 2: top-right; 3: bottom-right; 4: bottom-left.
​
wm_url
string
Watermark image URL. If not provided, the default watermark is used.
​
payload
string
Pass-through parameter. No processing is performed; data transmission only.
​
meta_data
string
Metadata identifier. JSON-formatted string, pass-through field.

​
Response

​
task_id
string
Task ID, used to query task status.
​
status
string
Task status. Optional values: processing (in progress), failed (failed), completed (completed).
​
created_at
integer
Creation timestamp (Unix timestamp).