Skip to main content
POST
https://api.novita.ai
/
v3
/
async
/
vidu-q3-pro-t2v
Vidu Q3 Pro Text-to-Video
curl --request POST \
  --url https://api.novita.ai/v3/async/vidu-q3-pro-t2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "audio": true,
  "prompt": "<string>",
  "wm_url": "<string>",
  "duration": 123,
  "off_peak": true,
  "watermark": true,
  "resolution": "<string>",
  "wm_position": 123,
  "aspect_ratio": "<string>"
}
'
{
  "task_id": "<string>"
}
Vidu Q3 Pro Text-to-Video generates high-quality videos with synchronized audio from text descriptions, supporting resolutions up to 1080p and durations from 1-16 seconds.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
seed
integer
Random seed for reproducibility. Use 0 for random.Value range: [0, 2147483647]
​
audio
boolean
default:true
Enable synchronized audio generation (dialogue and sound effects). Only supported by Q3 model.
​
prompt
string
required
Text description for video generation. Max 2000 characters.Length limit: 0 - 2000
​
wm_url
string
URL of the watermark image.
​
duration
integer
default:5
Video length in seconds (1-16).Value range: [1, 16]
​
off_peak
boolean
default:false
Use off-peak pricing tier. Tasks will be processed within 48 hours at reduced cost.
​
watermark
boolean
default:false
Whether to add watermark to the video.
​
resolution
string
default:"720p"
Output video quality.Optional values: 540p, 720p, 1080p
​
wm_position
integer
Watermark position: 1=top-left, 2=top-right, 3=bottom-left, 4=bottom-right.Value range: [1, 4]
​
aspect_ratio
string
default:"16:9"
Output video aspect ratio.Optional values: 16:9, 9:16, 4:3, 3:4, 1:1

​
Response

​
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.