Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://toapis.com/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "viduq3-pro",
    "prompt": "A cat playing piano, camera slowly zooms in, cinematic quality",
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "audio": true
  }'

{
  "id": "<string>",
  "object": "<string>",
  "model": "<string>",
  "status": "<string>",
  "created_at": 123
}
  • Async task API, returns a task ID after submission
  • Supported models: viduq3-pro, viduq3-turbo, viduq3
  • viduq3-pro: High quality model, supports audio-video sync and storyboard generation
  • viduq3-turbo: Fast model, intelligent scene switching, fastest generation, best cost-effectiveness
  • viduq3: Best multi-camera consistency, intelligent camera switching, multi-reference generation
Use publicly accessible image URLs. Do not pass base64 image data in image_urls; upload local images with the Upload Image API first.

​
Authorization

​
Authorization
string
required
All endpoints require Bearer Token authentication.
Authorization: Bearer YOUR_API_KEY

​
Request Parameters

​
model
string
required
Vidu Q3 model name.Options:
  • viduq3-pro - high quality, supports audio-video sync and storyboard generation
  • viduq3-turbo - fastest generation, intelligent scene switching
  • viduq3 - best multi-camera consistency, for multi-reference/subjects generation
​
prompt
string
required
Text prompt, maximum 5000 characters.Describes subject, action, scene, camera movement, and style. When using subjects, reference them via @name in the prompt.Example: "A cat playing piano, camera slowly zooms in, cinematic quality"
​
duration
integer
default:"5"
Video duration in seconds.
  • viduq3-pro / viduq3-turbo: 1 to 16
  • viduq3: 3 to 16
​
resolution
string
default:"720p"
Video resolution.Options:
  • 540p
  • 720p
  • 1080p
​
aspect_ratio
string
Video aspect ratio.Common values: 16:9, 9:16, 1:1Q3 models support any aspect ratio. When image_urls is provided, the output ratio is usually determined by the reference image.
​
image_urls
string[]
Reference image URL array.
  • viduq3-pro / viduq3-turbo
    • Omitted: text-to-video
    • 1 image: image-to-video, image as first frame
    • 2 images: first-last frame
  • viduq3
    • Required, up to 7 reference images
Example: ["https://example.com/reference.jpg"]
​
audio
boolean
Whether to enable audio-video output.
  • All Q3 models default to true
When true, the system generates speech and sound effects based on the prompt.
​
seed
integer
Random seed for more reproducible results with the same parameters.
​
metadata
object
Extended parameters for fields supported by the upstream API but not exposed as top-level fields.

​
Model Selection

ModelUse CaseImage InputResolutionDuration
viduq3-proHigh quality text/image/first-last frameOptional, up to 2 images540p / 720p / 1080p1-16s
viduq3-turboFast text/image/first-last frameOptional, up to 2 images540p / 720p / 1080p1-16s
viduq3Multi-reference/Subjects generationRequired, up to 7 images540p / 720p / 1080p3-16s

​
Billing Dimensions

Vidu Q3 is billed by model, resolution, and generation type:
  • viduq3-pro: high quality tier, approximately 2x the price of turbo
  • viduq3-turbo: fast tier, best cost-effectiveness
  • viduq3: multi-reference generation, billed at reference generation rate

​
Response

​
id
string
Task ID for querying task status.
​
object
string
Object type, usually generation.task.
​
model
string
Model used for the request.
​
status
string
Task status: queued, in_progress, completed, or failed.
​
created_at
integer
Task creation timestamp.

​
Examples

​
Text-to-Video

{
  "model": "viduq3-pro",
  "prompt": "A cat playing piano, camera slowly zooms in, cinematic quality",
  "duration": 8,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "audio": true
}

​
Image-to-Video

{
  "model": "viduq3-turbo",
  "prompt": "The person in the image slowly turns and smiles",
  "image_urls": ["https://example.com/portrait.jpg"],
  "duration": 5,
  "resolution": "720p"
}

​
First-Last Frame

{
  "model": "viduq3-pro",
  "prompt": "The person naturally sits down from standing, smooth motion",
  "image_urls": [
    "https://example.com/first-frame.jpg",
    "https://example.com/last-frame.jpg"
  ],
  "duration": 8,
  "resolution": "720p"
}

​
Multi-Reference Image Video

{
  "model": "viduq3",
  "prompt": "Keep the character consistent from the reference images, walking through a futuristic city street",
  "image_urls": [
    "https://example.com/character-front.jpg",
    "https://example.com/character-side.jpg"
  ],
  "duration": 6,
  "resolution": "1080p"
}

​
Subjects Mode

{
  "model": "viduq3",
  "prompt": "@cat and @dog are running in the park, sunny day",
  "image_urls": ["https://example.com/park-bg.jpg"],
  "duration": 8,
  "resolution": "720p",
  "audio": true,
  "metadata": {
    "subjects": [
      {"name": "cat", "images": ["https://example.com/cat.jpg"]},
      {"name": "dog", "images": ["https://example.com/dog.jpg"]}
    ],
    "audio_type": "all"
  }
}
Video generation is asynchronous. Use the Get Video Task Status endpoint to query progress and results.
curl --request POST \
  --url https://toapis.com/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "viduq3-pro",
    "prompt": "A cat playing piano, camera slowly zooms in, cinematic quality",
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "audio": true
  }'