Vidu Q3 Drama Clip

Playground

Vidu Q3 Drama Clip generates 8-12 second script-driven drama videos from structured assets, including characters, scenes, and tools. It is ideal for compact story scenes, storyboard shots, and focused narrative moments. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q3 Drama Clip

Vidu Q3 Drama Clip generates short 8-12 second drama clips from a script and a structured asset list. It is designed for compact narrative moments where you define the characters, scene, tools, visual references, and output controls in one request.

Why Choose This?

Short drama clip generation: Create focused drama fragments from 8 to 12 seconds.
Script-driven control: Use content to describe the plot, action, dialogue, camera movement, and visual details for the clip.
Structured asset control: Define characters, scenes, and tools with IDs, names, types, reference images, and descriptions.
Reference positioning: Use image and placement to control positioning, panorama, or step-based references.
Precise duration selection: Choose a fixed duration of 8, 9, 10, 11, or 12 seconds.
Narrative workflow: Suitable for storyboard shots, scene-level clips, ads, hooks, and short character-driven video moments.

Properties

Property	Required	Type	Description
name	Yes	string	Task name.
content	Yes	string	Drama script or content. Supports up to 5000 characters.
assets	Yes	array(object)	Asset list. Up to 14 assets are supported; 3-10 are recommended.
assets.id	Yes	string	Asset ID, using numeric strings such as `01`, `02`, `03`.
assets.name	Yes	string	Asset name, up to 30 characters.
assets.type	Yes	string enum	Asset type. Supported values: `character`, `scene`, `tool`.
assets.image_uri	Yes	string	Reference image for this asset. Supports public image URL or Base64 image data.
assets.description	No	string	Asset description, such as identity, appearance, age, role, scene details, or tool details.
image	No	string	Positioning reference image uploaded by the user.
placement	No	string enum	Placement mode: `upload`, `panorama`, or `step`. Default: `upload`.
quality	No	string enum	Quality level: `standard` or `high`. Default: `high`.
duration	Yes	integer enum	Fixed clip duration in seconds. Supported values: `8`, `9`, `10`, `11`, and `12`.
resolution	No	string enum	Output resolution: `720p` or `1080p`. Default: `1080p`.
aspect_ratio	No	string enum	Output aspect ratio: `9:16` or `16:9`. Default: `9:16`.
style	No	string	Video style, such as realistic, 3D modeling, or 2D animation. Limit: 30 characters; punctuation is not recommended.

Image Requirements

assets.image_uri supports image URL or Base64 image data.
Supported image formats: PNG, JPEG, JPG, and WebP.
Base64 input should include the content type prefix, for example: data:image/png;base64,{base64_encode}.
Each asset can correspond to one image.
Keep image URLs publicly accessible.
Keep images within the documented size, aspect ratio, and request body limits.

Pricing

Billing is based on effective video duration at $0.14 per second.

Duration	Price
8s	$1.12
9s	$1.26
10s	$1.40
11s	$1.54
12s	$1.68

Effective duration is limited to 8-12 seconds. Missing or lower values are billed as 8 seconds; values above 12 seconds are billed as 12 seconds.

How to Use

Enter name for the task.
Write the drama clip script in content.
Add assets for characters, scenes, or tools.
Set each asset ID as 01, 02, 03, and so on.
Upload or provide image_uri for every asset.
Optionally provide a positioning reference image and choose placement.
Select quality, duration, resolution, aspect ratio, and style as needed.
Submit the task and retrieve the generated clip when complete.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/q3/drama-clip" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "placement": "panorama",
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "9:16"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
name	string	Yes	-	-	The name of the drama generation task.
content	string	Yes	-	-	Drama content or script. Supports up to 5000 characters.
assets	array	Yes	-	1 ~ 14 items	Asset list. Asset IDs are generated automatically by order as 01, 02, 03, and so on.
image	string	No		-	The positioning reference map uploaded by the user.
placement	string	No	panorama	panorama, upload, step	upload 、panorama 、 step (Any option is acceptable) The default upload speed is the fastest. The other two fields will only take effect when the upload_image_url is empty. The second one is panoramic reference, generating panoramic images; The third one is sequential reference. Input the four-square grid of the previous shot into the next shot
duration	integer	No	8	8, 9, 10, 11, 12	Select the fixed duration for this drama clip. This model is designed for short drama fragments, storyboard shots, and scene-level clips. Supported values are 8, 9, 10, 11, and 12 seconds only. Choose the exact clip length you want to generate.
resolution	string	No	1080p	720p, 1080p	Video resolution.
aspect_ratio	string	No	9:16	9:16, 16:9	The aspect ratio of the generated media.
style	string	No	-	-	Video style. You can enter styles such as 3D modeling style, 2D animation style, etc. Limited to 30 characters. No punctuation allowed. Default: live action photorealistic.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Vidu Q2 Turbo Extend Video Vidu Q3 Image To Video