Kandinsky5 Pro Text To Video

Playground

Kandinsky 5 Pro Text-to-Video turns natural-language prompts into coherent 5-second clips with strong prompt adherence and smooth motion. Choose 512p or 1024p output across common aspect ratios for social posts, ads, and concept shots. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.

Features

Kandinsky 5 Pro Text-to-Video

Kandinsky 5 Pro Text-to-Video is a production-ready text-to-video model that generates dynamic 5-second MP4 clips from a single prompt. It’s optimized for fast iteration and clean, prompt-faithful motion, with simple controls for resolution and aspect ratio.

Why it stands out

5-second text-to-video generation Turn a prompt into a complete short clip—ideal for rapid concept testing and social-ready outputs.
Two resolution tiers Choose 512P for faster, cheaper drafts or 1024P for sharper detail.
Creator-friendly aspect ratios Built-in framing for 3:2, 1:1, and 2:3 to match common feed and creative formats.
Fast, stable inference Designed for predictable performance in real-world pipelines and batch experimentation.

Parameters

Parameter	Description
prompt*	The text prompt describing subject, action, scene, and style.
resolution	Output resolution: 512P (default) or 1024P.
aspect_ratio	Output aspect ratio: 3:2 (default), 1:1, or 2:3.
duration	Fixed at 5 seconds.

How to use

Write a clear prompt describing the subject, action, environment, and style.
Select aspect_ratio for your delivery format (landscape, square, or portrait).
Choose resolution: 512P for quick drafts, 1024P for final detail.
Run the model and download the generated MP4.

Prompt tips

Use clear verbs for motion: “walks,” “turns,” “sparks fly,” “camera pans slowly.”
Keep the structure simple: subject → action → scene → lighting → style.
For stronger coherence, describe one main shot rather than multiple scene changes.

Pricing

All videos are 5 seconds.

Resolution	Price per second	Price per 5s video
512P	$0.04	$0.20
1024P	$0.12	$0.60

Use Cases

Social media short clips and creative testing
Storyboarding and previsualization
Marketing concept drafts and ad iterations
Stylized motion scenes for presentations and demos

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/wavespeed-ai/kandinsky5-pro/text-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "512p",
    "aspect_ratio": "3:2",
    "duration": 5
}'

# 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
prompt	string	Yes		-	The text prompt to guide video generation.
resolution	string	No	512p	512p, 1024p	Video resolution quality.
aspect_ratio	string	No	3:2	3:2, 1:1, 2:3	Aspect ratio of the generated video.
duration	integer	No	5	5	Video duration in seconds (currently only 5s is supported).

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.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
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

Kandinsky5 Pro Image To Video Latentsync