Video Generation API

Generate videos from text prompts or uploaded media files. Supports both application/json and multipart/form-data (for file uploads). Powered by providers like novita and google.

01Request Headers

Authorizationstringrequired

Bearer token for authentication. Format: Bearer <YOUR_TOKEN>. Exchange your API key for a token via the Authentication endpoint.

Content-Typestringrequired

Use application/json for text-only requests, or multipart/form-data when including file uploads (e.g. image-to-video).

02Request Body

Required Fields

promptstringrequired

Text prompt describing the video to generate.

modelstringrequired

The video model to use. Retrieve the full list from the GET Models endpoint and use the model name from the response.

resolutionstringrequired

Video resolution. Options: "480P", "720P", "1080P".

aspect_ratiostringrequired

Aspect ratio of the output video. Options: "16:9", "9:16", "1:1", "4:3", "3:4", "21:9".

durationintegerrequired

Duration of the video in seconds. Must be an integer between 4 and 12.

generate_audiobooleanrequired

Whether to generate audio alongside the video.

camera_fixedbooleanrequired

Keep the camera fixed during generation.

service_tierstringrequired

Service tier for priority routing. Options: "default", "flex".

Optional Fields

fpsinteger

Frames per second. Default: 24.

seedinteger

Random seed for reproducibility. Omit or use -1 for random output.

File Uploads

When using multipart/form-data, include file attachments under the files field (e.g. a reference image for image-to-video). All other fields are passed as form string values.

Example Request

// Text-to-video generation

{
  "model": "seedance-v1.5-pro-t2v",
  "prompt": "a cat drinking milk in a cozy kitchen",
  "resolution": "720P",
  "aspect_ratio": "16:9",
  "duration": 5,
  "generate_audio": true,
  "camera_fixed": false,
  "service_tier": "default",
  "fps": 24,
  "seed": -1
}

03Response

Response Fields

idstring

Unique request identifier (UUID).

createdinteger

Unix timestamp of when the job was created.

textstring

Confirmation message echoing the prompt used.

finish_reasonstring

Reason generation stopped. Typically "stop".

providerstring

The provider that handled the request.

modelstring

The model used for generation.

usageobject

Token counts: prompt_tokens, completion_tokens, total_tokens.

latency_msnumber

End-to-end processing latency in milliseconds.

videosarray

Array of generated video objects, each with a url and type (e.g. mp4).

resolutionstring

Resolution of the generated video (e.g. "1280*720").

imagesarray

Image outputs if applicable, otherwise an empty array.

audiosstring | null

Audio file path if generated, otherwise null.

application/json200 OK

{ "api_details": { "api_status": "success", "api_message": "API has return response successfully." }, "data": { "id": "3a4dbc94-455f-47f4-ae42-4cb528ac5b3d", "created": 1774529224, "text": "Generated video for prompt: a cat drinking the milk", "finish_reason": "stop", "provider": "novita", "model": "seedance-v1.5-pro-t2v", "usage": { "prompt_tokens": 11, "completion_tokens": 0, "total_tokens": 11 }, "latency_ms": 46795.58, "images": [], "videos": [ { "url": "https://...", "type": "mp4" } ], "resolution": "1280*720", "audios": null }, "error": {} }

Error Status Codes

Code	Status	Description
200	OK	Video generated successfully.
400	Bad Request	Invalid request body or unsupported provider/model.
401	Unauthorized	Missing or invalid Authorization header / Bearer token.
403	Forbidden	Insufficient credit balance.
422	Unprocessable Entity	Request body failed schema validation.
500	Internal Server Error	Unexpected error during video generation.