Create Task

POST https://www.kkiai.com/volc/v1/contents/generations/tasks

Official Documentation: https://www.volcengine.com/docs/82379/1520757

Request Parameters

Authorization

Add the Authorization parameter to the Header, with the value being the Token concatenated after Bearer

Example: Authorization: Bearer ********************

Header Parameters

Parameter Name	Type	Required	Description	Example
Content-Type	string	Optional		application/json
Accept	string	Optional		application/json
Authorization	string	Optional		Bearer {{YOUR_API_KEY}}

Body Parameters (application/json)

Parameter Name	Type	Required	Description
model	string	Required	doubao-seedance-1-5-pro-251215 Supports: text-to-video, first frame, first and last frame doubao-seedance-1-0-pro-250528 Supports: text-to-video, first frame, first and last frame doubao-seedance-1-0-pro-fast-251015 Supports: text-to-video, first frame doubao-seedance-1-0-lite-t2v-250428 Supports: text-to-video doubao-seedance-1-0-lite-i2v-250428 Supports: first frame, first and last frame, reference image (1-4)
content	array[object]	Required	Information input to the model for video generation, supporting text and image information.
└ type	string	Required	Type of input content: text represents text image_url represents image
└ text	string	Required	Text content input to the model, describing the expected video to be generated, including: Text prompt (required): Supports Chinese and English. Recommended not to exceed 500 characters. Excessive text can scatter information, and the model may ignore details and focus only on key points, resulting in missing elements in the video.
└ image_url	object	Optional	Image object input to the model.
└ role	string	Optional	Image purpose: reference_image represents reference image first_frame represents first frame This parameter can be omitted when only using first frame last_frame represents last frame
generate_audio	boolean	Optional	Controls whether the generated video includes audio synchronized with the visuals. true: The video output by the model includes synchronized audio. Seedance 1.5 pro can automatically generate matching human voice, sound effects, and background music based on text prompts and visual content. It is recommended to place dialogue within double quotes to optimize audio generation. For example: The man called out to the woman saying: "Remember, you can never point at the moon with your finger." false: The video output by the model is silent. Note: This parameter is only supported by Seedance 1.5 pro model Default value: true
-- Parameters	object	Optional	The following parameters need to be added after the prompt in the form of -- , refer to examples
└ resolution	string	Optional	Video resolution, enumerated values: 480p 720p 1080p: Not supported in reference image scenarios Seedance 1.5 pro, Seedance 1.0 lite Default value: 720p Seedance 1.0 pro & pro-fast Default value: 1080p
└ ratio	string	Optional	Aspect ratio of generated video: 16:9 4:3 1:1 3:4 9:16 21:9 Text-to-video: Default value 16:9 (Seedance 1.5 Pro defaults to adaptive) Image-to-video: Default adaptive (reference image video generation defaults to 16:9)
└ duration	integer	Optional	Duration of generated video in seconds. Supports 2-12 seconds Seedance 1.5 pro only supports 4-12 seconds Default value 5
└ camera_fixed	string	Optional	Whether to fix the camera. Enumerated values: true: Fix the camera. The platform will append fixed camera to the user prompt, actual results not guaranteed. false: Do not fix the camera. Note: Not supported in reference image scenarios Default value false
└ watermark	string	Optional	Whether the generated video includes a watermark. Enumerated values: false: No watermark. true: Contains watermark. Default value false
└ seed	integer	Optional	Seed integer used to control the randomness of generated content. Value range: Integer between [-1, 2^32-1]. Note: Under the same request, if the model receives different seed values, such as: not specifying a seed value or setting seed to -1 (which uses a random number instead), or manually changing the seed value, different results will be generated. Under the same request, if the model receives the same seed value, similar results will be generated, but complete consistency is not guaranteed. Default value -1 Cannot input -1 when passing

Request Example

{
    "model": "doubao-seedance-1-0-pro-fast-251015",
    "content": [
        {
            "type": "text",
            "text": "Photorealistic style, under a clear blue sky, a vast field of white daisies. The camera slowly pushes in, gradually moving closer, and finally stops on a close-up of a single daisy with several sparkling dewdrops on its petals. --resolution 480p --ratio 16:9 --duration 2 --camera_fixed false --watermark false --seed 1"
        }
    ]
}

cURL Example

curl --location --request POST 'https://www.kkiai.com/volc/v1/contents/generations/tasks' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "doubao-seedance-1-0-pro-fast-251015",
    "content": [
        {
            "type": "text",
            "text": "Photorealistic style, under a clear blue sky, a vast field of white daisies. The camera slowly pushes in, gradually moving closer, and finally stops on a close-up of a single daisy with several sparkling dewdrops on its petals. --resolution 480p --ratio 16:9 --duration 2 --camera_fixed false --watermark false --seed 1"
        }
    ]
}'

Response

🟢 200 Success

Response Example

{
    "id": "cgt-20250918165243-bfpzb",
    "status": "submitted"
}