Create Video Generation Task API (doubao-2.0)

POST https://www.kkiai.com/api/v3/contents/generations/tasks

https://www.volcengine.com/docs/82379/1520757?lang=zh

Request Parameters

Authorization

Add the Authorization parameter to the Header. Its value is the Token concatenated after Bearer.

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

Body Parameters (application/json)

Parameter	Type	Required	Description
model	string	Required
content	array[object]	Required
└ type	string	Required
└ text	string	Optional
└ image_url	object	Required
└ role	string	Required
└ video_url	object	Optional
└ audio_url	object	Optional
generate_audio	boolean	Optional
ratio	string	Optional
duration	integer	Optional
watermark	boolean	Optional

Request Example

{
    "model": "doubao-seedance-2-0-260128",
    "content": [
         {
            "type": "text",
            "text": "Use the first-person POV composition from Video 1 throughout the entire video, and use Audio 1 as the background music throughout. Create a first-person promotional advertisement for fruit tea, featuring the Seedance \"Ping Ping An An\" limited-edition apple fruit tea. The opening frame should match Image 1: your hand picks a dew-covered Aksu red apple, with a crisp and refreshing apple contact sound. 2–4 seconds: fast-paced cuts. From a first-person perspective, your hand drops apple chunks into a shaker cup, adds ice cubes and a tea base, then shakes it vigorously. The sound of ice clinking and shaking should sync rhythmically with upbeat drum beats. Background voiceover: \"Freshly cut, freshly shaken.\" 4–6 seconds: first-person close-up of the finished drink. The layered fruit tea is poured into a transparent cup. Your hand gently squeezes milk foam on top, letting it spread across the surface. Then a pink label sticker is placed on the cup. The camera moves closer to highlight the texture and layering of the milk foam and fruit tea. 6–8 seconds: from a first-person perspective, your hand holds up the fruit tea shown in Image 2 in front of the camera, as if offering it directly to the viewer. The label on the cup should be clearly visible. Background voiceover: \"Take a sip of fresh refreshment.\" The final frame should freeze on Image 2. Use a female voice consistently for all background voice lines."
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic1.jpg"
            },
            "role": "reference_image"
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic2.jpg"
            },
            "role": "reference_image"
        },
        {
          "type": "video_url",
          "video_url": {
              "url": "https://pro.filesystem.site/cdn/20260403/0e80a635b859e7716671a40d836135.mp4"
          },
          "role": "reference_video"
        },
        {
          "type": "audio_url",
          "audio_url": {
              "url": "https://ark-project.tos-cn-beijing.volces.com/doc_audio/r2v_tea_audio1.mp3"
          },
          "role": "reference_audio"
        }
    ],
    "generate_audio":true,
    "ratio": "21:9",
    "duration": 11,
    "watermark": false
}

cURL Example

curl --location --request POST 'https://www.kkiai.com/api/v3/contents/generations/tasks' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "doubao-seedance-2-0-260128",
    "content": [
         {
            "type": "text",
            "text": "Use the first-person POV composition from Video 1 throughout the entire video, and use Audio 1 as the background music throughout. Create a first-person promotional advertisement for fruit tea, featuring the Seedance \"Ping Ping An An\" limited-edition apple fruit tea. The opening frame should match Image 1: your hand picks a dew-covered Aksu red apple, with a crisp and refreshing apple contact sound. 2–4 seconds: fast-paced cuts. From a first-person perspective, your hand drops apple chunks into a shaker cup, adds ice cubes and a tea base, then shakes it vigorously. The sound of ice clinking and shaking should sync rhythmically with upbeat drum beats. Background voiceover: \"Freshly cut, freshly shaken.\" 4–6 seconds: first-person close-up of the finished drink. The layered fruit tea is poured into a transparent cup. Your hand gently squeezes milk foam on top, letting it spread across the surface. Then a pink label sticker is placed on the cup. The camera moves closer to highlight the texture and layering of the milk foam and fruit tea. 6–8 seconds: from a first-person perspective, your hand holds up the fruit tea shown in Image 2 in front of the camera, as if offering it directly to the viewer. The label on the cup should be clearly visible. Background voiceover: \"Take a sip of fresh refreshment.\" The final frame should freeze on Image 2. Use a female voice consistently for all background voice lines."
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic1.jpg"
            },
            "role": "reference_image"
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://ark-project.tos-cn-beijing.volces.com/doc_image/r2v_tea_pic2.jpg"
            },
            "role": "reference_image"
        },
        {
          "type": "video_url",
          "video_url": {
              "url": "https://pro.filesystem.site/cdn/20260403/0e80a635b859e7716671a40d836135.mp4"
          },
          "role": "reference_video"
        },
        {
          "type": "audio_url",
          "audio_url": {
              "url": "https://ark-project.tos-cn-beijing.volces.com/doc_audio/r2v_tea_audio1.mp3"
          },
          "role": "reference_audio"
        }
    ],
    "generate_audio":true,
    "ratio": "21:9",
    "duration": 11,
    "watermark": false
}'

Response

🟢 200 Success

Response Example

{}