bytedance/seedance-2-0-mini/text-to-video

1. Authentication

The API uses an API Key for authentication.

Get your API Key

Get your API key from https://icreat.ai/hub/keys .

2. Calling the API

Submit a request

Use cURL to submit a http request to start a task:

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST https://api.icreat.ai/v1/task/submit/bytedance/seedance-2-0-mini/text-to-video \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "content": [
    {
      "type": "text",
      "text": "A golden retriever running on a beach at sunset in slow motion"
    }
  ],
  "ratio": "16:9",
  "resolution": "1080p",
  "duration": 5
}'

The server will return a response body like:

{ "task_id" : "task-xxx"}

Use the task_id to poll the status and get the results.

3. Polling the status

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/query-status" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "task_id": "task-xxx"
}'

The server will return the status of the task. When the status is SUCCEEDED, you can get the results.

4. Get the results

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/get-result" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "task_id": "task-xxx"
}'

The server will return the outputs of this task.

5. Schema

Top Level

The API uses a multimodal input structure. content is a required array that supports any combination of text, image, video, and audio references.

Field	Type	Required	Description
`content`	object[]	Yes	An array of multimodal content. See the schema below
`generate_audio`	boolean	No	Whether to generate audio
`ratio`	string	No	Output aspect ratio. Supported values: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `21:9`, and `adaptive`. When set to `adaptive`, the model automatically selects the most suitable aspect ratio based on the input
`resolution`	string	No	Output resolution. Supported values: `480p`, `720p`
`duration`	integer	No	Video duration in seconds. Accepts an integer from `4` to `15`, or `-1` to let the model select the duration automatically
`watermark`	boolean	No	Whether to add an “AI Generated” watermark
`tools`	object[]	No	A list of tools to use

`content[]` Items

Field	Type	Required	Description
`type`	string	Yes	Content type: `text`, `image_url`, `video_url`, or `audio_url`
`text`	string	Conditional	Required when `type=text`. Supports Chinese, English, Japanese, Indonesian, Spanish, and Portuguese
`image_url`	object	Conditional	Required when `type=image_url`. Format: `{"url":"https://..."}`
`video_url`	object	Conditional	Required when `type=video_url`. Format: `{"url":"https://..."}`
`audio_url`	object	Conditional	Required when `type=audio_url`. Format: `{"url":"https://..."}`
`role`	string	Required for media	Media role: `reference_image`, `reference_video`, `reference_audio`, `first_frame`, or `last_frame`
`need_review`	boolean	No	Whether to submit the reference for official review. Set this to `true` when the reference contains faces or copyrighted IP

Chinese prompts must not exceed 2000 characters, and English prompts must not exceed 2000 words. Excessively long prompts may dilute the information and cause the model to ignore some details.

`need_review` Guidelines

If the reference contains faces or copyrighted IP, set need_review to true; otherwise, generation is highly likely to fail.
If content requiring review is submitted with need_review set to false, the task is highly likely to fail.
If content that does not require review is submitted with need_review set to true, generation may take longer.

`tools[]` Items

Field	Type	Required	Description
`type`	string	Yes	Tool type. Currently, only `web_search` is supported

6. Input examples

6.1 text to video

{
  "content": [
    {
      "type": "text",
      "text": "A cat is playing a ball"
    }
  ],
  "generate_audio": true,
  "ratio": "3:4",
  "duration": 5,
  "resolution": "480p"
}

6.2 without watermark

{
  "content": [
    {
      "type": "text",
      "text": "A cat is playing a ball"
    }
  ],
  "generate_audio": true,
  "ratio": "3:4",
  "duration": 5,
  "resolution": "480p",
  "watermark": false
}

6.3 enable web_search

{
  "content": [
    {
      "type": "text",
      "text": "A kitten plays the piano under the Eiffel Tower"
    }
  ],
  "ratio": "3:4",
  "duration": 5,
  "resolution": "480p",
  "tools": [
    {
      "type": "web_search"
    }
  ]
}