Create a Clip from a Brief or Reference Material · Alibaba

{
  "type": "object",
  "required": [],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "seed": {
          "type": "integer",
          "maximum": 2147483647,
          "minimum": 0,
          "description": "Optional integer in 0–2147483647. A repeated value can reuse the random starting point, but cannot ensure the same clip or unchanged characters."
        },
        "audio": {
          "type": "boolean",
          "default": true,
          "description": "Optional boolean with default true. Enable it for a generated audio track, or set false for silent output. Exact narration and original-sound preservation are not guaranteed."
        },
        "media": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "type",
              "url"
            ],
            "properties": {
              "url": {
                "type": "string",
                "minLength": 1,
                "description": "Each entry requires a nonempty public HTTPS URL. A document may be docx/xlsx/pptx/pdf/txt/md, up to 100 MB and 50 pages where applicable; webpages must need no login. Image types accept JPG/JPEG, PNG without alpha, BMP and WEBP, up to 20 MB, 240–8000 pixels per side and ratio 1:8–8:1. Video accepts MP4/MOV, up to 100 MB, 1–15 seconds, at least 16 fps, sides 240–4096 and ratio 1:8–8:1. Audio accepts WAV/MP3, up to 15 MB and 1–15 seconds. HTTP, base64 and local paths are not valid source links here."
              },
              "type": {
                "enum": [
                  "first_frame",
                  "last_frame",
                  "reference_image",
                  "reference_video",
                  "reference_audio",
                  "file",
                  "link"
                ],
                "type": "string",
                "description": "Required choice: first_frame, last_frame, reference_image, reference_video, reference_audio, file or link. Use one first frame alone or together with one last frame; last-only input is not supported, and frames cannot combine with references, files or links. Reference images, videos and audio may combine, capped at 10, 5 and 5 respectively, and may add either one file or one link. file and link cannot coexist."
              }
            },
            "additionalProperties": false
          },
          "description": "Optional when a valid prompt is present; otherwise provide a nonempty eligible list. Entries must contain type and url. Keep order within each reference type for separate Image 1, Video 1 and Audio 1 numbering. Video/audio clips must each last 1–15 seconds, with their combined input duration no more than 15 seconds. Omit this list for text-only creation."
        },
        "ratio": {
          "enum": [
            "adaptive",
            "16:9",
            "9:16",
            "1:1",
            "4:3",
            "3:4"
          ],
          "type": "string",
          "default": "adaptive",
          "description": "Optional adaptive by default, or 16:9, 9:16, 1:1, 4:3, 3:4. Choose 9:16 for the vertical PDF example. adaptive selects a suitable shape from the input and intent; 21:9 is outside the available choices."
        },
        "prompt": {
          "type": "string",
          "maxLength": 20000,
          "minLength": 1,
          "description": "When provided, use nonempty text no longer than 20000 characters. A prompt or eligible media is needed. State the intended content and any point to emphasize; name references Image 1, Video 1 or Audio 1 using separate order per type. Overlong text is not accepted under this Tool’s length limit."
        },
        "duration": {
          "anyOf": [
            {
              "type": "integer",
              "maximum": 30,
              "minimum": 2
            },
            {
              "type": "string",
              "const": "auto"
            }
          ],
          "default": 5,
          "description": "Optional 2–30 whole seconds or the string auto; default 5. auto delegates the length choice to the model. When reference video is included, all input-video seconds plus output seconds must total no more than 30. This Tool does not accept -1 as duration."
        },
        "watermark": {
          "type": "boolean",
          "default": false,
          "description": "Optional boolean, default false. Setting true requests the AI Generated watermark."
        },
        "resolution": {
          "enum": [
            "480P",
            "720P",
            "1080P"
          ],
          "type": "string",
          "default": "720P",
          "description": "Optional 480P, 720P or 1080P, with 720P as the native default. The example selects 720P; inspect the actual result after completion."
        },
        "prompt_extend": {
          "type": "boolean",
          "default": true,
          "description": "Optional boolean, default true. Intelligent rewriting runs before generation and can increase processing time. File and webpage inputs require true; rewriting does not establish factual accuracy or exact visual fidelity."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}