Turn a Written Scene into a Short Video · Alibaba

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "prompt"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "seed": {
          "type": "integer",
          "maximum": 2147483647,
          "minimum": 0,
          "description": "Optional integer from 0 to 2147483647. A repeated seed can reuse the random starting point, but cannot ensure identical footage, shot timing or sound."
        },
        "ratio": {
          "enum": [
            "16:9",
            "9:16",
            "1:1",
            "4:3",
            "3:4"
          ],
          "type": "string",
          "default": "16:9",
          "description": "Optional 16:9, 9:16, 1:1, 4:3 or 3:4, default 16:9. Choose 9:16 for the vertical tea-scene example. It selects the frame shape, not the shot sequence or camera composition."
        },
        "prompt": {
          "type": "string",
          "maxLength": 5000,
          "minLength": 1,
          "description": "Required nonempty text, at most 5000 characters. Describe subjects, action, style and camera views. For several shots, write their order and requested time intervals in the text; these directions do not guarantee exact cuts, timing or continuity."
        },
        "duration": {
          "type": "integer",
          "default": 5,
          "maximum": 15,
          "minimum": 2,
          "description": "Optional integer from 2 to 15 seconds, default 5. It applies to the whole generated video, including any requested shots. The tea-scene example uses 6 seconds; written shot intervals remain creative instructions."
        },
        "audio_url": {
          "type": "string",
          "minLength": 1,
          "description": "Optional nonempty public HTTPS URL for a WAV or MP3 file, 2–30 seconds and at most 15 MB. HTTP, Base64 and local-file inputs are not accepted. Longer audio is cut to its opening segment matching the video duration; shorter audio leaves a silent tail. Without supplied audio the model can generate background music or effects. Audio timing, lip-sync and track preservation are not guaranteed."
        },
        "watermark": {
          "type": "boolean",
          "default": false,
          "description": "Optional boolean, default false. Set true to request an AI Generated watermark on the clip."
        },
        "resolution": {
          "enum": [
            "720P",
            "1080P"
          ],
          "type": "string",
          "default": "720P",
          "description": "Optional 720P or 1080P, default 720P for this Tool. The tea-scene example requests 720P. A higher tier does not guarantee more accurate subjects, text or shot transitions."
        },
        "prompt_extend": {
          "type": "boolean",
          "default": true,
          "description": "Optional boolean, default true. It allows the model to rewrite the prompt before generating the clip and can add processing time. Rewriting does not guarantee quality or adherence to the requested shot plan."
        },
        "negative_prompt": {
          "type": "string",
          "maxLength": 500,
          "description": "Optional text, at most 500 characters, describing unwanted elements. It guides generation rather than guaranteeing their complete absence."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}