generateDhVideo

Create customized digital human videos by specifying avatar ID, voice ID, text, resolution, and background. Enable subtitles, automatic gestures, and select camera angles for personalized video output.

Instructions

#工具说明：根据所选数字人像ID及发音人ID，生成数字人视频。

样例1：

用户输入：用数字人像ID为xxx，发音人ID为yyy的音色，视频的内容是“大家好，我是数字人播报的内容”，使用横屏全身的机位，视频背景用“https://digital-human-material.bj.bcebos.com/-[Ljava.lang.String;@46f6cc1e.png”，开启自动添加动作，开启字幕，生成一个1080P的数字人视频。思考过程: 1.用户想要用人像ID生成一个数字人视频，对声音，背景，字幕，分辨率等有要求，不是一个简单的数字人视频，需要使用“generateDhVideo”工具。 2.工具需要FigureId，driveType，text，person，inputAudioUrl，width，hight，cameraID，enable，backgroundimageUrl，autoAnimoji这些参数。 3.FigureId是需要使用的人像ID，所以值为xxx。给的播报内容是文本，所以driveType是文本驱动，text为“大家好，我是数字人播报的内容”。发音人已经提供了ID，所以person的值是yyy，开启自动动作，所以autoAnimoji的值为true，开启字幕，所以enabled的值为true，分辨率为1080P，拆分为width的值为1920，hight的值为1080，backgroundimageUrl的值是“https://digital-human-material.bj.bcebos.com/-[Ljava.lang.String;@46f6cc1e.png”

Input Schema

Name	Required	Description	Default
`autoAnimoji`	No	自动添加数字人动作
`backgroundImageUrl`	No	背景图片
`backgroundTransparent`	No	背景是否透明
`callbackUrl`	No	回调地址
`cameraId`	No	数字人相机机位，0:横屏半身, 1:竖屏半身, 2: 横屏全身, 3: 竖屏全身
`driveType`	No	驱动类型, TEXT:文本驱动, VOICE: 音频驱动	TEXT
`figureId`	No	人像ID
`inputAudioUrl`	No	驱动音频URL
`resolutionHeight`	No	分辨率:高
`resolutionWidth`	No	分辨率:宽
`subtitleEnable`	No	是否启用字幕
`text`	No	播报内容
`voiceId`	No	音色ID

Input Schema (JSON Schema)

{
  "properties": {
    "autoAnimoji": {
      "default": false,
      "description": "自动添加数字人动作",
      "title": "Autoanimoji",
      "type": "boolean"
    },
    "backgroundImageUrl": {
      "default": null,
      "description": "背景图片",
      "title": "Backgroundimageurl",
      "type": "string"
    },
    "backgroundTransparent": {
      "default": false,
      "description": "背景是否透明",
      "title": "Backgroundtransparent",
      "type": "boolean"
    },
    "callbackUrl": {
      "default": null,
      "description": "回调地址",
      "title": "Callbackurl",
      "type": "string"
    },
    "cameraId": {
      "default": 3,
      "description": "数字人相机机位，0:横屏半身, 1:竖屏半身, 2: 横屏全身, 3: 竖屏全身",
      "title": "Cameraid",
      "type": "integer"
    },
    "driveType": {
      "default": "TEXT",
      "description": "驱动类型, TEXT:文本驱动, VOICE: 音频驱动",
      "enum": [
        "TEXT",
        "VOICE"
      ],
      "title": "Drivetype",
      "type": "string"
    },
    "figureId": {
      "default": null,
      "description": "人像ID",
      "title": "Figureid",
      "type": "string"
    },
    "inputAudioUrl": {
      "default": null,
      "description": "驱动音频URL",
      "title": "Inputaudiourl",
      "type": "string"
    },
    "resolutionHeight": {
      "default": 1280,
      "description": "分辨率:高",
      "title": "Resolutionheight",
      "type": "integer"
    },
    "resolutionWidth": {
      "default": 768,
      "description": "分辨率:宽",
      "title": "Resolutionwidth",
      "type": "integer"
    },
    "subtitleEnable": {
      "default": false,
      "description": "是否启用字幕",
      "title": "Subtitleenable",
      "type": "boolean"
    },
    "text": {
      "default": null,
      "description": "播报内容",
      "title": "Text",
      "type": "string"
    },
    "voiceId": {
      "default": null,
      "description": "音色ID",
      "title": "Voiceid",
      "type": "string"
    }
  },
  "title": "generateDhVideoArguments",
  "type": "object"
}

Baidu Digital Human MCP Server

generateDhVideo

Instructions

样例1：

Input Schema

Input Schema (JSON Schema)

Other Tools from Baidu Digital Human MCP Server

Related Tools

MCP directory API