Media

鼓替换器

检测鼓轨或完整混音中的底鼓、军鼓和踩镲鼓击，用你自己的采样（或内置合成采样）叠加或替换。

file· 文件结果打开工具

快速开始

用三种语言从你的代码中调用此工具。

cURL

# 1) Request a presigned URL → returns { uploadUrl, storageKey }
curl -X POST 'http://127.0.0.1:3003/api/upload/presign/drum-replacer' \
  -H 'Content-Type: application/json' \
  -d '{"filename":"audioFile.ext","contentType":"application/octet-stream","size":12345}'
curl -X POST 'http://127.0.0.1:3003/api/upload/presign/drum-replacer' \
  -H 'Content-Type: application/json' \
  -d '{"filename":"kickSample.ext","contentType":"application/octet-stream","size":12345}'
curl -X POST 'http://127.0.0.1:3003/api/upload/presign/drum-replacer' \
  -H 'Content-Type: application/json' \
  -d '{"filename":"snareSample.ext","contentType":"application/octet-stream","size":12345}'
curl -X POST 'http://127.0.0.1:3003/api/upload/presign/drum-replacer' \
  -H 'Content-Type: application/json' \
  -d '{"filename":"hatSample.ext","contentType":"application/octet-stream","size":12345}'

# 2) PUT the file bytes directly to the presigned uploadUrl
curl -X PUT '<presigned uploadUrl>' \
  --data-binary @/path/to/file.ext

# 3) Call the tool, passing the returned storageKey for each file field
curl -X POST 'http://127.0.0.1:3003/zh/api/tools/drum-replacer' \
  -F 'audioFile=uploads/2026/01/01/your-tool-1700000000000-abc123.ext' \
  -F 'targets=kick,snare,hats' \
  -F 'kickSample=uploads/2026/01/01/your-tool-1700000000000-abc123.ext' \
  -F 'snareSample=uploads/2026/01/01/your-tool-1700000000000-abc123.ext' \
  -F 'hatSample=uploads/2026/01/01/your-tool-1700000000000-abc123.ext' \
  -F 'blendMode=layer' \
  -F 'sampleLevel=70' \
  -F 'duckDepthDb=12' \
  -F 'sensitivity=medium' \
  -F 'outputFormat=wav'

API 参考

以 JSON 形式 POST 提交输入参数。文件类型参数需先单独上传。

请求端点

HTTP

POST http://127.0.0.1:3003/zh/api/tools/drum-replacer

请求参数

参数名	类型	必填	说明
audioFile	file需先上传	是	—
targets	select	是	—
kickSample	file需先上传	否	—
snareSample	file需先上传	否	—
hatSample	file需先上传	否	—
blendMode	select	是	—
sampleLevel	number	否	—
duckDepthDb	number	否	—
sensitivity	select	是	—
outputFormat	select	是	—

文件类型参数需先通过 POST /upload/drum-replacer 上传，再将返回的 filePath 传入对应的文件字段。

响应格式

文件结果

JSON

{
  "filePath": "/public/processing/randomid.ext",
  "fileName": "output.ext",
  "contentType": "application/octet-stream",
  "size": 1024,
  "metadata": {
    "key": "value"
  },
  "error": "Error message (optional)",
  "message": "Notification message (optional)"
}

MCP 集成

将此工具加入你的 Model Context Protocol 服务，让 AI 智能体可以列出并调用它。

服务配置

将以下内容加入你的 MCP 客户端配置：

mcp.json

{
  "mcpServers": {
    "elysiatools-drum-replacer": {
      "name": "drum-replacer",
      "description": "检测鼓轨或完整混音中的底鼓、军鼓和踩镲鼓击，用你自己的采样（或内置合成采样）叠加或替换。",
      "baseUrl": "http://127.0.0.1:3003/mcp/sse?toolId=drum-replacer",
      "command": "",
      "args": [],
      "env": {},
      "isActive": true,
      "type": "sse"
    }
  }
}

列出可用工具

连接到 SSE 端点后，列出已开放的工具：

tools/list

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/list"
}

调用此工具

通过工具 id 调用，参数由其参数表构建：

tools/call

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "drum-replacer",
    "arguments": {
  "audioFile": "https://example.com/file.ext",
  "targets": [
    "kick",
    "snare",
    "hats"
  ],
  "kickSample": "https://example.com/file.ext",
  "snareSample": "https://example.com/file.ext",
  "hatSample": "https://example.com/file.ext",
  "blendMode": "layer",
  "sampleLevel": 70,
  "duckDepthDb": 12,
  "sensitivity": "medium",
  "outputFormat": "wav"
}
  }
}

可用逗号分隔的 toolId 在一个会话中串联多个工具，例如 /mcp/sse?toolId=png-to-webp,jpg-to-webp,gif-to-webp（最多 20 个）。

文件参数仅支持公开的文件链接 URL（https://…）。不支持本地路径、data: URI 和 Base64 字符串。

有问题或反馈？请联系 [email protected]