Media
清除字幕中的听障（SDH）噪声：[APPLAUSE]、(engine rumbles) 等括注音效，JOHN:、NARRATOR - 等说话人标签，♪ ♫ 音符行——并删除清理后留下的空 cue。
用三种语言从你的代码中调用此工具。
curl -X POST 'https://api.elysiatools.com/zh/api/tools/srt-sdh-annotation-cleaner' \
-H 'Content-Type: application/json' \
-d '{"subtitleText":"1\n00:00:01,000 --> 00:00:03,000\n♪ [GENTLE PIANO MUSIC] ♪\n\n2\n00:00:03,500 --> 00:00:05,500\n[ENGINE RUMBLING]\n\n3\n00:00:06,000 --> 00:00:08,000\nJOHN: We need to talk.\n\n4\n00:00:08,500 --> 00:00:10,500\n(quietly, to himself)\nThis is not good.","cleanMode":"standard","removeSpeakers":true,"removeMusicNotes":true,"keepLyricText":false,"outputFormat":"srt"}'以 JSON 形式 POST 提交输入参数。文件类型参数需先单独上传。
POST https://api.elysiatools.com/zh/api/tools/srt-sdh-annotation-cleaner| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| subtitleText | textarea | 是 | — |
| cleanMode | select | 否 | — |
| removeSpeakers | checkbox | 否 | — |
| removeMusicNotes | checkbox | 否 | — |
| keepLyricText | checkbox | 否 | — |
| outputFormat | select |
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。
将以下内容加入你的 MCP 客户端配置：
{
"mcpServers": {
"elysiatools-srt-sdh-annotation-cleaner": {
"name": "srt-sdh-annotation-cleaner",
"description": "清除字幕中的听障（SDH）噪声：[APPLAUSE]、(engine rumbles) 等括注音效，JOHN:、NARRATOR - 等说话人标签，♪ ♫ 音符行——并删除清理后留下的空 cue。",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=srt-sdh-annotation-cleaner",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}连接到 SSE 端点后，列出已开放的工具：
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}通过工具 id 调用，参数由其参数表构建：
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "srt-sdh-annotation-cleaner",
"arguments": {
"subtitleText": "1\n00:00:01,000 --> 00:00:03,000\n♪ [GENTLE PIANO MUSIC] ♪\n\n2\n00:00:03,500 --> 00:00:05,500\n[ENGINE RUMBLING]\n\n3\n00:00:06,000 --> 00:00:08,000\nJOHN: We need to talk.\n\n4\n00:00:08,500 --> 00:00:10,500\n(quietly, to himself)\nThis is not good.",
"cleanMode": "standard",
"removeSpeakers": true,
"removeMusicNotes": true,
"keepLyricText": false,
"outputFormat": "srt"
}
}
}有问题或反馈？请联系 [email protected]
| 否 |
| — |
文本结果
{
"result": "Processed text content",
"error": "Error message (optional)",
"message": "Notification message (optional)",
"metadata": {
"key": "value"
}
}