Media
将位图图像转换为以频谱还原优先的音频，并同时导出音频和一张验证频谱图预览，方便直接对比还原效果。
用三种语言从你的代码中调用此工具。
# 1) Request a presigned URL → returns { uploadUrl, storageKey }
curl -X POST 'https://api.elysiatools.com/api/upload/presign/image-to-spectrogram-audio' \
-H 'Content-Type: application/json' \
-d '{"filename":"imageFile.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 'https://api.elysiatools.com/zh/api/tools/image-to-spectrogram-audio' \
-F 'imageFile=./public/processing/smoke-test-palette.png' \
-F 'durationSeconds=8' \
-F 'sampleRate=44100' \
-F 'outputFormat=wav' \
-F 'minFrequencyHz=200' \
-F 'maxFrequencyHz=12000' \
-F 'frequencyScale=linear' \
-F 'topRowHighFrequency=true' \
-F 'timeSlices=640' \
-F 'frequencyBins=160' \
-F 'resizeMode=stretch' \
-F 'contrast=1.25' \
-F 'threshold=0.05' \
-F 'verificationPalette=magma'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/image-to-spectrogram-audio| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| imageFile | file需先上传 | 是 | — |
| durationSeconds | number | 否 | — |
| sampleRate | select | 否 | — |
| outputFormat | select | 否 | — |
| minFrequencyHz | number | 否 | — |
| maxFrequencyHz | number | 否 | — |
| frequencyScale | select | 否 | — |
| topRowHighFrequency | checkbox | 否 | — |
| timeSlices | number | 否 | — |
| frequencyBins | number | 否 | — |
| resizeMode | select | 否 | — |
| contrast | number | 否 | — |
| threshold | number | 否 | — |
| verificationPalette | select | 否 | — |
HTML 结果
{
"result": "<div>Processed HTML content</div>",
"error": "Error message (optional)",
"message": "Notification message (optional)",
"metadata": {
"key": "value"
}
}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-image-to-spectrogram-audio": {
"name": "image-to-spectrogram-audio",
"description": "将位图图像转换为以频谱还原优先的音频，并同时导出音频和一张验证频谱图预览，方便直接对比还原效果。",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=image-to-spectrogram-audio",
"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": "image-to-spectrogram-audio",
"arguments": {
"imageFile": "./public/processing/smoke-test-palette.png",
"durationSeconds": 8,
"sampleRate": "44100",
"outputFormat": "wav",
"minFrequencyHz": 200,
"maxFrequencyHz": 12000,
"frequencyScale": "linear",
"topRowHighFrequency": true,
"timeSlices": 640,
"frequencyBins": 160,
"resizeMode": "stretch",
"contrast": 1.25,
"threshold": 0.05,
"verificationPalette": "magma"
}
}
}有问题或反馈？请联系 [email protected]