加载中…
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
FunASR 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 67/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 FunASR 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-07-26T12:13:35.527546Z",
"publishedAt": "2026-07-26T12:13:35.527546Z",
"statusChangedAt": "2026-07-26T12:13:35.527546Z"
}
},
"server": {
"name": "io.github.modelscope/funasr-mcp",
"title": "FunASR",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.1.2",
"packages": [
{
"transport": {
"type": "stdio"
},
"identifier": "ghcr.io/modelscope/funasr-mcp:0.1.2",
"runtimeHint": "docker",
"registryType": "oci",
"runtimeArguments": [
{
"name": "--mount",
"type": "named",
"value": "type=bind,src={audio_directory},dst=/audio,readonly",
"variables": {
"audio_directory": {
"format": "filepath",
"isRequired": true,
"description": "Host directory containing audio files. Use /audio/<file> when calling the tool.",
"placeholder": "/path/to/audio"
}
},
"description": "Mount the host audio directory read-only at /audio in the container."
},
{
"name": "--mount",
"type": "named",
"value": "type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope",
"description": "Persist downloaded ModelScope model files between container runs."
}
]
}
],
"repository": {
"id": "569959091",
"url": "https://github.com/modelscope/FunASR",
"source": "github",
"subfolder": "examples/mcp_server"
},
"websiteUrl": "https://github.com/modelscope/FunASR/tree/main/examples/mcp_server",
"description": "Transcribe local audio with FunASR and SenseVoice using private, on-device inference."
}
}