Pronunciation & Voice Coach

MCP ServerMCP Registry官方收录

io.github.JuhongPark/pronunciation · v0.3.0

Local MCP voice coach with English pronunciation, grammar, and fluency feedback.

源仓库 ↗

概览

Pronunciation & Voice Coach 是一个MCP Server，收录自官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。

安装

选择你的平台查看安装方式

{
  "mcpServers": {
    "pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ]
    }
  }
}

环境变量

MCP_PRONUNCIATION_MODEL可选

faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo.

HF_HUB_CACHE可选

Override Hugging Face Hub cache directory where Whisper weights are stored.

MCP_PRONUNCIATION_PRELOAD可选

Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests.

MCP_PRONUNCIATION_AUDIO_RETENTION可选

Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection.

TORCH_HOME可选

Override PyTorch cache directory for optional wav2vec2 forced-alignment weights.

统一 Manifest

{
  "id": "io.github.JuhongPark/pronunciation",
  "type": "mcp-server",
  "version": "0.3.0",
  "displayName": "Pronunciation & Voice Coach",
  "description": "Local MCP voice coach with English pronunciation, grammar, and fluency feedback.",
  "repository": {
    "url": "https://github.com/JuhongPark/mcp-server-pronunciation",
    "source": "github"
  },
  "distribution": {
    "packages": [
      {
        "registryType": "pypi",
        "identifier": "mcp-server-pronunciation",
        "version": "0.3.0",
        "runtimeHint": "uvx",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "MCP_PRONUNCIATION_MODEL",
            "description": "faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo."
          },
          {
            "name": "HF_HUB_CACHE",
            "description": "Override Hugging Face Hub cache directory where Whisper weights are stored."
          },
          {
            "name": "MCP_PRONUNCIATION_PRELOAD",
            "description": "Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests."
          },
          {
            "name": "MCP_PRONUNCIATION_AUDIO_RETENTION",
            "description": "Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection."
          },
          {
            "name": "TORCH_HOME",
            "description": "Override PyTorch cache directory for optional wav2vec2 forced-alignment weights."
          }
        ]
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.JuhongPark/pronunciation",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.JuhongPark%2Fpronunciation/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}

Pronunciation & Voice Coach

概览

安装

环境变量

相关资源

RFP.ai

xenarch-mcp

api

agent-lsp

hostinger-api-mcp

Unterm

统一 Manifest