Pronunciation & Voice Coach MCP Server

Name: Pronunciation & Voice Coach MCP Server
Author: io.github.JuhongPark

io.github.JuhongPark/pronunciation

Repository Registry

What is the Pronunciation & Voice Coach MCP server?

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

How to install Pronunciation & Voice Coach

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

MCP_PRONUNCIATION_MODEL
faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo.
HF_HUB_CACHE
Override Hugging Face Hub cache directory where Whisper weights are stored.
MCP_PRONUNCIATION_PRELOAD
Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests.
MCP_PRONUNCIATION_AUDIO_RETENTION
Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection.
TORCH_HOME
Override PyTorch cache directory for optional wav2vec2 forced-alignment weights.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

VS Code

.vscode/mcp.json

{
  "servers": {
    "pronunciation": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_MCP_PRONUNCIATION_MODEL>",
        "HF_HUB_CACHE": "<YOUR_HF_HUB_CACHE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_MCP_PRONUNCIATION_PRELOAD>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION>",
        "TORCH_HOME": "<YOUR_TORCH_HOME>"
      }
    }
  }
}

Claude Code

claude mcp add pronunciation --env MCP_PRONUNCIATION_MODEL=<YOUR_MCP_PRONUNCIATION_MODEL> --env HF_HUB_CACHE=<YOUR_HF_HUB_CACHE> --env MCP_PRONUNCIATION_PRELOAD=<YOUR_MCP_PRONUNCIATION_PRELOAD> --env MCP_PRONUNCIATION_AUDIO_RETENTION=<YOUR_MCP_PRONUNCIATION_AUDIO_RETENTION> --env TORCH_HOME=<YOUR_TORCH_HOME> -- uvx mcp-server-pronunciation