Pronunciation & Voice Coach MCP Server

by juhongparkio.github.JuhongPark/pronunciationv0.3.0

Local English voice coach with pronunciation, grammar, fluency and phoneme-level feedback, practice drills and learner-profile hints.

3Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Slowing5mo ago

Install Pronunciation & Voice Coach MCP server

claude mcp add pronunciation -- uvx mcp-server-pronunciation

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

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

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

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "pronunciation": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

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

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
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.