Pronunciation & Voice Coach

Package (pypi 0.3.0)

uvx mcp-server-pronunciation

Or add to your MCP client config:

{
  "mcpServers": {
    "mcp-server-pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<YOUR_VALUE>",
        "HF_HUB_CACHE": "<YOUR_VALUE>",
        "MCP_PRONUNCIATION_PRELOAD": "<YOUR_VALUE>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<YOUR_VALUE>",
        "TORCH_HOME": "<YOUR_VALUE>"
      }
    }
  }
}

• 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.