Pronunciation & Voice Coach

io.github.JuhongPark/pronunciation·v0.3.0·Other

Quality Score

/100

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

Repository →

§01 Install

Claude Desktop (uvx)

{
  "mcpServers": {
    "pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ],
      "env": {
        "MCP_PRONUNCIATION_MODEL": "<mcp_pronunciation_model>",
        "HF_HUB_CACHE": "<hf_hub_cache>",
        "MCP_PRONUNCIATION_PRELOAD": "<mcp_pronunciation_preload>",
        "MCP_PRONUNCIATION_AUDIO_RETENTION": "<mcp_pronunciation_audio_retention>",
        "TORCH_HOME": "<torch_home>"
      }
    }
  }
}

§02 Environment variables

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.

§03 MCP Quality Score · methodology

freshness

completeness

installability

documentation

stability

§04 Alternatives in Other

agency.lona/trading

AI-powered trading strategy development: backtesting, market data, and portfolio analysis

ABMeter

ai.abmeter/abmeter

Feature flagging and A/B testing platform with AI-first experimentation workflows.

AdAdvisor MCP Server

ai.adadvisor/mcp-server

Query Meta Ads performance data — accounts, campaigns, ad sets, ads, metrics & settings.