Pronunciation & Voice Coach
Local MCP voice coach with English pronunciation, grammar, and fluency feedback.
Open the source (opens github.com) https://github.com/juhongpark/mcp-server-pronunciation
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.JuhongPark.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
mcp-server-pronunciation@0.3.0
From the server's entry in the official MCP Registry
Settings it asks for
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.
Related
-
Speech AI - Pronunciation, STT & TTS
MCP serversPronunciation scoring, speech-to-text, and text-to-speech for language learning
-
Voice Coach
MCP serversGives Claude ears: local pitch, pronunciation and public-speaking analysis for voice coaching.
voice-coach-mcp@0.1.1 -
Speakeroo speaking coach
MCP serversAI speaking coach: feedback on speeches from text or audio, plus topics, pronunciation and rubrics.
-
Brainiall Pronunciation
MCP serversPronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.
-
Onepin
MCP serversAI Voice Production Agent: picks from 30+ TTS models, fixes pronunciation, validates every line.
-
soundbox
MCP serversFree, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-speech and voice cloning on your own GPU (Stable Audio, ACE-Step and more). No account, no credits, offline. Windows/macOS app, HTTP API and a 21-tool MCP server for Claude Code and Cursor.
git clone https://github.com/HamSanders/soundbox.git