FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Pronunciation & Voice Coach
Verified · 8 days agoLocal MCP voice coach with English pronunciation, grammar, and fluency feedback.
Install
claude mcp add pronunciation -- uvx mcp-server-pronunciation
Our take
A local voice coach that lets you talk to your assistant by mic and get pronunciation, grammar, and fluency feedback in the same turn — with surprisingly deep drill mode (per-word IPA alignment, minimal pairs, prosody checks, Korean-L1 hints). Everything runs on-device via faster-whisper; audio never leaves your machine. Honest about its limits with a prominent accuracy disclaimer. Expect a ~150 MB model download and a working mic; it's a practice tool, not an assessment.
Verification record
- 8 days ago
- 2
- 3 mo ago
- no
- MIT
- 2026-05-03
More in media
browse all →Figma-Context-MCP
Verified · 8 days agoGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.
openshorts
Verified · 16 days agoTurn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
claude-real-video
Verified · 16 days agoLet any LLM watch a video locally — and search everything it has ever watched.
Figma MCP Server
Verified · 11 days agoThe Figma MCP server brings Figma design context directly into your AI workflow.
voicemode
Verified · 9 days agoNatural voice conversations for AI assistants - STT/TTS via MCP