Modelscope FunASR
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
FreeOpen source
What you get
Modelscope FunASR is a free, open-source MCP server published on GitHub by modelscope.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
GitHub stars: 20,795
License: MIT (free to use)
Language: Python
Topics: asr, audio, chinese, emotion-recognition, funasr, mcp-server, multilingual-asr, openai-compatible-api
Last updated: 2026-10-21
How to get it: open the repository on GitHub, read the README and follow the setup steps. HEEEXY lists it in the Lab because it is popular, actively maintained and openly licensed.
More for mcp servers
- Gemini CLI: An open-source AI agent that brings the power of Gemini directly into your terminal.
- Morluto Rea: Reverse engineer anything with agents, from app behavior down to native binaries.
- Scrapling: A Web Scraping framework that handles everything from a single request to a full-scale crawl!