FunASR

modelscope/FunASR

★ 16,247 stars Python 🤖 AI/LLM Updated 2d ago

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "funasr": {
      "command": "uvx",
      "args": [
        "funasr"
      ]
    }
  }
}

Or install with pip: pip install funasr

README Excerpt

([简体中文](./README_zh.md)|English|[日本語](./README_ja.md)|[한국어](./README_ko.md)) <p align="center"> <a href="https://github.com/modelscope/FunASR"><img src="https://svg-banners.vercel.app/api?type=origin&text1=FunASR🤠&text2=💖%20A%20Fundamental%20End-to-End%20Speech%20Recognition%20Toolkit&width=800&height=210" alt="FunASR"></a>

Tools (1)

benchmark

Topics

asraudiochineseemotion-recognitionmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-timespeaker-diarizationspeech-recognitionspeech-to-textstreaming-asr

FunASR

Quick Install

README Excerpt

Tools (1)

Topics

Related AI/LLM Servers