MCP Directory
Back

FunASR

by modelscope · Python · ★ 18,636

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

#asr#audio#chinese#emotion-recognition#funasr#mcp-server#multilingual-asr#openai-compatible-api#paraformer#punctuation#pytorch#real-time#speaker-diarization#speech-recognition#speech-to-text#streaming-asr#transcription#vllm#voice-activity-detection#whisper-alternative

Install

pip install git+https://github.com/modelscope/FunASR.git

Auto-generated from the repo's primary language — check the repo's own README for its exact install instructions.

Claude Desktop config

A starting point for your claude_desktop_config.json (auto-generated — the repo's README may specify a published package name or required env vars):

{
  "mcpServers": {
    "funasr": {
      "command": "uvx",
      "args": [
        "git+https://github.com/modelscope/FunASR.git"
      ]
    }
  }
}

From the README

([简体中文](./README_zh.md)|English|[日本語](./README_ja.md)|[한국어](./README_ko.md)) Industrial speech recognition. Up to 340x realtime, 26x faster than Whisper. 50+ languages. Speaker diarization · Emotion detection · Streaming · One API call Quick Start · Colab · Benchmark · Model selection · Migration guide · Use cases · Deployment matrix · Models · Agent Integration · Docs · Contribute |---|---|---| | Top speed | **340x realtime** (Fun-ASR-Nano + vLLM) | 13x realtime | ~1x realtime | | Speaker ID | ✅ Built-in | ❌ Needs pyannote | ✅ Extra cost | | Emotion | ✅ via SenseVoi…
Read full README on GitHub →

Related ai & ml servers