FunASR

Level AMCP ecosystemNot an MCP ServerLocal

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Overview

FunASR is an open-source industrial speech recognition toolkit for offline, streaming, and edge deployment. It covers ASR, VAD, punctuation, and speaker-diarization pipelines, plus emotion and audio-event models, and can serve through OpenAI-compatible APIs or an MCP server for AI agents. It supports training, inference, and deployment across speech scenarios.

⭐ 21.1kAI GenerationPythonRepo ↗Updated 2026-11-19

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "funasr-mcp": {
      "command": "npx",
      "args": [
        "ghcr.io/modelscope/funasr-mcp:0.1.2"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/modelscope/FunASR

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "funasr-mcp": {
      "command": "npx",
      "args": [
        "ghcr.io/modelscope/funasr-mcp:0.1.2"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers