# FunASR

FunASR turns local audio files into text through an MCP tool. Use it to transcribe a meeting or voice memo from your AI coding client.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 20804
- Author: modelscope
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/modelscope/FunASR/tree/HEAD/examples/mcp_server
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/funasr

## What it does

The server exposes `transcribe_audio`, which takes an audio file path and returns recognized speech as text. It accepts WAV, MP3, FLAC, M4A, and OGG files. You can let it identify the language or provide a code such as `en` or `yue`. Longer recordings are split into speech segments; timestamps appear when the selected model provides them.

Inference runs locally, so an API key is not needed. Choose a model with `FUNASR_MODEL` and a device with `FUNASR_DEVICE`; supported options include `cpu`, `cuda`, and `mps`. CPU is the default, so check that this setting fits your machine. For a Python setup, install `funasr`; Claude Code can also launch the published Docker image with the command below.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add mcp_server -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2
```

### Codex

**Platform CLI**
```bash
codex mcp add mcp_server -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mcp_server": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/modelscope/funasr-mcp:0.1.2"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mcp_server": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/modelscope/funasr-mcp:0.1.2"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add mcp_server docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2
```

## When to use it
- transcribe a meeting recording
- turn a voice memo into text
- extract speech from an MP3 or FLAC file
- split a long recording into speech segments before recognition

## Example prompts
- Transcribe the meeting recording at `~/Downloads/meeting.wav`.
- Turn `~/voice_note.m4a` into text.
- Tell me what is said in `/path/to/interview.mp3`.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74559
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md