# Audio

An MCP server for audio work: it measures loudness, checks specs, cleans recordings, applies EQ, cuts files, and converts formats.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 329
- Author: audiojs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/audiojs/audio
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/mcp/audio

## What it does

Audio gives an agent MCP tools for loading, analyzing, editing, playing, and converting sound. It can measure loudness, spectrum, beats, pitch, chords, and key; check audio against a named specification; remove noise; apply EQ; trim clips; and save a processed file. WebAssembly codecs handle formats without FFmpeg.

The project uses stream-first processing, virtual edits with undo, and paged data for large files. It also includes a CLI for batch work and scripting. The MCP process starts with `npx -y audio`, with setup commands listed for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and other supported clients.

In Claude Code, install it with `claude mcp add audio -- npx -y audio`. FFmpeg is not required, so its absence does not block the server’s listed audio operations.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add audio -- npx -y audio
```

### Codex

**Platform CLI**
```bash
codex mcp add audio -- npx -y audio
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "audio": {
            "command": "npx",
            "args": [
                "-y",
                "audio"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "audio": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "audio"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add audio npx -y audio
```

## When to use it
- measure loudness and true peak
- prepare a voice recording for a podcast
- trim an audio file and save a new copy
- identify BPM, key, or chords
- apply denoise and EQ to a recording

## Example prompts
- Make `~/Desktop/interview.m4a` podcast-ready and report its loudness before and after processing.
- Check `voice.wav` against podcast requirements, clean it, and save the result as `clean.mp3`.
- Trim `song.mp3`, normalize its level, and describe what changed.

## 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
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
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