Getting Started

Requirements

  • Python 3.10 or later
  • An MCP-compatible AI assistant (Claude Desktop, Claude Code, Cursor, or others)
  • Audio files to analyze (WAV, FLAC, MP3, AIFF, OGG supported)

Install Phantom

$ install

curl -sSL https://fadelab.net/install | bash

The installer detects your OS, installs dependencies, and configures the MCP server automatically. You can choose core-only (~50MB) or full install with stem separation and reference matching (~2.5GB).

Verify the installation:

$ verify

phantom —version

Try it without installing

Don’t want to commit to a full install yet? Run Phantom directly with uvx:

$ try without installing

uvx phantom-audio

Optional extras

Install only what you need:

$ optional extras

# Stem separation (Demucs, ~2GB) pip install phantom-audio[separation] # Reference matching pip install phantom-audio[matching] # Fix and apply processing tools pip install phantom-audio[processing] # Everything pip install phantom-audio[separation,matching,processing]

Configure your AI assistant

Phantom connects to your AI assistant via MCP (Model Context Protocol). You need to tell your assistant where to find the Phantom server.

See the full configuration guide: Configuring AI Assistants

Quick setup for Claude Code:

Claude Code

claude mcp add phantom — phantom-mcp

Quick setup for Claude Desktop — add to your claude_desktop_config.json:

claude_desktop_config.json

{ "mcpServers": { "phantom": { "command": "phantom-mcp", "args": [] } } }

Run your first analysis

Once connected, ask your AI assistant to analyze an audio file. Use a natural language prompt — no special syntax needed.

Your prompt:

Analyze the loudness of my mix at mix-v3.wav

Phantom output:

Loudness Analysis Integrated: -14.2 LUFS True peak: -0.8 dBTP Range (LRA): 7.3 LU Short-term: -12.1 LUFS (max) Momentary: -9.4 LUFS (max)

Your AI assistant interprets this and responds with something like:

Your mix is at -14.2 LUFS integrated, which is loud for streaming platforms (Spotify targets -14, Apple Music targets -16). The true peak at -0.8 dBTP is cutting it close — most platforms require -1.0 dBTP or lower. You have 7.3 LU of dynamic range, which is moderate. I’d suggest pulling the limiter back slightly to get true peak below -1.0 dBTP.

Pro tip

Start with analyze the loudness of [file] or run a full diagnostic on [file] as your first prompt. These give comprehensive results that demonstrate Phantom’s capabilities.

What to try next

  • Full diagnostic: “Run a full diagnostic on vocals.wav” — measures everything at once
  • Problem detection: “Check my mix for problems” — finds clipping, mud, sibilance, resonances
  • Fix problems: “Fix the issues found in vocals.wav” — auto-applies corrective EQ and filtering
  • Comparison: “Compare my mix to a reference track at reference.wav” — A/B against a professional master
  • Batch analysis: “Analyze all stems in my session folder” — process up to 50 files in parallel

Next steps