🎵 PhantomMusic

Neural data sonification for the Phantom BCI stack.

Transform brain signals into an interactive musical experience. PhantomMusic streams neural data from PhantomLink and converts neuron firing patterns into real-time synthesized music.

✨ Features

• 🎹 Neural Orchestra — 142 neurons mapped to 4 instrument groups (synth, drums, bass, pad)
• 🎯 Target Chords — MC_Maze targets trigger harmonic chord progressions
• 📊 Live Visualization — Real-time neural activity display with color-coded neuron groups
• 🔬 Diagnostic Tools — Mapping inspector and scientific target protocols
• 🎛️ Audio Controls — Multiple scales (pentatonic, minor, major, blues), volume, mute
• 🔗 PhantomLink Integration — Direct WebSocket streaming from neural datasets

🚀 Quick Start

# Install dependencies
npm install

# Start dev server
npm run dev

Open http://localhost:5173 and enter a PhantomLink session code.

🎼 How It Works

Neuron Group	Channels	Instrument	Sound
Synth	0-35	PolySynth	Melodic leads
Drums	36-70	MembraneSynth + MetalSynth	Kick & hi-hat
Bass	71-105	MonoSynth	Deep bass lines
Pad	106-141	FMSynth	Ambient textures

When the target position changes in the dataset, a corresponding chord plays:

• Target 0 → C Major
• Target 1 → D Major
• Target 2 → E Major

🛠️ Tech Stack

• Vite + React 19 + TypeScript
• Tone.js — Web Audio synthesis
• Zustand — State management
• Framer Motion — Animations
• Tailwind CSS v4 — Styling
• msgpack-lite — Binary WebSocket decoding

📡 PhantomLink Connection

PhantomMusic connects to PhantomLink's binary WebSocket stream:

wss://phantomlink.fly.dev/stream/binary/{sessionCode}

Messages are MessagePack-encoded StreamPacket objects containing:

• spike_data.spike_counts — 142-channel spike counts
• kinematics.velocity — Movement velocity
• intention.target — Predicted target (0, 1, or 2)

🎨 Part of the Phantom Stack

Project	Description
PhantomCore	C++ real-time neural decoder
PhantomLink	Python streaming server
PhantomLoop	React visualization dashboard
PhantomX	PyTorch neural network training
PhantomSpecs	Protocol specifications
PhantomZip	Rust neural compression codec
PhantomMusic	🎵 Neural sonification (you are here)

🙏 Acknowledgments

This project was developed with assistance from AI coding assistants and workflows:

• Claude Opus 4.5 (Anthropic)
• Claude Sonnet 4.5 (Anthropic)
• Gemini 3.0 Pro (Google)
• Grok code fast 1 (xAI)

MIT