Protoss Voice Effect Generator

🔮 Khala Engine - Apply psionic audio effects to voice recordings using SoX and FFmpeg. Mimics the StarCraft Protoss voice style: deep, resonant, and telepathic.

Architecture: "The Void" (V9)

• Removes the original human voice entirely.
• Processes the signal into a deep, reversed-reverb "shadow" entity.
• Results in a distant, massive, and telepathic sound signature.

Implementations

This repository contains two implementations:

• Python Version - Original implementation using Python subprocess
• Node.js Version - JavaScript implementation using Node.js child_process

Quick Start

Use the provided Makefile for easy setup and usage:

# Install all dependencies
make install

# Run basic tests
make test

# Process audio (requires demo_input.mp3)
make demo

# Clean temporary files
make clean

Installation

System Dependencies

Both implementations require ffmpeg and sox (Sound eXchange).

# macOS with Homebrew
brew install ffmpeg sox

# Ubuntu/Debian
sudo apt install ffmpeg sox

# Windows (using Chocolatey)
choco install ffmpeg sox

Python Version

cd python
pip install -r requirements.txt

Node.js Version

cd nodejs
npm install

Usage

Python Implementation

Run the script on any audio file:

cd python
python3 protoss_fx.py <path_to_audio_file>

Example:

cd python
python3 protoss_fx.py ../recordings/my_voice.mp3

Node.js Implementation

Run the script on any audio file:

cd nodejs
node protoss_fx.js <path_to_audio_file>

Or using npm script:

cd nodejs
npm start <path_to_audio_file>

Example:

cd nodejs
node protoss_fx.js ../recordings/my_voice.mp3

Files are saved as *_psionic.mp3 in the source directory for both implementations.

Algorithm

The current architecture prioritizes a massive, distinctive spatial presence.

1. Shadow Generation: Pitch shift (-2 semitones) + Time stretch (0.9x).
2. Void Layer: Reverse -> Dense Reverb -> Reverse (creates "pre-verb" suction).
3. Mastering: Original voice is discarded. Bass boosted (+5dB), Subsonics cut (<100Hz).

Integration Workflows

ElevenLabs Post-Processing

This tool is designed to be used as a post-processing step for TTS generation. When generating voice content to mimic "Selendis" or other Protoss personas:

1. Generate: Create raw speech using ElevenLabs.
2. Process: Pass the output file immediately through the Protoss effect processor.
3. Result: Use the resulting _psionic.mp3 file as the final asset.

OpenClaw Integration

Each implementation folder contains a SKILL.md file for OpenClaw integration:

• Python: python/SKILL.md
• Node.js: nodejs/SKILL.md

Project Structure

protoss-voice/
├── README.md              # This file
├── LICENSE                # MIT License
├── .gitignore            # Git ignore rules
├── python/               # Python implementation
│   ├── SKILL.md          # OpenClaw skill definition
│   ├── protoss_fx.py     # Main Python script
│   └── requirements.txt  # Python dependencies
└── nodejs/               # Node.js implementation
    ├── SKILL.md          # OpenClaw skill definition
    ├── package.json      # Node.js package config
    └── protoss_fx.js     # Main Node.js script

Contributing

We welcome contributions! Please see our Contributing Guide for detailed information on:

• Development setup
• Code style guidelines
• Testing procedures
• Pull request process

License

MIT License - see LICENSE file for details.

Author

Diego Ghersi - Creator and maintainer of the Protoss Voice Effect Generator.

Contributing

Feel free to submit issues and pull requests!