AudioSaR - Audio Slowed and Reverb

An automated audio processing pipeline for creating lo-fi/slowed+reverb remixes with animated waveform visualizations.

Features

• Audio Processing: Apply pitch shifting, reverb, and normalization to create lo-fi effects
• Batch Processing: Process multiple audio files at once
• Waveform Visualization: Generate animated waveform videos for YouTube uploads
• Web Interface: Easy-to-use Streamlit interface with real-time preview
• Flexible Controls: Adjust pitch shift, reverb room size, wet level, and normalization settings
• Multiple Formats: Support for MP3, WAV, M4A, and AAC audio files

Quick Start

Prerequisites

1. Python 3.8+
2. FFmpeg (required for audio/video processing)

Install FFmpeg:

Windows (Chocolatey):

choco install ffmpeg

Or download from: https://ffmpeg.org/download.html

macOS (Homebrew):

brew install ffmpeg

Linux (apt):

sudo apt-get install ffmpeg

Installation

1. Clone the repository:

git clone https://github.com/yourusername/AudioSaR.git
cd AudioSaR

2. Create a virtual environment:

python -m venv venv

3. Activate virtual environment:

# Windows
venv\Scripts\activate

# Mac/Linux
source venv/bin/activate

4. Install dependencies:

pip install -r requirements.txt

Usage

1. Start the Streamlit app:

streamlit run app.py

2. Open your browser to http://localhost:8501

3. Upload audio files (MP3, WAV, M4A, or AAC)

4. Adjust effect parameters in the sidebar:

   • Pitch Shift: -6 to +6 semitones (default: -2 for lo-fi effect)
   • Reverb Room Size: 0.0 to 1.0 (default: 0.5)
   • Reverb Wet Level: 0.0 to 1.0 (default: 0.3)
   • Normalization: Target volume in dBFS (default: -14.0)

5. Click Process to apply effects to individual files or Process All for batch processing

6. Generate waveform videos for YouTube uploads (optional)

Project Structure

AudioSaR/
├── app.py                 # Streamlit web interface
├── audio_processor.py     # Audio processing module (pitch shift, reverb, normalization)
├── video_generator.py     # Video generation module (waveform visualization)
├── requirements.txt       # Python dependencies
├── input_audio/          # Upload your audio files here
├── output_audio/         # Processed audio outputs (for SoundCloud, etc.)
└── output_videos/        # Generated waveform videos (for YouTube)

Audio Processing Pipeline

1. Load Audio: Supports MP3, WAV, M4A, AAC formats
2. Pitch Shift: Adjust pitch using semitone shifts (negative values = lower/slower)
3. Reverb: Apply high-quality reverb using Spotify's Pedalboard library
4. Normalize: Consistent volume across all tracks
5. Export: Save processed audio to output_audio/

Video Generation

Two methods available:

• SeeWav (default): Facebook Research's waveform visualization tool
• FFmpeg showwaves: Built-in FFmpeg filter with customizable modes

Generates animated waveform videos at 1920x1080 resolution (30 FPS) for YouTube uploads.

Dependencies

• streamlit: Web interface
• pydub: Audio manipulation and pitch shifting
• pedalboard: Professional-grade audio effects (Spotify's library)
• numpy: Numerical processing
• seewav: Waveform visualization
• torch/torchaudio: Deep learning framework for audio processing

File Size Limits

• Maximum upload size: 100 MB per file
• Recommended audio length: 2-5 minutes for optimal processing time

Troubleshooting

"FFmpeg not found" error:

• Ensure FFmpeg is installed and available in your system PATH
• Restart your terminal/command prompt after installation

"SeeWav not found" error:

• Reinstall dependencies: pip install -r requirements.txt
• Try FFmpeg video generation method instead

Processing fails:

• Check that audio files are not corrupted
• Ensure sufficient disk space in output directories
• Verify FFmpeg installation: ffmpeg -version

License

MIT License - See LICENSE file for details

Contributing

Contributions welcome! Please open an issue or submit a pull request.