Soundstorm is a cutting-edge AI-powered audio manipulation application designed to provide a rich yet simplified experience for sound designers, algorithmic composers, and experimental audio enthusiasts. From sample pack creation and algorithmic composition to AI text-to-audio and onscreen ChatGPT, Soundstorm is a sonic powerhouse.
Clone the repository and navigate into the project directory. Run the following command to install all the necessary packages:
pip install pedalboard pydub replicate midiutil soundfile openai numpy pygame
You'll need to have API keys for both Replicate and OpenAI:
Add these keys in the appropriate sections within the application before running it.
After installing the prerequisites and obtaining the API keys, you can run the application using:
python Soundstorm.py
This is SUPER rough. Currently, it only exists as a Python script and has only been tested on 2 different Macs. It is more or less a working prototype with a super stripped-down GUI. It can be buggy and does require finagling. Also things definitely need to be cleaned up, labeled better, etc etc. I could use assistance with this!
Contributions are welcome! This is the work of an amateur. Would love to see it fleshed out!
For support and feature requests, please open an issue on this repository.
This project is licensed under the MIT License.