This bot will accept the audio file along with variables such as the target model and pitch shift variable. It will serve the file to the input destination and it will monitor the output destination. It will reject too many arguments, incorrect models, and monitor a whitelist given the conversion server runs on my personal hardware.
The contents of the backend folder should go inside of your RBVC installation.
This is RBVC (AI Speech-to-Speech Voice Synthesis): https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI