Open teddybear082 opened 3 weeks ago
There is actually already a basic web server and swagger that starts up with the app, and you can even generate audio using it. It's not documented yet since its very much still a WIP, but its on the todo list.
If you have a specific use case or app you want to integrate with, let me know.
Thank you! Will try it out!
This seems like a great project! I am involved in several AI projects that use voice generation, is it in your plans to add a web server (REST API / websockets) by any chance that could load a voice model or audio effect model and generate a voice or sound file?