Hello,

I wanted to finetune StyleTTS 2 with my own voice and it was very tedious to create the training data by hand. I could not find an application specifically to create this kind of voice training data, so I made my own. I have been working on this for about a week so it’s still a work in progress. Please feel free to add ideas, suggestions, or requests.

Here is the description:

Phonotate.App is a local, open-source Electron app built with React designed to simplify creating training data for StyleTTS 2 and voice cloning models. Phonotate provides a seamless workflow for recording, analyzing, and managing voice samples. Whether you use open-source backend services or OpenAI APIs, this app ensures that all your data remains secure and within your control.

You can see screenshots of the application in action on the README.

https://github.com/LoganRickert/Phonotate.App