coqui/xtts · I am looking to develop an AI-powered conversational interface for Speech-to-Speech interaction

Hello everyone, I'm looking to develop an English practice application utilizing AI technology. The main feature I envision for this app is Speech-to-Speech interaction with AI. However, I'm unsure about how to proceed with building such an app. I understand the importance of Text-to-Speech (TTS) and Speech-to-Text (STT) functionalities, but I prefer not to rely on third-party APIs. Instead, I aim to run these APIs on my local server. Can anyone provide guidance on how to achieve this? I have experience building mobile apps using Flutter, but implementing the conversational voice feature with AI is where I'm seeking assistance.