Discussions

I'm looking to integrate a dynamic live streaming Avatar into my web application, featuring both voice and text capabilities, including Speech-to-Text (STT) and Text-to-Speech (TTS). My goal is for the avatar to respond based on a knowledge base, utilizing the default avatars provided. However, the live-streaming-demo repository on GitHub lacks specific instructions for my use case. Could you please provide guidance on achieving this and recommend an appropriate subscription plan for incorporating this feature into my project?