This project shows how to prototype a real-time voice AI Android app using Gemini 2.0’s Live API over WebSockets as an open-source proof of concept before committing to full production infrastructure. By combining low-level audio control on Android, duplex audio streaming, and multimodal AI, we built an
Voice AI applications need real-time and reliable audio communication for natural conversations with AI customer service bots, virtual assistants, IVR platforms, and other voice-enabled systems. Choosing the appropriate transport protocol is crucial for teams, as using the wrong one can lead to choppy audio, noticeable delays, and
In this post we are going to explore the concepts we explained in a previous post using a live video call demo, showing the interaction between the components of a web application using WebRTC and Websockets. At the end of the post, we will share the link
With a “learn how” post like this one, as a reader you don’t want a long intro. You just want to get to the point. So simply put, this post will explain how WebRTC and WebSockets can work together to build a chat-based application. How Can Your Application
