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
Expert WebRTC testing is what separates functional real-time applications from reliable ones. A platform that works for two developers on the same high-speed office network can quickly fall apart when hundreds of users try to join simultaneously from coffee shops, firewalled corporate networks, and crowded classrooms. While
Unlike traditional web applications with simple request-response patterns, real-time communication platforms require a cohesive ecosystem and sophisticated WebRTC tech stack to handle live media streams, manage peer connections, ensure low latency, and have the capability to scale to large numbers of concurrent users. Selecting the right WebRTC
Earlier this month, our CTO Alberto Gonzalez and I descended upon Las Vegas for AWS re:Invent 2025. As an AWS Partner working daily with AWS services to build real-time voice, video, and AI systems, re:Invent is more than a conference for us. It’s a chance to validate
