Building Viva: A Real-Time AI Interview Coach with Gemini Live API

TL;DR : I built Viva, a real-time AI interview coach that listens to your answers via bidirectional audio streaming and watches your body language through your webcam — all powered by Google's Gemini Live API and Vision API, deployed on Cloud Run. The Problem Job seekers practice interviews alone with zero feedback. You can record yourself on your phone and watch it back, but that doesn't tell you about your filler words, pacing, eye contact, or posture in real-time. Human coaches cost $100-300 per session. What Viva Does Viva is a full-stack interview coaching application that provides real-time feedback on both verbal answers and body language: Live audio conversation — bidirectional audio streaming via Gemini Live API ( gemini-2.5-flash-native-audio-latest ). The AI interviewer asks questions, listens to your answers, and responds naturally. You can interrupt mid-sentence (barge-in). Body language coaching — webcam frames analyzed every 2 seconds via Gemini Vision ( gemini-2.5-flash