Immergo is an immersive language learning application powered by the Google Gemini Live SDK. It simulates real-world roleplay scenarios (e.g., buying a bus ticket, ordering coffee) to help users practice speaking in various languages with an AI that acts as a native speaker.

JARVIS built using the Gemini Live API

Multi-provider voice AI showcase featuring 7 providers (ElevenLabs + Widget, OpenAI, xAI, Ultravox, Vapi, Retell, Google Gemini Live) with real-time transcripts, audio visualization, and glassmorphism UI. Built with React 19 + TypeScript.

Voice AI Conversation with Google Maps

A real-time voice AI web app using Google Gemini Live API. Features speech-to-text, text-to-speech, and interruptible conversations, restricted to Revolt Motors topics. Built with Node.js, Express, WebSocket, and Web Audio API for smooth low-latency voice interactions.

gemini live chat with voice/video/screen-share

Real-time voice agent using LiveKit and Gemini Live API

Portfolio V2 - themed in Neo-brutalist design with multilingual Voice AI mode.

Real-time voice assistant powered by Google Gemini Live API.

A simple ai-driven tracker that logs your daily mood, voice, energy and cycle patterns to reveal clear trends across the year

A lightweight Swift client for Gemini Live API.

Gemini acts as a conversation facilitator and moderator with a panelist to explore and engage in a conversation that includes audio/video..

OpenAI-compatible adapter for Google Gemini Live API • 4x higher rate limits (1M TPM) • Drop-in replacement • Streaming support • Docker-ready

An interactive Ender Dragon that listens and responds to you. Features flapping wings, moving mouth, ambient sounds, and live transcription of the conversation. Powered by Gemini.

Odyssey-AI is an intelligent travel assistant that provides personalized travel plans, real-world photos, and AI-generated visuals for an immersive planning experience.

Spatial Engine AI: A DeepTech Agent that sees like a designer and calculates like a physicist. Powered by Gemini 3 Pro & Vision to optimize energy efficiency in built environments.

A gesture-driven Reactive AI interface bridging the Lithosphere and the LLM. Powered by the Gemini Live API and TensorFlow.js, reactive.rocks uses the QUINCE recursive algorithm and $%r$ (Residual Reflection) to synchronize human kinetics with machine consciousness in real-time.

This is minimal implemeantion of gemini live API using a PHP backend. The example include webSocket implementation. The application capture transcript of both users and LLM response in realtime.