VoiceBroker AI — Autonomous Voice Trading Agent

VoiceBroker AI is an autonomous voice-powered trading platform built for the AI Agent Olympics Hackathon 2026 at Milan AI Week. The platform enables users to control a simulated trading desk entirely through natural voice commands. Users can speak commands such as “Buy $50 of Apple stock” or “Sell my Tesla position,” and the system automatically processes the request using real-time AI pipelines. The application combines Speechmatics real-time speech-to-text, Google Gemini AI for intent parsing and market reasoning, Kraken market APIs for trading data, and Supabase for portfolio management and historical tracking. VoiceBroker AI demonstrates a complete autonomous agent workflow: Voice Input → Speech Recognition → AI Intent Analysis → Risk & Market Evaluation → Trade Execution → Voice Confirmation The system includes intelligent fallback architecture to ensure reliability during live demos. If Gemini APIs fail or rate limits are reached, the platform automatically switches to rule-based parsing systems powered by real operational data. Key features include: • Real-time voice-controlled trading • AI-powered trading analysis • Autonomous trade execution simulation • Portfolio intelligence dashboard • Market forecasting insights • Voice confirmation system • Real-time AI processing visualization • Enterprise-grade fallback reliability The project demonstrates how multimodal AI agents can transform financial operations by making trading conversational, autonomous, and accessible. Tech Stack: React, TypeScript, Tailwind CSS, Supabase, Speechmatics, Google Gemini 1.5 Flash, Kraken APIs, Recharts, and Framer Motion.