Overview
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.
Note: the demo URL is substituted with the GitHub repository link.
Tech stack
No comments yet
Be the first to comment on this project.
sentinel
Full-Stack Self-Healing DevOps & Security Copilot The Concept: An AI operations engineer that doesn't just suggest code fixes—it monitors cloud infra, detects uptime/security drops, automatically provisions fixes, and generates audit reports for enterprise compliance.
Agency Compiler
Agentic creative project compiler. Most creatives, agencies and designers dont know how to use ai, none the less agents. We created a platform that allows a creative agency or studio owner to instantly spin up agents based on the project ask, resources and scale.
ProofRun
ProofRun helps developers answer a critical question before shipping: will this update break behavior users rely on? An AI agent inspects two Git revisions, designs targeted experiments, and proposes repairs. An independent Docker-based verifier runs those experiments against both versions, preserves the original tests, and checks whether the repair actually works. Developers receive an update, skip, or postpone recommendation with recorded evidence and a reviewable patch. In a live synthetic…