Truthy
Truthy - Real-Time AI Fact-Checker for Live Debates THE PROBLEM: Misinformation spreads faster than fact-checkers can verify it.
Core trick
Runs one Gemini Live transcription session per speaker, extracts check-worthy claims, and searches .gov and .edu sources to verdict them.
Description
Truthy - Real-Time AI Fact-Checker for Live Debates
THE PROBLEM:
Misinformation spreads faster than fact-checkers can verify it. Traditional
fact-checking happens hours or days after debates, when false claims have already
influenced millions. Live debates lack real-time accountability, allowing
unchallenged misinformation to shape public opinion.
THE SOLUTION:
Truthy uses Gemini's Realtime API to fact-check spoken claims in under 5 seconds
during live debates. It:
• Transcribes two speakers simultaneously using Gemini Live sessions
• Detects check-worthy factual claims (numbers, dates, comparisons)
• Searches Google for authoritative evidence (.gov, .edu, official sources)
• Displays color-coded verdicts (True → False → Unverifiable) with confidence scores
• Shows clickable sources with publication dates for transparency
README excerpt
# Truthy - Real-Time Debate Fact Checker AI-powered fact-checking for live debates using **Google Gemini Realtime API**. ## Overview Truthy listens to two speakers in a debate, transcribes their speech in real-time, detects factual claims, verifies them against trusted sources, and displays concise verdicts with citations — all in under 5 seconds. Built for the **Gemini + Fetch.ai Hackathon** to strengthen healthy democracies by grounding public discourse in shared, verifiable truth. ## Features - **Real-Time Transcription**: Two simultaneous Gemini Live sessions (Speaker A & B) - **Claim Detection**: AI identifies check-worthy factual statements - **Multi-Source Verification**: Searches Vectara corpus, web sources, and context validation - **Live Verdict Display**: Color-coded badges (True → Unverifiable) with confidence scores - **OBS Overlay**: `/overlay` route for livestream lower-third display - **TypeScript + Tailwind**: Strong typing and modern UI ## Tech Stack | Component | Technology | |-----------|-----------| | Frontend | Next.js 15 + React 19 + TypeScript | | Styling | Tailwind CSS | | AI Model | Google Gemini 2.0 Flash (Realtime) | | Audio | Web Audio API (16kHz input, 24kHz output) | | Database | PostgreSQL + Prisma (optional) | | Tools | Zod validation | ## Quick Start ### Prerequisites - **Node.js 18+** and npm/pnpm - **Gemini API Key**: Get one at [Google AI Studio](https://aistudio.google.com/apikey) ### Installation 1. **Clone and install depen