StefanM

Voice Chess Talk to your chess game. Voice Chess reimagines how we interact with one of the world's oldest strategy games. Instead of dragging pieces on a screen, you speak — "move knight to f3" — and an AI voice agent powered by ElevenLabs understands, executes, and responds in real-time natural conversation. What it does: Voice Chess is a fully playable chess app with two modes: - Solo vs. AI — Play against a built-in chess engine using your voice or by clicking. Ask the agent "what's on the board?" and it describes the full position aloud. Say "move from e2 to e4" and it plays the move for you. - Multiplayer — Create a room, share a code (or link), and play a timed 10-minute game against a friend over the internet. The voice agent works here too — it's your hands-free interface to the board. A 3D animated orb built with Three.js provides real-time visual feedback: it pulses when the agent is listening, shifts when it's speaking, and rests when idle. It turns the voice interaction into something you can see, not just hear. How it works: The frontend is a Next.js app that renders an interactive chessboard and connects to an ElevenLabs voice agent via their React SDK. The agent has two client tools — getBoard (reads the full board state aloud) and makeMove (executes a move) — so the conversation loop is tight: you speak, the agent acts on the game, and responds with what happened. The backend is a Bun server with Socket.IO handling all multiplayer logic: room creation, move validation via chess.js, turn enforcement, 10-minute clocks with 100ms tick resolution, and win/loss/draw/timeout/disconnect detection. The entire client is statically exported and served directly by Bun for minimal latency. Why it matters: Voice interfaces for games are still largely unexplored. This project demonstrates that conversational AI can be a first-class input method — not a gimmick, but a genuinely usable way to play. It's accessible (hands-free play for anyone who needs it), it's social (talk to your game while playing against a friend), and it showcases what's possible when you wire ElevenLabs Agents directly into application state with client tools. Built with: Next.js · Bun · Socket.IO · chess.js · ElevenLabs React SDK · ElevenLabs UI (Orb) · Three.js · Tailwind CSS

Submitted 23 Apr 2026

The world is constantly on the brink of crisis. Usually, you just watch it on the news. What if you were the one answering the 3 AM phone call? As a university student majoring in International Relations, I spend my days analyzing global conflicts, macro-economic shifts, and diplomatic standoffs. But reading theory in a textbook is completely different from actually sitting in the Situation Room. I wanted to build a platform that bridges that gap, turning passive doomscrolling into an interactive, high-stakes geopolitical dashboard. Enter Tely World Sim v2. Tely World Sim is a real-time geopolitical simulation where you enter as a country's leader. You watch a live, severity-ranked news feed, monitor macro indicators, click interactively across a world map, and navigate diplomatic crises using your actual voice. How it uses the tech ElevenLabs (The Voices of Power): This isn't just a text-based game; it's a fully voiced diplomatic simulator powered by ElevenLabs Conversational AI. Your Chief of Staff: You have an always-on voice assistant that you can talk to directly. They will brief you on live risk updates, summarize the news, and provide policy guidance. Simulated Presidents: The core "wow" factor is the Call President feature. If a crisis breaks out in another region, you can click that country on the map and instantly initiate a live voice transfer to an AI agent acting as that nation's leader. You actually have to negotiate, de-escalate, or threaten them over a live voice channel. Firecrawl (The Pulse of the World): A simulation is only as good as its data. Instead of relying on static, outdated LLM training data, I use Firecrawl to scrape and crawl real, live news websites. Firecrawl funnels these real-world headlines into my WebSocket data channel, where they are ranked by severity. This live data is then mixed with synthetic scenario events to actively shape the world map, giving the ElevenLabs agents actual, current events to argue with you about. State of the Project & Developer Feedback This project is currently in Alpha. I have massive plans to expand the game theory mechanics, introduce deeper economic consequences, and refine the multi-agent diplomatic negotiations. Building a complex, real-time app combining live web-scraping and low-latency voice AI was an incredible challenge. I ran into a few friction points and edge cases with both the ElevenLabs and Firecrawl APIs that required some very creative engineering workarounds to solve. Regardless of whether I win or not, my inbox is open. I would love to jump on a call or send over a write-up of my developer experience to both the Firecrawl and ElevenLabs engineering teams. I want to share the hurdles I faced and how I bypassed them to help make these tools even better for the next developer. Thank you for the opportunity to build this—the world is on the line, what are your orders?