AI Camera — Fan Edition: it hypes up your jersey like a stadium commentator 🏆

You'll need a free Gemini API key from

How I Built It

Passion shows up in different ways. Sometimes it's the quiet kind — building something so a person who can't see can still "see" the world around them. Sometimes it's the loud kind — losing your mind over your team's jersey during a World Cup year. I already had the first one built. Adding Fan Mode let the same engine carry both.

• Vanilla HTML/CSS/JS — no framework, no build step, no backend


• Camera access via getUserMedia, photo captured to a canvas and sent as base64 to the Gemini API (gemini-flash-latest) with a mode-specific prompt


• Each mode is just a different prompt string — Fan Mode's prompt asks Gemini to respond "like a hyped-up sports commentator hyping up the crowd"


• Responses are read aloud via the browser's Web Speech API (free, works offline once the page is loaded)


• The whole thing is one static index.html, so it deploys straight to GitHub Pages with HTTPS — which matters, because phones require a secure context for camera access

Prize Categories

Best Use of Google AI — Gemini's vision model is the core of the app; every one of the five modes depends on it to analyze the photo.

Notes for judges: please test on a phone if possible — that's the intended experience (rear camera + held up to real objects). Fan Mode is the new addition for this challenge; the other four modes existed before as an accessibility tool.