Unlocking Client-Side AI in Your Web App
summary
Shows how to run generative AI entirely in the browser using built-in AI APIs, WebNN, WebGPU and WebAssembly, with demos of an offline chatbot, live camera-based vision mesh, and on-device speech translation that work without a server. Explains Prompt API and high‑level task APIs (summarizer, translator, writer), how Chrome exposes Gemini Nano (flag for Gemini 4), and how to cache downloaded models, add WebGPU libraries, quantize models, and keep a cloud fallback for unsupported browsers.
AI-written summary · about
chapters (8)
- 0:00Client-side AI intro
- 1:54Run AI in web apps
- 5:50Cloud vs client-side AI
- 8:02Browser AI APIs
- 13:00Compatibility & fallbacks
- 15:28AI libraries & models
- 16:10Offline AI demo
- 20:44AI architecture tips
related talks
24mAI right in the browser with Chrome's built-in AI APIs
45mPrivacy-First In-Browser Generative AI Web Apps
30mUnleashing AI in Your Web Apps
02mDiscover Web AI: Client side Agents, Gen AI, and machine learning in the browser
22mClient side Web AI Agents: Building smarter user experiences for future agentic ...
32mPrivacy-first in-browser Generative AI web apps
12mBrowsing, building, and web in the AI era
24mState of client side AI