Tap into the AI APIs of Google Chrome and Microsoft Edge

Chrome and Edge now expose experimental built-in AI APIs powered by locally hosted models (Gemini Nano for Chrome, Phi-4-mini for Edge). Available APIs include Translator, Language Detector, Summarizer, Writer, Rewriter, Prompt, and Proofreader. A practical walkthrough demonstrates the Summarizer API: checking availability, creating a Summarizer object with options like type (teaser, tldr, headline, key-points), length, and format, then streaming output token by token. Key caveats include multi-gigabyte model downloads on first use, no programmatic model management, and a delay before the first token appears. The long-term goal is standardizing these APIs across the web platform.