The Chrome and Edge browsers have built-in APIs for language detection, translation, summarization, and more, using locally hosted models. Here’s how to take advantage of them.

InfoWorld is a source of news, analysis, and commentary on technology trends, IT strategies, and business innovation. With a focus on enterprise technology and digital transformation, InfoWorld offers insights and guidance for IT decision-makers, software developers, and technology professionals. From  articles on cloud computing and cybersecurity to product reviews and industry trends, InfoWorld helps readers navigate the complexities of modern IT environments and make informed decisions to drive business success.

InfoWorld

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.

Tap into the AI APIs of Google Chrome and Microsoft Edge

Step 3: Stream and iterate over the output