Microsoft has unveiled new APIs for its Edge web browser, enabling developers to integrate AI capabilities directly into their web applications. This announcement was made during the Build 2025 conference and aims to position Edge as a competitive alternative to Google Chrome, which offers similar built-in AI functionalities for developers.
The newly introduced APIs will provide access to Phi 4 mini, an AI model launched by Microsoft in late February, which has 3.8 billion parameters. This model is particularly adept at solving mathematical problems due to its robust training data, consisting of both human-generated and synthetic inputs. In the realm of artificial intelligence, the number of parameters in a model is a crucial determinant of its performance, with models featuring more parameters generally delivering superior results. However, smaller models like Phi 4 mini offer efficiency, making them suitable for devices with limited processing power, such as laptops and smartphones.
Aside from the core AI functionalities, Edge will also introduce writing assistance APIs that enable functions like text generation, summarisation, and editing. Additionally, Microsoft plans to release a translator API in the near future, facilitating AI-driven language translation capabilities within the Edge environment.
Microsoft has highlighted the potential for these experimental APIs to become web standards, which would ensure compatibility across different platforms and browsers while also supporting various AI models. Importantly, for developers operating in sensitive environments or regulated sectors, these APIs promise enhanced privacy through on-device processing capabilities. This means that users will not need to rely on external cloud services which may pose risks to data security.
Currently, these AI APIs are available for testing through Edge’s Canary and Dev channels.
Further enhancing Edge’s functionality, Microsoft is also set to roll out a PDF translation tool, which will support over 70 languages. Users will be able to translate PDF documents directly in Edge by clicking a translation icon in the address bar, generating a new document in their selected language. This feature is expected to launch widely next month, with Canary users able to access it immediately.
Through these advancements, Microsoft is clearly making a strong push to enhance the Edge browser’s capabilities and attract developers seeking robust, AI-driven solutions for their web applications.
Fanpage: TechArena.au
Watch more about AI – Artificial Intelligence
