In July 2026, Google introduced new features for the Gemini app on MacOS, enhancing user interaction through voice capabilities. This update follows the app's initial release earlier in the year, during which Google has been actively adding features to improve user experience. The new voice capabilities allow users to interact with the app using voice commands, making it easier to perform tasks without manual input. Additionally, a new Screen Awareness mode has been introduced, enabling the app to understand the user's current screen content and execute tasks accordingly. The intelligent dictation feature is one of the highlights of this update, transcribing spoken words into polished text while eliminating filler words like 'ums' and 'ahs.' This feature is similar to the Rambler functionality seen in Android 17, which also cleans up spoken text in real-time. The Gemini app's voice capabilities aim to streamline the process of creating documents and managing tasks, making it a valuable tool for users who prefer hands-free operation. The Screen Awareness mode further enhances the app's functionality by allowing it to 'see' what is on the user's screen. This opt-in feature can recognize active windows and assist users by executing commands based on the content displayed. For example, users can highlight text in a document and instruct Gemini to summarize it, which the app will then do by replacing the highlighted text with the requested output. This capability represents a significant advancement in how users can interact with their devices, as it combines voice recognition with contextual understanding of the user's work environment. As the Gemini app continues to evolve, Google is committed to expanding its features and capabilities. The new voice functionalities are currently available to English-speaking users globally, with plans to introduce support for additional languages later in the year. This ongoing development reflects Google's dedication to enhancing user experience and making technology more accessible and intuitive for everyone.