Google added a new feature to the Gemini application developed for macOS that allows users to access the artificial intelligence assistant much faster. Starting today, Mac users can use the keyboard icon located in the lower left corner of the keyboard. fn By long pressing the button, people will be able to communicate with Gemini by voice from any application. The new feature allows users to take notes, create text and perform artificial intelligence-supported operations without interrupting the work flow.
Gemini’s new voice access system can transcribe spoken phrases directly into the area where the cursor is located. In this way, when users are reading an article, taking notes during a meeting, or voicing their ideas out loud, Gemini converts them into text. According to the information provided by Google, the system creates a more orderly and readable text by automatically removing filler expressions such as “ıı” and “ee”, which are frequently used during speech. The resulting content thus aims to reduce the need for additional editing.
Google Gemini can work with different applications by analyzing the screen
With the new update, Google also makes Gemini’s screen-aware reasoning feature more accessible. If the user enables this feature, Gemini can analyze the content open on the screen and understand which applications are running. Thus, it can not only receive voice commands, but also perform context-appropriate operations through the content on the screen.
For example, after selecting a specific text in an open PDF file, the user can ask Gemini to summarize the selected section by pressing the fn key. Similarly, texts prepared in the notes application can be selected and an e-mail draft can be created from them. Google states that such advanced transactions are offered to users using Gemini’s artificial intelligence infrastructure called Spark. This system can go beyond single-step commands and perform tasks that connect multiple processes.
In addition, Gemini continues to support the ability to produce visuals with voice commands. Users can verbally describe the visual they want to see or request new visuals to be created using ideas and sketches open on the screen. Thus, different productive artificial intelligence functions such as text generation, content editing and visual creation come together under a single access method.
Google released the native Gemini application for macOS in April. The company made this version available just a day after the Windows app was announced. In June, Spark artificial intelligence assistant was added to the application, thus more complex tasks such as preparing new documents and spreadsheets began to be supported. With the latest update, the voice access feature, which works by long pressing the fn key, is being distributed to all macOS Gemini users worldwide.
For this feature, which currently only supports the English language, Google announced that other languages will be added later in the year. The company has not yet shared which languages will be supported initially. There is no official calendar for when Turkish support will arrive.
The new feature significantly speeds up macOS users’ access to Gemini and makes daily productivity scenarios such as note-taking, content preparation and document summarization more practical. However, the fact that advanced capabilities such as screen awareness only work when the necessary permissions are given helps maintain user control in terms of privacy. As the feature gains more language support, Gemini’s usage area on macOS is expected to expand.
Join Channel