Google is expanding the capabilities of its Gemini app for Apple desktops and laptops with a new update that brings smarter voice input and better use of on-screen context. The update follows the introduction of Gemini Spark, the personal AI agent for macOS first showcased during this year’s Google I/O keynote. The dedicated Gemini app launched in April and is now receiving the new features globally.
Gemini for macOS update: What’s new
The latest update allows Gemini for macOS to turn natural-language voice inputs into text. Google says users can “create, edit, and summarise” content regardless of the app they are using. Users can long-press the function key and “speak naturally into any window”. The “intelligent dictation” feature is enabled by default.
The feature is similar to the Rambler tool introduced during this year’s Android Show: I/O Edition. Gemini can correct words, remove filler phrases such as “um,” “ah”, and “like”, and refine speech-to-text content. It can also automatically remove formatted text.
The update also introduces “intelligent” transcription based on what is visible on the user’s screen. This feature is optional and can be enabled by turning on Gemini Reasoning in Settings. Users can then extract and summarise information and highlight local files, images and documents on their Mac.
Gemini can also work with text anywhere on the screen. Users can compose, rewrite or highlight text, use voice commands to rewrite it, adjust its tone and copy-paste the refined version.
The update extends voice controls to image creation and editing as well. Users can give voice prompts to generate images, edit them and make further changes to designs directly on their macOS devices.
Also read: Viksit Workforce for a Viksit Bharat
Do Follow: The Mainstream LinkedIn | The Mainstream Facebook | The Mainstream Youtube | The Mainstream Twitter
About us:
The Mainstream is a premier platform delivering the latest updates and informed perspectives across the technology business and cyber landscape. Built on research-driven, thought leadership and original intellectual property, The Mainstream also curates summits & conferences that convene decision makers to explore how technology reshapes industries and leadership. With a growing presence in India and globally across the Middle East, Africa, ASEAN, the USA, the UK and Australia, The Mainstream carries a vision to bring the latest happenings and insights to 8.2 billion people and to place technology at the centre of conversation for leaders navigating the future.