Support our independent tech coverage. Chrome Unboxed is written by real people, for real people—not search algorithms. Join Chrome Unboxed Plus for just $2 a month to get an ad-free experience, access to our private Discord, and more. Learn more about membership here.
START FREE TRIAL (MONTHLY)START FREE TRIAL (ANNUAL)
Google is continuing to expand its desktop AI features across platform ecosystems, and Mac users are getting a major workflow upgrade today.
According to a new post on News from Google (formerly The Keyword), the Gemini app for macOS is introducing new natural language voice capabilities designed to let users transcribe, edit, summarize, and generate content directly inside whatever desktop application they are using.
Intelligent dictation at the press of a key
The core addition to the macOS app is a quick-activation voice shortcut. By long-pressing the Fn key, users can speak naturally into any active window on their desktop to trigger intelligent dictation.
Rather than standard speech-to-text, Gemini cleans up spoken audio on the fly, automatically stripping out filler words like “ums” and “ahs,” handling mid-sentence corrections, and inserting formatted, polished text directly at the cursor location.
On-screen context and reasoning
For users looking to execute more complex workflows beyond transcription, Google is adding optional screen reasoning capabilities via settings. When enabled, Gemini can analyze the context on your display or parse highlighted desktop files to execute voice commands:
- Document extraction and summaries: Highlight local files, PDFs, or photos on your desktop and give natural language instructions (like reading veterinary records to draft an email summary for a pet sitter).
- Contextual rewriting: Highlight text anywhere on your screen and use voice commands to instantly adjust the tone, condense notes, or generate executive summaries.
- Voice-driven image generation and editing: Request visual assets or iterate on existing designs on your desktop using simple voice prompts, such as asking Gemini to convert an open illustration into a dark-mode version.
Availability
The new natural language voice updates are rolling out globally today for all users of the Gemini app for macOS in English, with additional language support planned for the future. Mac users can download the updated application directly at gemini.google/mac to test out the new features.
SUBSCRIBE TO UPSTREAM
Get Chrome Unboxed delivered straight to your inbox
Upstream is our flagship, curated newsletter with the top stories, most click-worthy deals, giveaways, and trending articles from Chrome Unboxed sent directly to your inbox a few times a week. Join 31,000+ subscribers.
