Google Gemini for Mac Gains Voice Dictation and Screen-Aware AI Commands

Google is rolling out a new voice mode for its Gemini app on Mac. Hold the Fn key and speak, and Gemini transcribes speech directly into the active app, with optional screen-aware AI for more advanced commands.



In a blog post, Google explained how the feature works. By default, intelligent dictation turns speech into clean, polished text. It removes verbal fillers like "ums" and catches mid-sentence corrections before inserting the formatted text directly at the cursor.


Users can also enable screen-aware reasoning in settings. Once enabled, Gemini can understand the context on your screen to handle more complex spoken requests. For example, you could ask it to "read these vet files and summarize my dog's medical history in an email to the kennel," or "turn these notes into an executive summary with a TL;DR at the top." Gemini can also generate or edit images through spoken requests, such as creating a dark-mode version of a design already on screen.

Google launched a native Gemini app for Mac in April. It started with a keyboard shortcut and permission-based tools for analyzing on-screen content. The company later redesigned the app around its Spark AI agent and added local file access and automation. The new voice mode builds on those capabilities by letting users create, edit, and summarize content through speech while remaining in the app they're already using.

Voice capability is rolling out globally to all users of the Gemini app for macOS in English. Google says more languages are coming soon.