Google Gemini for macOS introduces system-wide voice dictation and screen-aware commands

Google has launched new voice-powered capabilities for Gemini on macOS, letting users create, edit, and summarize content using spoken commands wherever they are working. By pressing and holding the Fn key, users can dictate naturally into any desktop window. The app automatically transcribes speech into polished text, removing fillers such as ums and ahs, correcting mid-sentence changes, and inserting the clean result at the cursor.

Following this foundation, users who opt into Gemini reasoning can allow the assistant to access on-screen context for more advanced tasks. This enables spoken commands that extract and summarize information from highlighted local files, images, or documents. It also allows users to rewrite existing text, adjust tone, and insert improved content, all via voice. For creative workflows, users can generate or edit images simply by describing their needs aloud, including quick iteration on desktop designs.

This enhanced voice experience for Gemini is rolling out globally to all macOS users of the Gemini app in English. Support for additional languages is planned for future releases.