After the preview at I/O 2026 in May, Gemini for macOS is now rolling out advanced voice control capabilities.
Google bills this as letting you “speak naturally into any window on your desktop,” with two key features.
The first is intelligent dictation that transcribes “spoken words into clean, polished text.” Gemini automatically removes “umm” and “ah,” while accounting for your mid-sentence corrections to capture the gist of what you’re saying.
The formatted text is entered at your current cursor position. This should offer a speech-to-text experience that’s similar to Gboard Rambler on upcoming Gemini Intelligence phones.
The other capability goes beyond transcription by understanding the context of your current screen to perform complex tasks. This opt-in functionality requires you to enable Gemini reasoning in app settings.
Long-press the Fn key wherever you are in macOS to activate, or tap the new screen sharing button at the end of the “Ask Gemini” prompt box. Gemini will show a floating pill that houses a waveform at the bottom of your screen.
Make sure you’ve updated to the latest version (1.88) of Gemini for macOS. This new voice capability is still rolling out globally to all users in English and more languages are “coming soon.”
FTC: We use income earning auto affiliate links. More.
Check out 9to5Google on YouTube for more news:
Editor-in-chief. Interested in the minutiae of Google and Alphabet. Tips/talk: abner@9to5g.com
