Gemini for macOS is rolling out advanced voice control features, allowing users to "speak naturally into any window on your desktop." The first key feature is intelligent dictation that transcribes spoken words into polished text, automatically removing filler words and accounting for corrections. This speech-to-text experience is designed to be similar to Gboard Rambler on upcoming Gemini Intelligence phones.

The second capability goes beyond transcription by understanding screen context for complex tasks. Opt-in Gemini reasoning allows users to highlight local files, images, or documents and request summaries or actions. For instance, one can ask Gemini to "Read these vet files and summarize my dog’s medical history in an email to the kennel."

Users can also use voice to rewrite text, adjust tone, and generate or edit images. To activate, long-press the Fn key or tap the new screen sharing button in the "Ask Gemini" prompt. Gemini for macOS version 1.88 is required, and the voice features are rolling out globally in English, with more languages to follow.