Gemini for macOS Gains Advanced Voice Capabilities

A new feature has been added to the Gemini app for macOS, allowing users to interact with their desktop using voice commands. This update enables users to create, edit, and summarize content without needing to physically type it out.

The key to this functionality lies in long-pressing the Fn key on a Mac keyboard. By doing so, users can speak naturally into any window on their desktop, bypassing the need for manual input. The app will automatically transcribe spoken words into clean text, removing filler words and phrases like ‘ums’ and ‘ahs’.

Users also have the option to enable Gemini reasoning through the settings menu. Once activated, the app can understand context-specific information on the screen to help users execute complex tasks. For instance, they can highlight local files or documents and instruct Gemini to extract specific details.

One example of this capability is extracting and summarizing information from highlighted content. Users can say something like ‘Read these vet files and summarize my dog’s medical history in an email to the kennel.’ The app will then generate a concise summary based on the provided context.

Another feature allows users to compose and rewrite text using voice commands. By highlighting relevant sections of text, they can instruct Gemini to instantly rewrite it with a different tone or style. This could be as simple as saying ‘Turn these notes into an executive summary with a TL;DR at the top.’

The app’s new voice capabilities also extend to image generation and editing. Users can use their voice to create visuals when conceptualizing ideas, enhance travel itineraries, or iterate on designs by referencing them for quick updates.

This feature is currently available globally in English, with more languages expected to be supported soon. The Gemini app for macOS can be downloaded from the official website.