Gemini for macOS adds new natural language capabilities

Speak naturally to Gemini to get clean transcriptions, edits, and summaries dropped right into the app you’re using.

The Gemini app for macOS was built to keep you in your flow. Today, we’re introducing a new way to create, edit, and summarize with Gemini using just your voice, right where you are already working.

By long-pressing the Fn key, you can speak naturally into any window on your desktop. By default, this enables intelligent dictation, letting you easily transcribe your spoken words into clean, polished text — automatically removing the “ums” and “ahs,” catching mid-sentence corrections, and dropping the formatted text instantly at your cursor.

If you want Gemini to do more than intelligently transcribe, you can opt into Gemini reasoning through your settings. Once enabled, Gemini can understand the context on your screen to help you execute complex tasks. For example, you can:

Extract and summarize information: Highlight local files, images, or documents on your desktop and tell Gemini exactly what you need. For example, you can say “Read these vet files and summarize my dog’s medical history in an email to the kennel.”
Compose and rewrite text: Highlight text anywhere on your screen and use your voice to instantly rewrite it, tweak the tone, and drop the polished version right where you need it. Try saying, “Turn these notes into an executive summary with a TL;DR at the top.”
Generate and edit images: Use your voice to create visuals when conceptualizing an idea or enhancing a travel itinerary, or iterate on a design on your desktop by referencing it to request quick updates. Try saying, “Take this illustration and generate a dark-mode version of it.”

This new voice capability is rolling out globally to all users of the Gemini app for macOS in English, with more languages coming soon. Download the app at gemini.google/mac to get started.

Speak naturally with Gemini app for macOS

Google has rolled out a major update for the Gemini app for macOS, introducing a powerful new feature called “Speak to Window.” This integration allows you to insert clean, context-aware transcriptions and execute complex AI commands across any open application on your desktop using just your voice. [1, 2, 3]

Key New Features

Intelligent Voice Dictation: Press and hold the Fn key to speak naturally into any active text field. Gemini automatically filters out filler words (like “ums” and “ahs”), processes mid-sentence self-corrections, and drops polished, formatted text right at your cursor. [2, 3, 4, 5]
Screen Context & Reasoning: By enabling the optional “Reasoning” setting, Gemini analyzes what is currently displayed on your screen. You can highlight text in any app to rewrite it, change its tone, or format it via voice commands. [2, 3, 5, 6]
Local File Processing: You can select local desktop documents, PDFs, or images in Finder and ask Gemini to extract key information, compile data into tables, or draft summaries. [5, 6, 7]
Voice-Activated Image Generation: Describe a visual prompt out loud to generate and drop images directly into your active workspace. [5]

How to Use the Feature

Activate Dictation: Long-press the Fn key, speak your thoughts, and release the key to drop text.
Turn on Reasoning: Open the Gemini app and go to Settings > Speak to Window to toggle on advanced screen context and reasoning.
Availability: The feature is currently rolling out globally in English. You can download the native assistant directly from Google’s official Gemini for Mac page. [1, 2, 5, 8]