Gemini App for macOS Adds New Voice Control Features

Google is updating its Gemini app for macOS with new natural language capabilities. Starting today, Mac users can long-press the Fn key to enable intelligent dictation in Gemini, and the chatbot will also be able to execute complex tasks if Mac users enable the chatbot’s reasoning feature.

When talking to Gemini, the chatbot can transcribe spoken text into any opened window while removing blurbs and taking mid-sentence corrections into account. This intelligent dictation feature is currently only available in English, with support for more languages coming soon.

With Gemini reasoning enabled, the Mac app can also compose and rewrite text, generate and edit images, and execute tasks while using information from local files. “For example, you can say “Read these vet files and summarize my dog’s medical history in an email to the kennel,” Google explained today.

With a Google AI Ultra subscription (and AI Pro if you’re in the US), Mac users can unlock Google’s Spark agent inside the Gemini for Mac app. Spark works as a personal AI agent that can work in the background and perform complex tasks using other Google services, connected third-party apps, websites, and more. Google said last week that it will bring Gemini Spark to AI Pro subscribers in more countries soon.