Google has added voice input to the Gemini app for macOS, letting you talk to it from inside whatever window you happen to be working in rather than switching over to a separate app.
The way it works is you long-press the Fn key and start talking. By default that gives you dictation, but a smarter version than what most people are used to. Gemini strips out the “ums” and “ahs,” catches it when you correct yourself mid-sentence, and drops clean formatted text at your cursor.
If you want it to do more than transcribe, there’s a setting that turns on Gemini’s reasoning and lets it read what’s on your screen. With that switched on, you can highlight files, images, or documents on your desktop and tell it what to do with them. Google’s example is saying “Read these vet files and summarize my dog’s medical history in an email to the kennel.”
It also handles rewriting. Highlight any text on screen, tell it how you want it changed, and the revised version lands back where you need it. Something like “Turn these notes into an executive summary with a TL;DR at the top.”
You can also generate images by voice or point at an existing design on your desktop and ask for changes, such as taking an illustration and generating a dark-mode version of it, said Google on Wednesday.
The feature is rolling out globally to everyone using the Gemini Mac app, in English to start, with more languages coming. We’re not seeing this working yet in Canada, but let us know if you’re seeing it.
Want to see more of our stories on Google?
P.S. Want to keep this site truly independent? Support us by buying us a beer, treating us to a coffee, or shopping through Amazon here. Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent Canadian media!
