Skip to playerSkip to main content
  • 1 day ago
See the new Gemini app for macOS in action! This presentation highlights how the AI can seamlessly process voice input, PDFs, and images to handle a real-world task—simplifying the tedious process of gathering pet info for a kennel into a single, effortless command.

Category

🤖
Tech
Transcript
00:00Jim and I have the Mac OS. Here it is on the screen. It's gorgeous. This is a small team
00:05that built this native app from scratch using anti-gravity.
00:09Want to see it live? Alright. We've got a big summer trip coming up and we've got to find a
00:17kennel for our two dogs.
00:20And here's a picture of our two dogs. There's Hank, looking good, and Louie Cinnamon, one of the most interesting
00:26names for a dog we've ever heard.
00:29What we're going to do, and remember when you have to go to a new kennel, there's lots of paperwork,
00:34allergies, vaccines, all the history you have to pull together.
00:37It's so painful. And so what you can do with this on Jim and I on Mac OS is actually
00:44take a look at a bunch of documents like this.
00:47You'll be able to select them all and then long press the function key and just dictate the email to
00:54the kennel.
00:54So it works something like this.
00:58Hi there. I need to do a short warding stay for my two dogs, Louie Cinnamon and Hank, starting this
01:05Thursday.
01:06Wait, no, actually it's this Friday. They've never stayed with you before, but they're very social dogs.
01:11And also, can you turn these files into a table with their details, allergies, recent vaccines, and make this email
01:19sound friendly so we make a good first impression?
01:24All right, I'm going to release the function key. You can see Jim and I speaking at the bottom here
01:29on this map.
01:30What it's done is because I've selected those files in Finder, using its multimodal understanding, it can go through the
01:38PDF, it can go through these images of their invoices, and it's all controlled by my voice.
01:44So it can actually take all that complex information, and look at that. There it is. It's got a table
01:50in line.
01:55It's also so amazing because it corrects, remember I said Thursday, no, scratch that Friday, but it picks up that
02:02and automatically cleans up by input.
02:06This is the power of what Jim and I can do using your voice.
02:10These new voice capabilities and Jim and I Spark will be coming to the Mac app this summer as well.
Comments

Recommended