Unknown

Google I/O '25 >> CHAZ: Good morning, everybody! All right! My name is Chaz, I make music as Toro y Moi. I'm from right here in the Bay Area from Berkeley, California. Today, I'll be playing with the Lyria RealTime This is going to be a performance and an experiment. Everything I'm playing is completely improvised, and I'm basically jamming with the computer. The computer will also be jamming with me. Feel free to just settle in. It's not a heavy performance. You can look at your phone. You can make friends, talk to your neighbors, but the it energy

will eventually pick up and then we'll be ready for the seminar. Here we go! ♪ [ music ] ♪ >> CHAZ: How are you guys feeling? All right, we're going to start to pick it up a little bit. Are you guys awake? Oh! Are you guys awake? All right! ♪ [ Music ] ♪ >> CHAZ: All right, everybody! You just got a chance to see how this works real time. Basically, I assigned a prompt to each knob, and everything from sitar drone to tabla to minimal technono I was adding these different elements and genres. I

felt like this was a really cool project to take on. Personally, music is my spiritual guide. Music is going towards AI with, or without me, and it's my responsibility as an artist to keep up. I think it's good for us to remember we're here today to see each other in person. And I think it's great to remember people matter. So make some friends today. Shake some hands. Meet some people. My name is Chaz. Thanks, everybody. See you next time. [Applause] ♪ [ Music ] ♪ >> This town ain't seen nothing yet. ♪ [ music ]

♪ One, two One, two, three, ow ♪ wake up, kids, we've got the dreamers disease ♪ ♪ age 14, they got you down on your knees ♪ ♪ so polite, we're busy still saying please ♪ ♪ you've got the music in you ♪ ♪ don't let go ♪ ♪ you've got the music in you ♪ ♪ one dance left ♪ ♪ this world is gonna pull through ♪ ♪ don't give up ♪ ♪ you've got a reason to live ♪ ♪ can't forget ♪ ♪ we only get what we give ♪ ♪ I'm comin' home,

baby ♪ ♪ you're tops ♪ ♪ give it to me now ♪ [Applause] >> SUNDAR PICHAI: Wow, cool video! It looks like the team has been having some fun. Hello everyone, good morning! Welcome to Google I/O. [Cheering and Applause] So good to see everyone here in Shoreline and hello to everyone joining virtually around the world. I learned that today is the start of Gemini season. Not really sure what the big deal is; every day is Gemini season here at Google. Normally, you wouldn't have heard much from us in the weeks leading up to I/O. That's

because we would be saving our best models for this stage. But in our Gemini era, we are just as likely to ship our most intelligent model on a random Tuesday in March or a really cool model like AlphaEvolve a week before. We want to get our best models into your hands and our products ASAP, and so we are shipping faster than ever. We've announced over a dozen models and research breakthroughs and released over 20 major AI products and features, all since the last I/O. I'm particularly excited about the rapid model progress. You can see the

step function change here. Elo scores, one measure of progress, are up more than 300 points since the first generation of Gemini Pro. And today, Gemini 2.5 Pro sweeps the LMArena leaderboard in all categories. [Applause] It is s state-of-the-art on man, many benchmarks, and we've also made rapid progress in coding. Our updated 2.5 Pro reached number one on WebDev arena, and now, surpasses the previous version by 142 Elo points. It's getting a lot of love across the top coding platforms, thanks to all of you. On Cursor, the leading AI code editor, Gemini is the fastest-growing model

of the year, producing hundreds of thousands of lines of accepted code additions per minute. Now, this last milestone might be the most impressive, at least in some circles. A couple of weeks ago, Gemini completed Pokémon Blue. [Applause] It earned all eight badges, traveled the Victory Road, defeated the Elite 4 and the champions, bringing us one step closer to achieving API, Artificial Pokémon Intelligence. [Laughter] [Applause] All this progress is enabled by our world-leading infrastructure, the foundation of our full-stack approach to AI. Our seventh generation TPU Ironwood is the first designed specifically to thinking and inference at

scale. It develops 10x the performance over the previous generation and packs an incredible 42.5 exaflops of compute per pod. Just amazing. ,And it's coming to Google Cloud customers later this year. [Applause] Our infrastructure strength, down to the TPU, is what helps us deliver dramatically faster models. Of the top models on the LMArena leaderboard, Gemini holds the top three spots for highest output tokens generated per second, all while model prices are coming down significantly, too. There's a hard trade-off between price and performance, yet over and over, we've been able to deliver the best models at the

most effective price point. Not only is Google leading the Pareto frontier, we have fundamentally shifted the frontier itself. The result: more intelligence available for everyone, everywhere. And the world is responding and adopting AI faster than ever before. As one marker of progress, this time last year, we were processing 9.7 trillion tokens a month across our products and APIs. Now, we are processing 480 trillion monthly tokens. That's about a 50x increase in just a year. [Applause] We are also seeing a wave of adoption across our d deloper API tools. Today, over 7 million developers have built

with the Gemini API across both Google AI Studio and Vertex AI, over 5x growth since last I/O. And Gemini usage on Vertex AI is up more than 40 times since last year. AI adoption is increasing across our products. The Gemini app now has over 400 million monthly active users, and we are seeing strong growth and engagement, particularly with 2.5 models. For those using 2.5 Pro in the Gemini app, usage has gone up 45%. You will hear a lot more about the Gemini app later. We also are seeing incredible momentum in Search. Today, AI Overviews have

more than 1.5 billion users every month. That means Google Search is bringing generative AI to more people than any other product in the world. And along with AI Overviews, AI Mode is the next big step for Search. You'll hear more about this later. What all this progress means is that we are in a new phase of AI platform shift, where decades of research are becoming reality for people, all over the world. I want to share three examples of how research is transforming our products today: Project Starline, Astra and Mariner. We debuted Project Starline, our breakthrough

video technology at I/O, a few years back. The goal was to create a feeling of being in the same room of someone even if you were far apart. We have continued to make technical advances and today, we are ready to announce our next chapter. Introducing Google Beam, a new AI-first, video communications platform. Beam uses a new state-of-the-art video model to transform 2D video streams into a realistic 3D experience. Behind the scenes, an array of six cameras captures you from different angles. With AI, we can merge these video streams together and render you on a 3D

light-field display. With near-perfect head tracking down to the millimeter and at 60 frames per second, all in real time. The result: A much more natural, and deeply immersive conversational experience. We are so excited to bring this technology to others. In collaboration with HP, the first Google Beam devices will be available for early customers later this year. HP will have a lot more to share a few weeks from now. Stay tuned. [Applause] Over the years, we have been bringing underlying technology from Starline into Google Meet. That includes realtime speech translation to help people break down language

barriers. Here's an example of how this could be useful when booking a vacation rental in South America and you don't speak the language. Let's take a look. >> Hi, Camila. Let me turn on speech translation. [Translation into Spanish] >> You're going to have a lot of fun, and I think you're going to love visiting the city. The house is in a very nice neighborhood and overlooks the mountains. >> That sounds wonderful -- [Translation into Spanish] >> There's a bus nearby, but I would recommend renting a car, so you can visit the nature and enjoy it.

>> That sounds great -- [Translation into Spanish] [Applause] >> SUNDAR PICHAI: You can see how well it matches the speaker's tone, patterns, and even their expressions. We are even closer to having a natural and free-flowing conversation across languages. And today, we are introducing this realtime speech translation directly in Google Meet. English and Spanish translation is now available for subscribers, with more languages rolling out in the next few weeks, and realtime translation will be coming to enterprises later, this year. [Applalae] Another early research project that debuted on the I/O stage was Project Astra. It explores the

future capabilities of a universal AI assistant that can understand the world around you. We are starting to bring it to our products. Today, Gemini Live has Project Astra's camera and screen-sharing capabilities, so you can talk about anything you see. People are using it in so many ways, whether practicing for a job interview, or training for a marathon. We've been appreciating the feedback from our trusted testers and some who are a little less trusted. Take a look. >> That's a pretty nice convertible. >> GEMINI: I think you might have mistaken the garbage truck for a convertible.

Is there anything else I can help you with? >> What's this skinny building doing in my neighborhood? >> GEMINI: It's a street light, not a building. >> Why are these palm trees so short? I'm worried about them. >> GEMINI: They're not short. They're actually pretty tall. >> Sick convertible. >> GEMINI: Garbage truck again. Anything else? >> Why do people keep delivering packages to my lawn? >> GEMINI: It's not a package, it's a utility box. >> Why is this person following me wherever I walk? >> GEMINI: No one's following you. That's just your shadow. [Applause] >>

SUNDAR PICHAI: Gemini is pretty good at telling you when you're wrong. We are rolling this out to everyone on Android and on iOS starting today. [Applause] Next, we also have a research prototype, Project Mariner, an agent that can interact with the web and get stuff done. Stepping back, we think of agents as systems that combine the intelligence of advanced AI models with access to tools. They can take actions on your behalf and under your control. Computer use is an important agentic capability. It's what enables agents to interact with and browsers and other software. Project Mariner

was an early step forward in testing computer use capabilities. We released it as an early research prototype in December and we made a lot of progress since. First, we are introducing multitasking, and it can now oversee up to 10 simultaneous tasks. Second, it's using a feature called Teach and Repeat. This is where you can show it a task once, and it learns the plan for similar tasks in the future. We are bringing Project Mariner's computer use capabilities to developers via the Gemini API. Trusted testers like Automation Anywhere and UI Path are already starting to build

with it, and it will be available more broadly this summer. Computer use is part of a broader set of tools we will need to build for an agent ecosystem to flourish, like our open agent-to-agent protocol so that agents can talk to each other. We launched this at Cloud Next with the support of 60 plus technology partners and hope to see that number grow. Then there is model context protocol, introduced by Anthropic so agents can access other services, and today, we are excited to announce that our Gemini SDK is now compatible with MCP tools. [Applause] These

technologies will work together to make agents even more useful, and we are starting to bring agentic capabilities to Chrome, Search, and the Gemini app. Let me show you what we are excited about in the Gemini app. We call it Agent Mode. If you want to find an apartment for you, and two roommates in Austin. You've each got a budget of $1,200 a month. You want a washer, dryer or at least a laundromat nearby. Normally, you would have to spend a lot of time scrolling through endless listings. Using Agent Mode, the Gemini app goes to work

behind the scenes. It finds listings from sites like Zillow that match your criteria, and uses Project Mariner, when needed, to adjust very specific filters. If there's an apartment you want to check out, Gemini uses MCP to access the listings and even schedule a tour on your behalf. And it will keep browsing for new listings for as long as you need, freeing you up to do the stuff you want to do, like plan the housewarming party. it's great for companies like Zillow, bringing in new customers and improving conversion rates. And an experimental version of Agent Mode

in the Gemini app will be coming soon to subscribers. This is a new and emerging area, and we are excited to explore how best to bring the benefits of agents to users and the ecosystem more broadly. The best way we can bring research into reality is to make it really useful, in your own reality. That's where personalization will be really powerful. We are working to bring this to life with something we call Personal Context. With your permission, Gemini models can use relevant context across your Google apps in a way that is private, transparent, and fully

under your control. Let me show you an example in Gmail. You might be familiar with our AI-powered Smart Reply features. It's amazing how popular they are. Now, imagine if those responses could sound like you. That's the idea behind personalized Smart Reply. Let's say my friend wrote to me looking for advice. He's taking a road trip to Utah, and he remembers I did this trip before. Now, if I'm being honest, I would probably reply something short and unhelpful. Sorry, Felix. But with Personalized Smart Replies, I can be a better friend. That's because Gemini can do almost

all the work for me, looking up my notes in Drive, scanning past e-mails for hotel reservations, and finding my itinerary in Google Docs. Trip to Zion National Park. Gemini matches my typical greetings from last e-mails, captures my tone, style, and favorite word choices, and then it automatically generates a reply. I love how it included details like keeping driving time under five hours per day. It uses my favorite adjective, "exciting." Looks great. Maybe you want to make a couple of changes to it and hit Send. This will be available in Gmail this summer for subscribers. [Applause]

And you can imagine how helpful personal context will be across Search, Docs, Gemini and more. Today, I've talked about intelligence, agents, and personalization. These are a few of the frontiers where we will make progress, and you will hear more examples through the keynote. But first, I want to invite someone who can share more about the intelligence driving our future innovation. Last year, I introduced him as Sir Demis. This year, we can add Nobel Laureate to his list of titles. Come on out, Demis. [Applause] >> DEMIS HASSABIS: Hi, everyone. It's really great to be back here

at I/O. We're living through a remarkable moment in history, where AI is making possible an amazing new future. It's been a year of relentless progress for us. As Sundar said, people love interacting with Gemini 2.5. We've seen you vibe-code with it, build games and apps in a single shop. You've used its vast reasoning powers on everything from unpacking scientific papers to understanding YouTube videos. And you've told us how collaborative, insightful, and genuinely helpful you found using Gemini. It's so exciting for us to see the awesome things you've all been doing and building with it. Gemini

2.5 Pro is our most intelligent model ever, and the best foundation model in the world. Just two weeks ago, we shipped a preview of an updated 2.5 Pro, so you could get your hands on it and start building with it right away. We've been really impressed by what you've created, from turning sketches into interactive apps, to simulating entire 3D cities. The new 2.5 Pro tops the popular coding leaderboard, WebDev arena, and now that it incorporates Learn LM, our family of models built with educational experts, 2.5 Pro is also the leading model for learning. And it's

number one across all the leaderboards on LMArena. Gemini Flash is our most efficient workhorse model. It's been incredibly popular with developers, who love its speed and low cost. Today, I'm thrilled to announce we're releasing an updated version of 2.5 Flash. The new Flash is better in nearly every dimension, improving across key benchmarks for reasoning, code and long context. In fact, it's second only to 2.5 Pro on the LMArena leaderboard. I'm excited to say that Flash will be generally available in early June with Pro soon after. [Applause] We're making final adjustments based on your feedback, but

you can go try out the preview now in AI Studio, Vertex AI and the Gemini app. As always, we're looking to push the state-of-the-art relentlessly forward, and we're excited about our latest research advances. To tell you more, I would like to welcome Tulsee to the stage. But first, let's take a look at what you're building with Gemini today. [Music] >> Can you... um... make a bunch of, like, confetti circles explode out of my mouse? >> GEMINI: I've updated the sketch. Okay. What should we build next? >> Here's another 30 ideas for you. [Music] [Applause] >>

TULSEE DOSHI: Thanks, Demis. I'm so excited to share the improvements we are creating to make it easier for developers, like all of you, to build with Gemini 2.5. All based on your feedback, with improved capabilities, enhanced security and transparency, better cost efficiency, and more control. First, in addition to the new 2.5 Flash that Demis mentioned, we are also introducing new previews for text-to-speech. These now have a first-of-its-kind multi-speaker support for two voices, built on native audio output. >> GEMINI: This means the model can converse in more expressive ways. It can capture the really subtle nuances

of how we speak. (whispering) It can even seamlessly switch to a whisper, like this. >> TULSEE DOSHI: This works in over 24 languages. And it can even easily go between languages. >> GEMINI: So the model can begin speaking in English, but then... [Speaking Hindi] And switch back, all with the same voice. >> TULSEE DOSHI: Pretty awesome, right? [Applause] You can use this capability starting today in the Gemini API. [Applause] The Live API will also have a 2.5 Flash preview version of native audio dialogue later today, so you can build conversational experiences with a more natural

Gemini. It's even able to distinguish between the speaker and background voices so it knows when to respond. Logan and Paige will show you more in the developer keynote. Second, we've strengthened protections against security threats, like indirect prompt injections, so Gemini 2.5 is our most secure model yet! And in both 2.5 Pro and Flash, we're including thought summaries via the Gemini API and Vertex AI. Thought Summaries take the model's raw thoughts, and organize them into a clear format with headers, key details, and information about model actions, like tool calls. This gives you increased transparency for what

the model is thinking, which is especially useful for high-latency tasks, while also just being easy to debug and consume. You also asked us for more efficiency, so today's 2.5 Flash is even more efficient, reducing the number of tokens the model needs to use for the same performance, resulting in 22% efficiency gains on our evals. Finally, we launched 2.5 Flash with Thinking Budgets to give you control over cost and latency, versus quality and the response was great so, so we're bringing Thinking Budgets to 2.5 Pro, which will roll out in the coming weeks, along with our

generally available model. With Thinking Budgets, you can have more control over how many tokens the model uses to think before it responds, or you can simply turn it off. Now, as you heard from Demis, Gemini 2.5 Pro is incredible at coding, so now, let me show how you can take any idea you have, and bring it to life. So if you've ever been to the American Museum of Natural History in New York City, it has a set of amazing exhibits, so to bring that to you today, I got 2.5 Pro to code me a simple

web app in Google AI Studio to share some photos and learn more. Here's what I have so far, but I want to make it more interactive. I'm still brainstorming the design, but I've got some ideas. You've seen something like this before, right? Someone comes to you with this brilliant idea scrarahed on a napkin. As a PM, I'm often this "someone." Now, standard two-dimensional web design is one thing, but I wanted to make this 3D. I learned that jumping into 3D isn't easy. It requires learning about all kinds of new things: setting up a scene, camera,

lighting, and more. Luckily for me, 2.5 Pro can help. Here, what I'm going to do is add the image I just showed you of the sphere, and I'm going to add a prompt to ask 2.5 Pro to update my code based on the image. We'll let 2.5 Pro get to work and as you can see, it's starting to think and going ahead and creating a plan based on what I asked for, and it will apply it to my existing code base. Because Gemini is multimodal, it can understand the abstract sphere sketch, and code beautiful 3D

animations applying them to my existing app. This takes about two minutes, so for the purpose of time we're going to do this baking show style, and I'm going to jump to another tab that I ran before the keynote with that same prompt. And here's what 2.5 Pro Generates. Whoa! [Applause] We went from a rough sketch directly to code, updating multiple of my files, and you can actually see it thought for 37 seconds, and you can see the changes it thought through and then the files it updated. We did all of this in AI Studio, so

once I finished prototyping, I can simply deploy the code along with my Gemini API key. So here's our final app in Chrome. Look at these animations! and I didn't need to have advanced knowledge of three.js libraries or figure out the complex 3D math to build this. I know it would have taken forever to do this by hand, and instead, I was able to create this just based on a sketch. I can make this experience even richer with multimodality. So I used 2.5 Flash to add a question to each photo, inviting you to learn a little

more about it. But what if it talked? That's where Gemini's native audio comes in. >> GEMINI: That's a pangolin and its scales are made of keratin just like your fingernails! >> TULSEE DOSHI: Wow, now, we're talking. You can hear how you can add expressive audio right into your apps. And, before I share more, I'll leave this demo with another fun layout that 2.5 Pro coded just for us! [Applause] We've put starter code for anyone to build on top of this demo in Google AI Studio. So go try it out. This is just one example of

how Gemini 2.5 is changing how we build and how you can leverage the incredible capabilities to integrate vision, speech, and coding into your own applications. 2.5 Pro is available on your favorite IDE platforms, and in Google products like Android Studio, Firebase Studio, Gemini Code Assist, and our asynchronous coding agent Jule [Applause] Just submit a task and Jules takes care of the rest: fixing bugs, making updates. It integrates with Github and works on its own. Jules can tackle complex tasks in large code bases that used to take hours, like updating an older version of Node.js. It

can plan the steps, modify files, and more, in minutes. Today, I'm delighted to announce that Jules is now in public beta so anyone can sign up at jules.google. [Applause] Like Demis said, we're always innovating on new approaches to improve our models, including making them more efficient and performant. We first revolutionized image and video generation by pioneering diffusion techniques. A diffusion model learns to generate outputs by refining noise, step by step. Today, we're bringing the power of diffusion to text with our newest research model. This helps it excel at tasks like editing, including in the context

of math and code. Because it doesn't just generate left to right, it can iterate on a solution very quickly and error correct during the generation process. Gemini Diffusion is a state-of-the-art experimental text diffusion model that leverages this parallel generation to achieve extremely low latency. For example, the version of Gemini Diffusion we are releasing today generates five times faster than even 2.0 Flash Lite, our fastest model so far, while matching its coding performance. Take this math example. Ready? Go! If you blinked, you missed it. [Applause] Now earlier, we sped things up, but this time, we're going

to slow it down a little bit. Pretty cool to see the process of how the model gets to the answer of 39. This model is currently in testing with a small group. And we'll continue our work on different approaches, lowering latency in all our Gemini models, with a faster 2.5 Flash Lite coming soon. Now, for more on the future of Gemini, back to you, Demis. [Applause] [Music] >> DEMIS HASSABIS: Thanks, Tulsee. We've been busy exploring the frontiers of thinking capabilities in Gemini 2.5. As we know from our experience with AlphaGo, responses improve when we give

these models more time to think. Today, we're making 2.5 Pro even better by introducing a new mode we're calling DeepThink. It pushes model performance to its limits, delivering groundbreaking results. DeepThink uses our latest cutting-edge research in thinking andnd reasoning, including parallel techniques. So far, we've seen incredible performance. It gets an impressive score on USAMO 2025, currently one of the hardest maths benchmarks. It leads on LiveCodeBench, a difficult benchmark for competition-level coding. Since Gemini has been natively multimodal from the start, it's no surprise that it also excels on the main benchmark measuring this, MM-MU. Because we're

defining the frontier with 2.5 Pro DeepThink, we're taking extra time to conduct more frontier safety evaluations and get further input from safety experts. As part of that, we're going to make it available to trusted testers via the Gemini API, to get their feedback before making it widely available. You'll hear more about our plans for 2.5 Pro DeepThink from Josh later today. Over the past decade, we've laid a lot of the foundations for the modern AI era. From our pioneering work inventing the Transformers architecture, which today underpins all large language models, to agent systems like AlphaGo

and AlphaZero, we continue to double down on the breadth and depth of our fundamental research, to invent the next big breakthroughs that are needed for Artificial General Intelligence. Gemini is already the best multimodal foundation model but we are working hard to extend it, to become what we call a world model. That is a model that can make plans and imagine new experiences by simulating aspects of the world, just like the brain does. This is something I've always been passionate about, having thought about virtual worlds since my early days, developing AI for simulation games like Theme

Park. We've been taking strides in this direction for a while through our pioneering work training agents to master complex games like Go and StarCraft, to most recently our Genie 2 model, capable of generating 3D simulated environments that you can interact with, just from a single image prompt. You can already y e these capabilities emerging, in the way Gemini can use its world knowledge and reasoning to represent things in nature. And in Veo, our state-of-the-art video model, which has a deep understanding of intuitive physics, like how gravity, light and materials behave. It's incredible how well Veo

maintains accuracy and consistency across frames. It knows what to do, even when the prompts get a little creative, like this person made out of life rafts. Understanding the physical environment will also be critical for robotics. AI systems will need world models to operate effectively in the real world. We fine-tuned a specialized model, Gemini Robotics, that teaches robots to do useful things like grasp, follow instructions, and adjust to novel tasks on the fly. For those of you here today, you can play around with the robots in the AI Sandbox. [Applause] Making Gemini a full world model

is a critical step in unlocking a new kind of AI, one that's helpful in your everyday life, that's intelligent and understands the context you are in, and that can plan and take action on your behalf, across any device. This is our ultimate vision for the Gemini app, to transform it into a Universal AI Assistant, an AI that's personal, proactive and powerful, and one of our key milestones on the road to AGI. This starts with the capabilities we first explored last year in Project Astra, such as video understanding, screen sharing, and memory. Over the past year,

we've been integrating capabilities like these into Gemini Live, for more people to experience today. Of course, we continue to relentlessly improve and explore new innovations at the frontier. For example, we've upgraded voice output to be more natural with native audio; we've improved memory; and added computer control. Let's take a look. >> I'm here with the latest research prototype of Projec Astra. And we're going to see how it can help me fix my bike. Hey, go online and look for a user's manual for a Huffy mountain bike. >> I have found a user manual for you.

What would you like to know about it? >> Okay, cool. Now scroll until you find the section about the brakes. >> Sure thing. Looking for that page now. >> I think I've stripped this screw. Can you go on YouTube and find a video for how to fix that? >> Of course. I'm opening YouTube now. This looks like a good video. >> Oh, nice. Thanks. Can you go through my emails with the bike shop and find which size hex nut I need? >> Sure. According to the email from Bicycle Habitat, you need a 3/8 inch hex

nut for your sprocket. I've highlighted the correct bin for you. >> It seems like I need a spare tension screw. Can you call the nearest bike shop and see what they have in stock? >> Yep. Calling them now. I'll get back to you with what they have in stock. >> I think my brake pads are wearing down. Can you check the manual again and see if it talks about them anywhere? >> According to the manual, if you look on page 24. >> Hey! Do you want to get lunch? >> Yeah. Give me five minutes. Can

you finish what you were saying? >> As I was saying, if you look on page 24, section 2, you'll see how to replace the brake pads. >> Hey, any updates on that call? >> Yeah, I just got off with the bike shop. They confirm they have your tension screw in stock. Would you like me to place a pickup order? >> Could you show me some examples of dog baskets I can put on my bike? >> Sure, I can help you with that. Just give me a moment. Here are some options. I think Zuka would look

really great in these. [Applause] >> DEMIS HASSABIS: A universal AI assistant will perform everyday tasks for us. It'll take care of our mundane admin, and surface delightful new recommendations, making us more productive and enriching our lives. We're gathering feedback about these new capabilities now from trusted testers and working to bring them Gemini Live, new experiences in Search, and the Live API for developers, as well as new form factors like Android XR glasses. You'll hear more on this later today. My entire career, at its core, has been about using AI to advance knowledge and accelerate scientific

discovery. At Google DeepMind, we've been applying AI across almost every branch of science for a long time. In just the past year, we've made some huge breakthroughs in a wide range of areas from mathematics to life sciences. We've built AlphaProof, that can solve maths-olympiad problems at the Silver Medal level; Co-Scientist, that can collaborate with researchers helping them develop and test novel hypotheses; and we've just released AlphaEvolve, which can discover new scientific knowledge, and speed up AI training itself. In life sciences, we've built AMIE, a research system that could help clinicians with medical diagnoses; AlphaFold 3,

which can predict the structure and interactions of all of life's molecules; and Isomorphic Labs, which builds on our AlphaFold work to revolutionize the drug discovery process with AI and will one day help to solve many global diseases. In just a few short years, AlphaFold has already had a massive impact in the scientific community. It's become a standard tool for biology and medical research with over 2.5 million researchers worldwide using it in their critical work. As we continue to make progress towards AGI, I've always believed, if done safely and responsibly, it has the potential to accelerate

scientific discovery and be the most beneficial technology ever invented. Taking a step back, it's amazing to me, that even just a few years ago, the frontier technology you're seeing today would have seemed nothing short of magic. It's exciting to see these technologies powering new experiences in products like Search and Gemini, and also coming together to help people in their daily lives. For example, we recently partnered with Aira, a company that assists people in the blind and low-vision community, to navigate the world by connecting them via video to human visual interpreters. Using Astra technology, we built

a prototype to help more people have access to this type of assistance. We're getting ongoing feedback from users, while Aira's interpreters are actively supervising for safety and reliability. [Applause] With this, and all our groundbreaking work, we're building AI that's more personal, proactive and powerful, enriching our lives, advancing the pace of scientific progress and ushering in a new golden age of discovery and wonder! [Music] >> I remember as a child playing until it got dark outside to make sure I could still play guitar without being able to see. I was diagnosed with retinitis pigmentosa when I

was probably about four years old. My vision is actively deteriorating, but music has been something that I can continue to do with the closing in of my visual reality. I feel free when I'm playing music. If Project Astra can help me be more independent, it would be you know the greatest thing ever. Touring, for example, I love it because I get to go out and go to places I've never been before and meet new people, but it definitely is becoming moree difficult. Hello there. Hello. Can you tell me what you see in this greenroom while

I scan around? >> I see a sign on the wall in the direction you're facing. The sign says, "Wi-Fi network. The Grey Eagle, and the password is live music." >> Thank you very much. Can you help me locate a microphone stand? >> Sure. I can help with that. Do you mind if I turn on the flashlight? I see a wall with several coiled cables and what look like mic stands towards the top right in the video. >> The most powerful thing I can do is to get on stage, pick up my guitar and play. It

helps people understand that there's more than just blind or not blind, disability and ability. If Project Astra can help me along the way, I'm all for it. >> Have a great time at your show. [Music] [Applause] >> SUNDAR PICHAI: Thanks, Demis. Amazing to see the possibilities for Project Astra to help with accessibility. It's another exciting example of how AI is advancing our timeless mission to organize the world's information and make it universally accessible and useful. No product embodies our mission more than Google Search. It's the reason we started investing in AI decades ago, and how

we can deliver its benefits at the scale of human curiosity. Our Gemini models are helping to make Google Search more intelligent, agentic and personalized. One great example of progress is our AI Overview Since launching at I/O last year, they have scaled up to over 1.5 billion users every month in more than 200 countries and territories. As people use AI Overviews, we see they are happier with their results, and they search more often. In our biggest markets like the U.S. and India, AI Overviews are driving over 10% growth in the types of queries that show them.

What's particularly exciting is this growth increases over time. It's one of the most successful launches in Search in the past decade. [Applause] AI Overviews are also one of the strongest drivers of growth for visual searches in Google Lens. Lens grew 65% year over year with more than 100 billion visual searches already this year. People are asking more queries. They're also asking more complex queries. With our latest Gemini models, our AI Overviews are of the quality and accuracy you've come to expect from Search and are the fastest in the industry. For those who want an end-to-end

AI search experience, we are introducing an all-new AI Mode. It's a total reimagining of Search. With more advanced reasoning, you can ask AI more longer and more complex queries like this. In fact, users have been asking much longer queries. Two to three times the length of traditional searches, and you can go further with follow-up questions. All of this is available today as a new tab right in Search. I've been using it a lot, and it's completely changed how I use Search, and I'm excited to share that AI Mode is coming to everyone in the U.S.

starting today. [Applause] AI Mode is where we will first bring our frontier capabilities into Search, and starting this week, Gemini 2.5, our most intelligent model series, is coming to Search. To share a whole lot more, here's Liz. [Music] [Applause] >> LIZ REID: Thanks, Sundar. In just one year, there's been a profound shift in how people are using Search. For years, people have come to Google to ask questions like this. And now they're also asking questions that look more like this. They're asking longer questions, harder ones, and as you just heard from Sundar, lots more of

them. They're experiencing what AI-powered Search can do. As we bring together Our Gemini model's advanced capabilities with Search's unparalleled understanding of the Web and the world's information. Today, you'll see how you can ask anything. And a more intelligent, agentic, and personalized Search will take on your toughest questions and help you get stuff done. This is the future of Google Search, a Search that goes beyond information to intelligence. And you're starting to see this come to life already with AI Overviews and AI Mode takes this to the next level. AI Mode is Search transformed with Gemini

2.5 at the core. It's our most powerful AI search, able to tackle any question. And as Sundar announced, we're excited to start rolling out AI Mode for everyone in the U.S., starting today! [Applause] You'll find it as a new tab directly in Search, or right from your search bar. AI Mode will be loaded up with all of our best AI features and capabilities, but it's even more than that; it's a glimpse of what's to come. Over time, we'll graduate many of AI Mode's cutting-edge features and capabilities directly into the core Search experience. That starts today,

as we bring the same models that power AI Mode to power AI Overviews, so you can bring your hardest questions, right to the Search box. Today, we'll give you a tour of AI Mode. You'll see how it works, and how it's getting even better. With personal context, deeper research, complex analysis and visualization, live multimodality, and new ways to shop. That's a lot, because AI Mode can do a lot, so let's dive in. First, with AI Mode, you can ask whatever's on your mind. And as you can see here, Search gets to work. It generates your

response, putting everything together for you, including links to content and creators you might not have otherwise discovered, and merchants and businesses with useful information like ratings. Search uses AI to dynamically adapt the entire UI, the combination of text, images, links, even this map, just for your question. And you can follow up conversationally. AI Mode isn't just giving you information; it's bringing a whole new level of intelligence to Search. What makes this possible is something we call our query fan-out technique. Now, under the hood, Search recognizes when a question needs advanced reasoning. It calls on our

custom version of Gemini to break the question into different subtopics and it issues a multitude of queries simultaneously on your behalf. It searches across the entire web, going way deeper than a traditional search. And it taps into all of our datasets of realtime information, like the Knowledge Graph, Shopping Graph, and in this case, local data, including insights from our Maps community of over 500 million contributors. Search pulls together a response and checks its work to make sure it meets our high bar for information quality. If it detects any gaps, it issues even more searches to

fill them in. That means with AI Mode, you get all this from just a single search, and you get it fas Now, let's take a look at what's coming next to AI Mode starting in Labs. Soon, AI Mode will be able to make your responses even more helpful with personalized suggestions based on your past searches. You can also opt in to connect other Google apps starting with Gmail. We call this Personal Context, and you'll see when AI Mode is bringing yours in to help. So now, based on your recent restaurant bookings and searches, it gets

that you prefer outdoor seating. And since you subscribe to gallery newsletters, it suggests some cool art exhibits to check out while you're in town. That's not all. Because your flight and hotel confirmations are in your inbox, you get event ideas that sync up with when you'll actually be in Nashville, with many nearby where you're staying. You can see how Personal Context in AI Mode makes Search really yours, with recommendations, customized just for you. This is always under your control, and you can choose to connect or disconnect it at any time. Personal Context is coming to

AI Mode this summer. [Applause] Next, for questions where you want an even more thorough response, we're bringing deep research capabilities into AI Mode. You already come to Search today to really unpack a topic but this brings it to a much deeper level. So much so, that we're calling this Deep Search. Deep Search uses the same query fan-out technique you just heard about, but multiplied. It can issue dozens, or even hundreds of searches on your behalf. It reasons across all those disparate pieces of information to create an expert-level, fully cited report in just minutes. It includes

links to the web throughout, so you can easily explore and take action. That's a core part of how we've built AI Mode overall, and how we've always thought about AI in Search, because we believe AI will be the most powerful engine for discovery that the web has ever seen, helping people discover even more of what the web has to offer and find incredible, hyper-relevant content. You're starting to see how Search is becoming more intelligent, and we've got more to show you. So I'll hand it to Rajan, who will share how AI Mode is helping analyze

complex data for one of his passions, sports. [Applause] [Music] >> RAJAN PATEL: Thanks, Liz! Okay. So I'm a huge baseball fan and lately, there's been a lot of buzz about these new torpedo bats. If you don't follow baseball, it's a new bat design where more of the weight of the bat is in the sweet spot. As you can see, I've been digging in on whether it's making a real impact on the game. And now, I'm wondering what the numbers say. So I'll ask: Show the batting average and on-base percentage for this season and last for

notable players who currently use a torpedo bat. Think about it. There are so many parts to that question! Search needs to understand who the notable players are, which ones are using torpedo bats, and their stats. I get this helpful response, including this easy-to-read tabls fresh and accurate, since it uses our sports data that's continuously updated, down to the last strike. Search even brings in important context, like that it's still early in the season. I can follow up and ask: How many home runs have these players hit this season? Just like that, I get this graph.

This goes back to what Liz mentioned about AI Mode dynamically generating the right UI for each response. Search figured out that the best way to present this information is a graph, and it created it. It's like having my very own sports analyst right in Search! Complex analysis and data visualization is coming this summer for sports and financial questions. [Applause] Okay, so all this talk about baseball, made me want to get closer to the game. Like, at-the-next-game close, but finding the perfect tickets can be a chore. So I'm excited to share, that we're bringing Project Mariner's

agentic capabilities into AI Mode. You've already seen how AI Mode is becoming more intelligent and personalized, and here's where you start to see Search getting more agentic. Search can take work off my plate while still under my control. I'll say: Find two affordable tickets for this Saturday's Reds game in the lower level. Search kicks off a query fan-out, looking across several sites to analyze hundreds of potential ticket options doing the tedious work of filling in forms with all the criteria I asked for. And it puts it all together, reasoning across the results to analyze realtime

pricing and inventory. Then right here, task complete! I get great ticket options, with helpful context so I can make an informed decision. Looks like these seats have a good view and at a reasonable price! Search helps me skip a bunch of steps, linking me right to finish checking out. Tickets secured! [Applause] Search will help with tasks like this soon, starting with event tickets, restaurant reservations, and appointments for local services. Next, let's talk about multimodality. We've been blazing the trail for multimodal search since before it was really even a thing. We introduced Google Lens on this

very stage back in 2017. Since then, we've made it easier to search what you see. Snap a picture with Google Lens or simply Circle to Search, and you can get an AI Overview, instantly. Like Sundar mentioned, Visual Search is on fire, and today, I'm excited to share that Lens has over 1.5 billion users every month. Now, we're taking the next big leap in multimodality by bringing Project Astra's Live capabilities into AI Mode. Think about all those questions that are so much simpler to just talk through, and actually show what you mean, like a DIY home

repair, a tricky school assignment, or learning a new skill. We call this Search Live, and now, using your camera, Search can see what you see and give you helpful information as you go back and forth, in real time. It's like hopping on a video call with Search! I have three kids, and they ask about a million questions a minute. And with summer right around the corner, the team and I decided to put Search Live to the ultimate test: Helping us, and our kids, tackle something new. We recorded at home with our families just this past

weekend, let's take a look. >> It looks like you're about to do a fun science experiment. >> All right. Ready Anya? Ready Adi? >> Are you ready for your science experiment? >> Yeah. Can you guess which experiment I'm trying to do? I have hydrogen peroxide and dish soap and yeast. >> You're likely going to make elephant toothpaste. >> How do I know which one of these strawberries is ready to eat? >> I'm trying to get this remote to work. >> Pump it to about 50 pounds per square inch, but don't go over 90 psi. >>

I mixed the baking soda. What do I do next? >> It looks like someone tried dipping a finger into the cinnamon water. >> You could try using different catalyst. Potassium iodide is a good option. >> Whoa, why is it doing that? >> A ripe strawberry will also have a sweet smell. The green leaves at the top should look fresh and vibrant. >> The chemical reaction is going well. >> This is awesome thanks. Whoa! Can we do it again? Go! >> Oh boy. How do I get strawberry stains out of a shirt? >> Try using a

mixtutu of 1 tablespoon of white vinegar. [Music] >> VIDHYA SRINIVASAN: With AI Mode, we are bringing a new level of intelligence to help you shop with Google. As you heard earlier, AI Mode brings in information from the web and our realtime data. In this case, that means you get the visual inspiration of Google Images and the world's most comprehensive set of products and retailers from our Shopping Graph, which has over 50 billion product listings that get constantly updated. Let me show you how this comes together. so I've been on the hunt for a new rug

for my living room. I'll say: I have a light gray couch and am looking for a rug to brighten the room. What I need first is visual inspiration. Search dynamically generates a browsable mosaic of images, and shoppable products, personalized just for me. I see rugs from some of my go-to brands, and more modern options since I often search for things in that style. These are nice, but I know most of them wouldn't survive a day in my home! So I'll add: I have 4 active kids and they like to have friends over. Search understands this

involves plenty of messes! It recommends a low pile, or washable rug made from durable materials, along with some products I can shop. But I don't know a lot about rugs, so luckily Search points out some things to consider, with helpful follow-ups like these. Taking a few days of research down to just a few minutes. You can imagine how helpful this new experience in AI Mode will be for all your shopping needs. Speaking of, I want a few new dresses for summer. Search gave me some great options, but now, I'm faced with the classic online shopping

dilemma. I have no clue how these styles will look on me. So we're introducing a new try-on feature that will help you virtually try on clothes so you get a feel for how styles might look on you. Let me show you a live demo. So I looked at many dresses, and I really like this blue one here. I click on this button try it on. It asks me to upload a picture. I go to my camera roll, and I Have many pictures here, I'm going to pick one here, full length and a clear view of

me. Off it goes. While it's processing, I'll show you what's happening behind the scenes. To create a try-on experience that works at scale, we need a deep understanding of the human body and how clothing looks on it. To do this, we built a custom image generation model, specially trained for fashion. Wow, and it's back! [Applause] I have to say I love a live demo when it works. All right. More on how it works. It brings in 3D shape understanding and helps us better visualize the human body. Our try-on experience works with your photo, not a

precaptured image or model that doesn't look like you. And then, when it comes to clothes you're interested in, the AI model is able to show you how the material folds, stretches, and drapes on people. this technology is the most state of the art in the industry at scale. It allows us to visualize how billions of apparel products look on a wide variety of people. You can see how it really gives me a feel for the way this dress might look on me. All right. So I'm now set on the dress. Search can find it at

the price I want and buy it for me, with our new agentic check-out feature. Let me get back here to the dress. And I'm going to click this thing to track price. I picked my size. Then y t I havo set a target price, $50. And tracking is happening. Search will now continuously check websites where the dress is available and let me know if the price drops. So now, let's switch out of the live demo mode and sprinkle some I/O magic and let's assume the price has now dropped. When that happens, I get a notification

just like this. And if I want to buy, my checkout agent will add the right size and color to my cart. I can choose to review all my payment and shipping information or let the agent just buy it for me. [Applause] With just one tap, Search securely buys it for me with Google Pay. And of course, it's -- all of this happened under my guidance. From inspiration to purchase, our new intelligent capabilities bring the best of shopping together with the best of AI, right here in Search. Our new visual shopping and agentic checkout features are

rolling out in the coming months, and you can start trying on looks in Labs beginning today. [Applause] And now, back to you, Liz! [Music] [Applause] >> LIZ REID: Thanks, Vidhya! As Sundar mentioned, this all gets an even bigger upgrade later this week, when we bring a custom version of Gemini 2.5 to both AI Overviews and AI Mode. This is the next frontier of Google Search, where AI Overviews bring the helpfulness of AI to everyone in the main Search experience. And as you've seen today, AI Mode is a totally reimagined AI Search, with all our most

cutting-edge AI features and capabilities. We couldn't be more excited about this chapter of Google Search, where you can truly ask anything, and we mean anything. Your simplest and your hardest questions, your deepest research, your personalized shopping needs, your just-take-it-off-my-plate tasks. All you have to do is ask. [Music] [Applause] [Music] >> What else should I do to make it stronger? >> To make it stronger, consider adding more triangles to the design. [Music] [Applause] >> JOSH WOODWARD: For years, people have pursued building an AI assistant that doesn't just respond, but understands; one that doesn't just wait, but

anticipates; a truly universal assistant that empowers you. Today, we're taking a new step toward that future and we're using the Gemini app to get there. Our goal is to make Gemini into the most personal proactive, an powerful AI assistant. It starts with being personal. What if your AI assistant was truly yours? Truly yours. An assistant that learns you, your preferences, your projects, your world, and you were always in the driver's seat. And, with your permission, you could share your relevant Google information with it, making it an extension of you. We call this Personal Contex We've

already made it possible for you to connect your Search History with Gemini, so it can understand that you've searched for recipes in the past, and craft responses like this. Starting soon, you'll also be able to add even more personal context from across Google so Gemini will be uniquely helpful. You can choose to turn this on, and you'll always be in control of the experience. You can view and manage this information, as well as connect or disconnect your Google Apps. This level of personalization gives you a more proactive AI assistant, and this changes a lot. See,

today most AI is reactive: You ask, it answers. What if it could see what's coming and help you prepare even before you ask? Imagine you're a student. Your physics exam is looming. Instead of you scrambling, Gemini sees it on your calendar a week out, but it doesn't just remind you; it comes to you with personalized quizzes, crafted from your materials, notes from your professor, even photos, handwritten notes. That's not just helpful; that will feel like magic. And imagine a step beyond that, where Gemini can go off and make custom explainer videos based on your interests,

so you can understand a topic better. In this case, Gemini knows I'm into cycling, so it explains the concept of thermodynamics to me using an analogy I'll understand. This is where we're headed with Gemini, and it's all possible because of the powerful capabilities in the underlying model. Last month, we shipped our latest 2.5 Pro model in the Gemini app, and that wasn't just an upgrade; it was a leap forward. People are doing extraordinary things in the app. They're not just vibe coding; they're inventing entire games and making fully featured websites in minutes. They're thinking things

into existence. And it's fun to write software for the first time or create videos with our Veo model to generate and edit images. It's a new superpower for everyone. So these three Ps -- personal, proactive, powerful -- these are the frontiers of AI assistance, and thanks to 2.5 Pro, we're making big strides across all three. So let's talk more about how all of this is coming together to life in the Gemini app. we're launching five things today. First, let's talk about Gemini Live. People are blown away by How interactive and natural the conversations are. And

it works in more than 45 languages across 150+ countries. And it's so intuitive, so engaging, that conversations are five times longer than the text conversations in the app. I can tell you from personal experience, it's great for talking through things on the drive to work in the morning. As Sundar mentioned, Gemini Live now includes camera and screen sharing, both of which are incredible. It's available free of charge in the Gemini app on Android and iOS today. [Applause] And in the coming weeks, you'll be able to connect Gemini Live to some of your favorite apps, like

Calendar, Maps, Keep, and Tasks. So soon, you can just point your camera and ask it to add this invite to your calendar. And it will be done. Or if you need to decipher your roommate's shopping list, Gemini Live turns those scribbles into a neat list in Google Keep. Our Gemini Live roadmap is overflowing with new ideas that are all being prototyped in Project Astra like you saw earlier, and as those ideas mature, we'll graduate them into Gemini Live for everyone. And since Gemini and Android work so closely together, many of these experiences work great on

Android across the entire ecosystem. So stay tuned for more! realtime interaction is amazing, but sometimes you need to go deep, unravel something complex. This is where Deep Research comes in. Starting today, Deep Research will now let you upload your own files to guide the Research Agent, one of the top requested features. And soon, we'll let you research across Google Drive and Gmail so you can easily pull in information from there, too. So let's say you have this incredible, detailed report. In this case, about the science of comets moving through space. How do you get that

brilliance f comets moving through space. How do you get that brilliance distilled down into something digestible, engaging, something you can share? That's where Canvas comes in, Gemini's space for co-creation. Canvas will now let you transform that report with one tap into all kinds of new things, like a dynamic webpage or infographic, a helpful quiz, even a podcast in 45 languages. , but if you want to go further, You can vibe code all sorts of amazing things in Canvas, with as much back-and-forth as you want to create the experience you're looking for. Check out this interactive

comet simulation that one of our Googlers made just by describing what they wanted to build and collaborating with Gemini to get it just right. And you can now share apps like this so others can jump in to modify it and remix it. This is the power to transform anything, and it's a whole new way to use Gemini. And there's another new way you can use Gemini today, too. we're introducing Gemini in Chrome. This will be your AI assistant that's there for you as you browse the web on your desktop. The amazing part of using it

is that it can understand the context of the page you're on automatically, so if you have a question, it can be answered. I especially love it for comparing reviews on long pages, like this camping website. We're starting to roll out Gemini in Chrome this week to Gemini subscribers in the U [Applause] All right. We've taken some quizzes, talked to Gemini Live, we've learned about comets and campsites. Now it's time to create some things. This is -- Starting today, we're bringing our latest and most capable image generation model to the Gemini app. It's called Imagen 4

and it's a big leap forward. [Applause] The images are richer, with more nuanced colors, and fine-grain Details. The shadows in the different shots, the water droplets that come through in the photos. I've spent a lot of time around these models, and I can say that This model and the progression has gone from good to great to stunning. And Imagen 4 is so much better at text and typography. In the Past you might have created something that looked good, but adding words didn't always look right. So check this out. Maybe I want to create a poster

for a music festival. Let's make the Chrome Dino the big headliner. Imagen 4 doesn't just get the text and spelling Right; it's actually making creative choices like using dinosaur bones in the font or figuring out the spacing, the font size, the layout that makes it look like this great poster. The image quality is higher, the speed is faster, the text is better. All of this lets you make posters, party invites, or anything else. And with Gemini's native image generation, you can easily edit the images right in the app! We've also made a super fast variant

of Imagen 4. We can't wait for you to get your hands on it. In fact, it's 10 times faster than our previous model so you can iterate through many ideas. All right, I want to show you one last thing. images are incredible, but sometimes, you need motion and sound to tell the full story. Last December, Veo 2 came out and redefined video generation For the industry. And if you saw Demis's sizzling onions post yesterday, you know we've been cooking something else, too. Today, I'm excited to announce our new state-of-the-art model, Veo 3. [Applause] And like

a lot of other things you've heard about from the stage today, it's available today. [Applause] The visual quality is even better. Its understanding of physics is stronger. Bought here's the leap forward. Veo 3 comes with native audio generation. [Applause] That means that Veo 3 can generate sound effects, background sounds, and dialogue. Now you prompt it, and your characters can speak. Here's a wise old owl and nervous young badger in the forest. Take a listen. [Music] >> They left behind a ball today. It bounced higher than I can jump. >> What manner of magic is that.

[Applause] >> JOSH WOODWARD: Pretty cool, right? Veo added not just the sounds of the forest, but also the dialogue. We're really entering a new era Of creation with combined audio and video creation that's incredibly realistic. The quality is so good, it feels like you're there, on the boat with this guy. >> This ocean, it's a force, a wild untamed might, and she commands your awe with every breaking light. [Applause] >> JOSH WOODWARD: The photorealistic generation, the emotion, the movement of his Ocean, it's incredible how fast Veo continues to visible as an incredible creative tool We've

been working closely with the film industry to imagine what's possible and get this right, which you'll hear more about in a few minutes. And so that's what's happening around Gemini. Starting today, Gemini live capabilities are free and rolling out across Android and iOS. Deep Research and Canvas are getting their biggest updates yet. There's a new Agent Mode coming for multi-step actions, that you heard about earlier. We're introducing Gemini in Chrome to help you navigate the web. And you can create stunning images and videos with sound using the new Imagen 4 and Veo 3 models. It's

all coming together in the Gemini app as we work to deliver the most personal, proactive, and powerful AI assistant. And now, to go into more detail about how our generative models are unlocking creative expression, here's Jason. [Applause] [Music] >> JASON BALDRIDGE: Thanks, Josh. Whether you're a creator, a musician, or filmmaker, generative media is expanding the boundaries of creativity. By working closely with the artistic community since the very beginning, we continue to build technology that empowers their creative process. For example, we worked with musicians to develop Music AI Sandbox. It's a tool for professionals to explore

the possibilities of our generative music model Lyria in their work. Let's watch a clip starring the legendary, Grammy-award winning, singer and composer Shankar Mahadevan putting Music AI Sandbox and Lyria to use. >> I'm Shankar Mahadevan and I'm a music composer, singer, producer and a happy man. [Music] Working with Sandbox is great. We inputted our requirements and it gave us a bed. We used that bed and we came up with the song. For the musician, it's such an inspiring tool. You open a door and you see, hey, there's another room there, and then you open one

more door and you see one more room there. So that's what AI does. [Music] [Applause] >> JASON BALDRIDGE: Amazing. We recently launched Lyria 2, which can generate high-fidelity music and professional-grade audio. The music is melodious with vocals, in solos and choirs. As you hear, it makes expressive and rich music. [Music] [Applause] Lyria 2 is available today for enterprises, YouTube creators, and musicians. This focus on collaboration carries over not just into what we build, but how. Right now, it's not easy for people or organizations to detect AI-generated images. This will become only more true as technology

improves and the music, audio, images, and videos become more lifelike. So we're continuing to innovate in this space. Two years ago, we pioneered SynthID which embeds invisible watermarks into generated media. To date, over 10 billion pieces of content have been watermarked. We're also expanding our partnerships to ensure that more content is watermarked with SynthID and that more organizations can detect it, too. Finally, we're also making it easier to detect the watermark. Our new SynthID Detector can identify if an image, audio track, text or video has SynthID in it, whether it's in the whole piece or

even just a part. We are starting to roll this out to early testers today. [Applause] Our collaboration efforts have also helped us explore Veo as a filmmaking tool. Recently, we teamed up with visionary Director Darren Aronofsky, and his new storytelling venture "Primordial Soup," to shape Veo's capabilities to meet the needs of storytellers, putting artists in the driver's seat of innovation. Together, we are putting the world's best video generation model into the hands of top filmmakers to push the boundaries of technology as a tool for more creative and emotional storytelling. The first of the partnership's three

short films is director Eliza McNitt's "ANCESTRA." Let's take a peek. >> DARREN ARONOFSKY: Film has always been this deeply human act of connecting people with each other's stories, and it has the ability to rip us out of our experience and take us on another journey. I don't think that ever changes. >> ELIZA MCNITT: This is a story that traverses the entire history of the universe. But it's really about a mom and what happens when her child is born with a hole in her heart. We filmed really emotional performances but then generated video we could never

capture otherwise. I want the baby to be holding the mother's finger. >> DARREN: Just the bliss of the two of them. >> ELIZA McNITT: Veo is a generative video model, but to me it's another lens through which I get to imagine the universe around me. >> DARREN: It's been incredibly interesting to see the strengths of these models, the limits of the models, and try to shape them to make storytelling tools. >> ELIZA McNITT: To be honest, I never thought about telling the story of the day I was born, but here we are. >> This was

supposed to be a checkup. >> Crash C-section. >> Baby's in distress. We need help here! We need to go. >> Is my baby going to be OK? >> We're going to do everything we can. >> Am I going to be okay? >> NARRATOR: For every creature that came before you, from every star that died so that you could begin. [Music] [Applause] >> JASON BALDRIDGE: Incredible work! [Applause] Eliza combined live-action performance with Veo-generated video, like the microscopic worlds, cosmic events and herself as a newborn. This approach opened up completely new storytelling possibilities, empowering Eliza to bring

cinematic scale and emotion to a deeply personal story. This partnership also helped shape Veo's capabilities to meet the needs of storytellers like Eliza. We've built new capabilities for film-makers, so when you're making a video, it will use ingredients you give it: Characters, scenes or styles and keep them consistent. Or you can direct Veo, giving it precise camera instructions and have it shoot along a specific path. These capabilities help filmmakers fluidly express their ideas with Veo. We then took things one step further. To tell you more, let's get Josh back out here. Pretty much [Music] [Applause]

>> JOSH WOODWARD: Thanks, Jason. Done in collaboration with the creative community we've been building a new AI filmmaking tool for creatives that combines the best of Veo, Imagen, and Gemini, a tool built for creatives, by creatives. It's inspired by that magical feeling you get when you're lost in the creative zone and time slows down. We're calling it Flow, and it's launching today. Let me show you how it work [Applause] Let's drop into a project I'm working on. Our hero, the grandpa, is building a flying car with help from a feathered friend. These are my ingredients:

the old man and his car. We make it easy to upload your own images into the tool, or you can generate them on the fly using Imagen which is built right in. We can create agamis gold gearshift just by describing it Next, we can start to assemble all of those clips together. With a single prompt, you can describe what you want, including very precise camera controls. Flow puts everything in place. And I can keep iterating in the scene builder. Here's where it gets really exciting. If I want to capture the next shot of the scene,

I just just hit the plus icon to create the next shot. I can also describe what I want to happen next, like adding a 10 foot tall chicken in the backseat and Flow does the rest. The character consistency, the scene consistency, it just works. And if something isn't quite right, no problem. You can just go back in like any other video tool and trim it up, if it's not working for you. But Flow works in the other direction as well. It lets me extend a clip too, so I can get that perfect ending I've been

working toward. Once I've got all the clips I need, I download the files. I can bring them into my favorite editing software, add in music from Lyria. Now the old man finally has his flying car. [Music] >> JOSH WOODWARD: Pretty awesome. I want you to hear a few words from a few AI filmmakers who have been using Flow and how they describe using it, and how they're making it even better. Let's take a watch. >> I don't know if I'm on the right path, but I'm trying to find it. I'm questioning, searching, and something shifts,

and I'm not trying anymore, I'm just doing. And all the pieces start falling into place. [Music] >> It all feels pretty clear in my head. I see these like flashes of possibilities, almost like I'm traveling through dimensions. >> I'm looking down at myself and my characters in these different worlds, and it's almost coming to life on their own, even though I know I'm in control of that narrative. It feels like it's almost building upon itself at some point. You know, you could have an infinite amount of endings to your story. >> So the work isn't

built brick by brick by brick. It blooms like a spontaneous garden. It grows naturally, fully vibrant and complete. >> I'm not forcing it. I'm just finding it. And that's when know I'm in the right place. [Music] >> JOSH WOODWARD: It's so amazing to hear those filmmakers talk about bringing their incredible visions to life. That feeling of building and creating, that's exactly what we want to put in your hands today. So I'm excited to share that we're upgrading two AI subscription plans. We will have Google AI Pro and Google AI Ultra. With the Pro plan, which

is going to be available globally, you'll get a full suite of AI products with higher rate limits and special features compared to the free version. This includes the Pro version of the Gemini app that was formally known as Gemini Advanced. Then there's the Ultra plan. It's for the trailblazers, the pioneers, Those of you who want cutting edge AI from Google. This plan comes with the highest rate limits, the earliest access to new features and products from across Google. It's available in the US today, and we'll be rolling it out globally soon. You can think of

this Ultra plan as your VIP pass for Google AI. So if you're an Ultra subscriber, you'll get huge rate limits and access to that 2.5 Pro Deep Think mode in the Gemini app when it's ready. You'll also get first access to Flow with Veo 3 available today. It also comes with YouTube Premium and a massive amount of storage. We can't wait to see what you build, create, and discover with these new Google AI plans. And now, to give you a look ahead Into how AI is interacting with the physical world, please welcome up Shahram. [Music]

[Applause] >> SHAHRAM IZADI: Hi, everyone. There's so many exciting things happening in Android right now. It's the platform where you see the future first. Just last week at the Android Show, we unveiled a bold new design and major updates to Android 16 and Wear OS 6. And of course, Android is the best place to experience AI. Many of the Gemini breakthroughs you saw today are coming soon to Android. You can already access Gemini instantly from the power button. It understands your context and is ready to help. But Android is powering more than your phone; it's

an entire ecosystem of devices. In the coming months, we're bringing Gemini to your watch, your car's dashboard, even your TV, so wherever you are, you have a helpful AI assistant to make your life easier. But what about emerging form factors that could let you experience an AI assistant in new ways? That's exactly why we are building Android XR. [Applause] It's the first Android platform built in the Gemini era, and it supports a broad spectrum of devices for different use cases, from headsets, to glasses, and everything in between. We believe there's not a one-size-fits-all for XR,

and you'll use different devices throughout your day. For example, for watching movies, playing games, or getting work done, you'll want an immersive headset. But when you are on the go, you'll want lightweight glasses that can give you timely information without reaching for your phone. We built Android XR together as one team with Samsung and optimized it for Snapdragon with Qualcomm. Since releasing the Android XR developer preview last year, hundreds of developers are building for the platform. We're also reimagining your favorite Google apps for XR. And it's Android after all, so your mobile and tablet apps

work too. Now, today, I want to share how Gemini transforms the way you experience both headsets and glasses. On these devices, your AI assistant understands your context and intent in richer ways to help you throughout your day. Let's start with Gemini on headsets. This is Samsung's Project Moohan, the first Android XR device. [Applause] Moohan gives you an infinite screen to explore your apps with Gemini by your side. With Google Maps in XR, you can teleport anywhere in the world, simply by asking Gemini to take you there. You can talk with your AI assistant about anything

you see, and have it pull up videos and websites about what you're exploring. So many of us dream about sitting front row to watch our favorite team. Imagine watching them play in the MLB app as if you were right there in the stadium while chatting with Gemini about player and game stats. Samsung's Project Moohan will be available for purchase later this year. We can't wait for you to try it for yourselves. Now, let's turn our attention to glasses. As you know we've been working on glasses for over 10 years, and we've never stopped. Glasses with

Android XR are lightweight and designed for all-day wear, even though they are packed with technology. A camera and microphones give Gemini the ability to see and hear the world; speakers let you listen to the AI, play music or take calls. And an optional, in-lens display privately shows you helpful information just when you need it. These glasses work with your phone, giving you access to your apps while keeping your hands free. All this makes glasses a natural form factor for AI, bringing the power of Gemini right to where you are. So unlike Clark Kent, you can

get superpowers when you put your glasses on. Okay. Who's up for seeing an eaearly demo of Android XR glasses? Let's see how they work in the most hectic environment possible, backstage at I/O. Our very own Superwoman Nishtha, is back there to show us how these glasses work for real. Let me send her a text now, and get started. >> NISHTHA BHATIA: Hey, everyone! Right now, you should be seeing exactly what I'm seeing through the lens of my Android XR glasses, including this delicious coffee and that text from Shahram that just came in. Let's see what

he said. All right, it's definitely show time, so I'm going to launch Gemini and get us going. Send Shahram a text that I'm getting started and silence my notifications, please. >> GEMINI: Okay. I've sent that message to him and muted all your notifications. >> NISHTHA BHATIA: Perfect. >> DIETER BOHN: Hey, Nishtha. I see the light's on on your glasses, so it's safe to say we're live right now? >> NISHTHA BHATIA: We're officially on with the I/O crew >> DIETER BOHN: It's pretty great to see I/O from this angle. You promised me my own pair of

glasses if I helped out back here, so what do you say? >> NISHTHA BHATIA: Of course. Let's get coffee after this, and I'll bring you those glasses. >> DIETER BOHN: Awesome, I'll see you then. Good luck. >> NISHTHA BHATIA: As you can see, there's a ton going on back stage. Is that pro basketball player Giannis wearing our glasses? >> GIANNIS: I love this. It frees up both my hands. >> NISHTHA BHATIA: Let me show you what these glasses can do. I've been curious about this photo wall all day. Like what band is this? And how

are they connected to this place? >> GEMINI: That's Counting Crows, a legendary rock band based in the Bay Area. They've played numerous shows at Shoreline amphitheater, which are often seen as homecoming shows for the band. >> NISHTHA BHATIA: No way. Can you show me a photo of one of their performances here? Pretty >> GEMINI: Sure. Here's one. Want me to play one of their songs? >> NISHTHA BHATIA: I would love that. I can listen while I make my way to the stage. >> GEMINI: Great. Here's Under the Aurora by Counting Crows. >> SHAHRAM IZADI: Who's

ready to see these glasses? Welcome, Nishtha! >> NISHTHA BHATIA: Hey, everyone! >> SHAHRAM IZADI: Thanks for that star-studded behind the keens look. By the way, do you want to book that coffee with Dieter now? >> NISHTHA BHATIA: The crew gave me some great coffee back stage. So let me try something fun. What was the name of the coffee shop on the cup I had earlier? >> GEMINI: Hmm, that might have been Bloomsgiving. From what I can tell, it's a vibrant coffee shop on Castro street. >> NISHTHA BHATIA: Great memory. [Applause] Can you show me some

photos of that cafe? I want to check out the vibe. >> GEMINI: Definitely. Do these photos from Maps help? >> SHAHRAM IZADI: I know that shot. It's a flower shop, as well as a flower shop, but it is downtown. >> NISHTHA BHATIA: Okay. Gemini, show me what it would take to walk here. >> GEMINI: Getting those directions now. It will take you about an hour. >> NISHTHA BHATIA: Okay. I can get some steps in and the heads-up directions, and the full 3D map should make it super easy. [Applause] Go ahead and send Dieter an invite

for that cafe and get coffee at 3:00 p.m. today. >> GEMINI: I'll send out that invite now. Enjoy the coffee! >> SHAHRAM IZADI: As you saw, Gemini helped Nishtha search what she sees, remember details like the coffee cup, book an event, even navigate, all without taking her phone out of her pocket. I'm even wearing the glasses right now too, they are my personal teleprompter! and I have prescription lenses, so I can see you all. This is a big moment for glasses. Let's capture it. >> NISHTHA BHATIA: Yes. Get ready for a quick photo everyone, and

let's bring out our star! All right., Gemini. Take a photo for me! [Applause] All right, Gemini, take a photo for me and add it to my favorites. >> SHAHRAM IZADI: That looks amazing. [Applause] I'm completely starstruck. Okay. One last thing. Sundar showed what's possible with live translation earlier. Let's see what that's like on glasses. This is a very risky demo, but we're going to give it a shot. Nishtha and I are going to speak to each other in our mother tongues. Nishtha is going to speak Hindi, and I'm going to speak Farsi very poorly. You'll

see the feed from both of our glasses back here, so you can all follow along. We'll show an English translation in real time. Okay Let's give it a shot. Fingers crossed! [Speaking native languages] >> NISHTHA BHATIA: (Speaking Hindi) >> SHAHRAM IZADI: (Speaking Farsi) We said it's a risky demo. [Applause] Thank you so much. >> SHAHRAM IZADI: Thank you, Nishtha, for that awesome tour of Android XR glasses. We're so excited about the possibilities when you have an incredibly helpful AI assistant by your side with these Android XR devices. But that's not all. We're taking our partnership

with Samsung to the next level by extending Android XR beyond headsets to glasses. We're creating the software and reference hardware platform to enable the ecosystem to build great glasses alongside us. Our glasses prototypes are already being used by trusted testers. And you'll be able to start developing for glasses later this year. Now, we know that these need to be stylish glasses you'll want to wear all day. That's why I'm excited to announce today that Gentle Monster and Warby Parker will be the first eyewear partners to build glasses with Android XR. [Applause] We want you to

be able to wear glasses that match your personal taste. This is just the start. I can't wait for you to try Android XR for yourself, and we'll have lots more to share in the months ahead. Thank you so much! [Applause] [Music] >> SUNDAR PICHAI: Those XR glasses are amazing! Research to reality, literally right in front of our eyes. Okay. So we are nearing the end of the show. Today, you've heard a lot about ELO scores, benchmarks, and state-of-the-art performance. But I know there's one metric you all have been waiting for, our AI counter. So let's

take a Look at one last leaderboard. It looks like I guess we have a new entrant, Gemini takes the lead, coming in at 95. Very exhilarating. [Applause] On a more serious note, here's everything we've announced today. From new launches and product expansion to glimmers of what's to come, the opportunity with AI is truly as big as it gets, and it will be up to this wave of developers, technology builders and problem solvers to make sure its benefits reach as many people as possible. I want to leave you with a few examples that inspire me. The

first is top of mind for those who live here in California and so many other places around the world. So many of us know someone who has been affected by wildfires. They can start suddenly and grow out of control in a matter of minutes. Speed and precision can make all the difference. Together with an amazing group of partners, we are building something called Firesat, a constellation of satellites that use multispectral satellite imagery and AI, aiming to provide near-realtime insights. Just look at the resolution. It can detect fires as small as 270 square feet or about

the size of a one-car garage. Our size of a one-car garage. Our first satellite is in orbit now. When fully operational, imagery will be updated with a much greater frequency, down from every 12 hours today to every 20 minutes. [Applause] Speed is also of the essence in other kinds of emergencies During Hurricane Helene, Wing in partnership with Walmart and the Red Cross, provided relief efforts with drone deliveries, supported by AI, we were able to deliver critical items like food and medicine to a YMCA shelter in North Carolina based on realtime needs. We can imagine how

this would be helpful in disaster relief in other communities, and we are actively working to scale up. These are examples of ways AI is helping society right now. This is especially inspiring to think about the research of today that will become reality in a few short years. Whether it's building the next generation of helpful robots, finding treatments for the world's deadly diseases, advancing error-corrective quantum computers or delivering fully autonomous vehicles that can safely bring you anywhere you want to go, all of this is very much possible within not decades, but years. It's amazing. This opportunity

to improve lives is not something I take for granted. A recent experience brought that home for me. I was in San Francisco with my parents. The first thing they wanted to do was ride in a Waymo, like a lot of other tourists. I had taken Waymos before, but watching my father who's in his 80s in the front seat be totally amazed, I saw the progress in a whole new light. It's a reminder of the incredible power of technology to inspire and move us forward. And I can't wait to see what amazing things we will build

together next. Thank you. [Applause] [thumping beat] >> I see ... infinite possibilities with Flow. >> What manner of magic is that? >> AI Mode is the biggest revolution since the search engine was invented. >> You tell Gemini exactly what you want built, and it builds it for you. >> No! >> Coding with Gemini 2.5 Pro, it is awesome! >> Project Mariner is gonna change how we use our browsers. >> It's an AI agent that gets things done for you. >> NotebookLM's Mind Map completely transforms learning. >> Why is this person following me wherever I walk?

>> GEMINI: That's just your shadow. >> Wait, you're gonna turn right?! >> AI is completely changing how we fight fires. >> Generative media is expanding the boundaries of creativity. >> It was magic the first time I saw this. >> This isn't just another tool. >> It's a game changer. >> This is just like, mindblowing. >> The potential is almost limitless. [Music]