Google I/O ’25 Keynote

Google I/O ’25 Keynote

[APPLAUSE, CHEERING] SUNDAR PICHAI: Wow, cool video. Looks like the team has
been having some fun. Hello, everyone. Good morning. Welcome to Google I/O. [APPLAUSE, CHEERING] 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. I’m 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’d 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 breakthrough like AlphaEvolve
just 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 have 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, CHEERING] It is state of the art
on many, many benchmarks. And we have also made
rapid progress in coding. Our updated 2.5 Pro reached
number one on WebDev Arena, and now surpasses the previous
version by 140 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
every single 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, CHEERING] It earned all eight badges,
traveled to Victory Road, defeated the Elite
Four, and the champion, bringing us one step closer
to achieving API, Artificial Pokemon Intelligence. [APPLAUSE, CHEERING] All of 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 design to power
thinking and inference at scale. It delivers 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. 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
this parade of 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. It’s 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’re also seeing
a wave of adoption across our developer AI 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. 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 are also 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
the 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– projects Starline,
Astra, and Mariner. We debuted project Starline,
our breakthrough 3D video technology, at I/O
a few years back. The goal was to create a feeling
of being in the same room as someone, even if
you were far apart. We’ve 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. And with AI, we can merge
these video streams together and render you on a
3D lightfield 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, CHEERING] Over the years, we’ve been
bringing underlying technology from Starline into Google Meet. That includes real-time
speech translation to help 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. [VIDEO PLAYBACK] – Hi, Camilla. Let me turn on
speech translation. It’s nice to
finally talk to you. – [NON-ENGLISH SPEECH] – [NON-ENGLISH SPEECH] – 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. Is the house– – [NON-ENGLISH SPEECH] – [NON-ENGLISH SPEECH] – There’s a bus nearby, but I
would recommend renting a car so you can visit the
nature and enjoy it. – That sounds great
[NON-ENGLISH SPEECH] [END PLAYBACK] [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 real-time 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 real-time translation
will be coming to Enterprises later this year. [APPLAUSE] Another early research project
that debuted on the I/O stage was Project Astro. 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 Astro’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. [VIDEO PLAYBACK] – That’s a pretty
nice convertible. – 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? – It’s a street
light, not a building. – Why are these
palm trees so short? I’m worried about them. – They’re not short. They’re actually pretty tall. – Sick convertible. – Garbage truck again. Anything else? – Why do people keep
delivering packages to my lawn? – It’s not a package. It’s a utility box. – Why is this person
following me wherever I walk? – No one’s following you. That’s just your shadow. [END PLAYBACK] [APPLAUSE, CHEERING] SUNDAR PICHAI: Gemini is
pretty good at telling you when you’re wrong. We are rolling this
out to everyone on Android and iOS
starting today. [APPLAUSE, CHEERING] Next, we also have our research
prototype Project Mariner. It’s 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 operate 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 have 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 a 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 UiPath, 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 an open
Agent2Agent protocols so that agents can
talk to each other. We launched this at Cloud
Next, with the support of over 60 technology
partners, and hope to see that number grow. Then there is the 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. Say 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’d 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’ll keep browsing for
new listings for as long as you need, freeing
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. An experimental version of the
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 Replies. 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
and drive, scanning past emails for
reservations, and finding my itinerary in Google Docs,
trip to Zion National Park. Gemini matches my typical
greetings from past emails, 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, and
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, CHEERING] And you can imagine how
helpful personal contacts 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’ll hear more examples
throughout 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. [MUSIC PLAYING] DEMIS HASSABIS: Hey, 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, building games and
apps in a single shot. 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
LearnLM, 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
that 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, CHEERING] We’re making final adjustments
based on your feedback, but you can go try
out the preview now in AI Studio, Vertex
AI, and 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’d like to
welcome Tulsee to the stage, but first, let’s take
a look at what you’re building with Gemini today. [VIDEO PLAYBACK] [MUSIC PLAYING] – Can you make a bunch
of confetti circles explode out of my mouse? – I’ve updated the sketch. – OK, what should we build next? – OK, here’s another
30 ideas for you. [END PLAYBACK] [APPLAUSE, CHEERING] TULSEE DOSHI: Thanks, Demis. I’m so excited to share
the improvements we’re 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. [AUDIO PLAYBACK] – This means the
model can converse in more expressive ways. It can capture the really
subtle nuances of how we speak. (WHISPERS) It can even
seamlessly switch to a whisper, like this. [END PLAYBACK] TULSEE DOSHI: This works
in over 24 languages, and it can easily go
between languages. [AUDIO PLAYBACK] – So the model can begin
speaking in English, but then– [NON-ENGLISH SPEECH]
–and switch back, all with the same voice. [END BLAYBACK] TULSEE DOSHI: That’s
pretty awesome, right? [APPLAUSE] You can use this text-to-speech
capability starting today in the Gemini API. [APPLAUSE, CHEERING] The Live API will also
have a 2.5 Flash preview version of Native Audio
dialogue later today. So you can directly 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. And 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 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 you 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. So here’s what I have
so far, but I want to make it more interactive. And I’m still brainstorming the
design, but I’ve got some ideas. You’ve seen something
like this before. Someone comes to you with
a brilliant idea scratched 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 it 3D. And 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. So here, what I’m
going to do is I am going to add the image I
just showed you of the sphere, and I’m going to add in a prompt
that asks 2.5 Pro to update my code based on the image. So we’ll let 2.5
Pro get to work. And as you can see,
it’s starting to think, and it’s going ahead
and creating a plan based on what I asked for. And it’ll 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. So 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 right before this
keynote, with the same prompts. And here’s what
Gemini generates. Whoa! [APPLAUSE] We went from that rough
sketch directly to code, updating multiple of my files. And actually, you can 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. [AUDIO PLAYBACK] – That’s a pangolin. And its scales are
made of keratin, just like your fingernails. [END PLAYBACK] 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 the starter
code for anyone to build on top of this
demo in Google AI Studio, so go try it out. And 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, Jules. [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. So today, I’m
delighted to announce that Jules is now
in public beta, so anyone can sign
up at Jules Google. [APPLAUSE] And 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’re releasing today
generates five times faster than even 2.0 Flash-Lite,
our fastest model so far, while matching
its coding performance. So 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
testing with a small group. And we’ll continue our work
on different approaches, lowering latency in all
of our Gemini models with a faster 2.5
Flash-Lite coming soon. And now, for more on the future
of Gemini, back to you, Demis. [MUSIC PLAYING, APPLAUSE] 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 Deep Think It pushes model
performance to its limits, delivering
groundbreaking results. Deep Think uses our latest
cutting-edge research in thinking and reasoning,
including parallel techniques. So far, we’ve seen
incredible performance. It gets an impressive
score on USAMO 2025, currently one of the
hardest math benchmarks. It leads on LiveCodeBench,
a difficult benchmark for competition level coding. And since Gemini has
been natively multimodal from the start, it’s no
surprise that it also excels on the main benchmark
measuring this, MMMU. Because we’re
defining the frontier with 2.5 Pro Deep Think,
we’re taking a little bit of 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 Deep Think 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’re 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 see 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 really 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, CHEERING] 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’re 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. [VIDEO PLAYBACK] – I’m here with the
latest research prototype of Project Astra,
and we’re going to see how it can
help me fix my bike. [MUSIC PLAYING] 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? – OK, cool. Now scroll until you find
the section about the brakes. – Sure thing. Looking for that page now. – I think I 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. – Place a rubber band over
the head of the screw– – Oh, nice. Nice. 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? – Yep. I just got off
with the bike shop. They confirmed 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 could 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. [END PLAYBACK] [APPLAUSE, CHEERING] DEMIS HASSABIS: A
universal AI assistant will perform everyday
tasks for us. It will take care
of 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 to 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 Math Olympiad problems at the silver medal
level, coscientists 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 the 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. [APPLAUSE, CHEERING] 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, CHEERING] 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. [VIDEO PLAYBACK] – I remember as a child playing
till 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 the
greatest thing ever. [MUSIC PLAYING] 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 more difficult. – Hello there. – Hello. Can you tell me what you
see in this green room while I scan around? – I see a sign on the wall in
the direction you’re facing. The sign says, Wi-Fi
network, The Gray Eagle. And the password is LIVEMUSIC. – 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? – Yes, please. – 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. Helps people
understand that there’s more than just blind or not
blind, disability and ability. If Project Astra could help me
along the way, I’m all for it. – Have a great
time at your show. [END PLAYBACK] [APPLAUSE] SUNDAR PICHAI: Thanks, Demis. It’s 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 Overviews. 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 US and India, AI Overviews are driving
over 10% growth in the types of queries that show them. What’s particularly
exciting is that 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. So people are
asking more queries, and they’re also asking
more complex queries. With our latest Gemini
models, our AI Overviews are at 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 Mode 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 US starting today. [APPLAUSE, CHEERING] 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 PLAYING, 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 its 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 US, 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, and 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. Now, that’s a lot because
AI Mode can do a lot. So let’s dive in. First, with AI mode, you can
ask whatever is 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. Now, 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
fanout 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 data
sets of real-time information, like the knowledge graph,
the 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 it checks its work to make
sure it meets our high bar for information quality. And if it detects any gaps,
it issues even more searches to fill them in. That means, with
AI Mode, you get all of this from
just a single search. And you get it fast. 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
those gallery newsletters, it suggests some cool
art exhibits to check out while you’re in town. But 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
contacts in AI Mode make search really yours, with
recommendations customized just for you. Now, this is always
under your control, and you can choose to connect
or disconnect at any time. Personal context is coming
to AI Mode this summer. [APPLAUSE, CHEERING] Next, for questions
when 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 fanout 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-sighted report in just minutes. It includes links to
the web throughout, so you can easily
explore and take action. Now, 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
over to Rajan, who will share how AI
Mode is helping analyze complex data for
one of his passions, sports. [MUSIC PLAYING, APPLAUSE] RAJAN PATEL: Thanks, Liz. OK, 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 table. And I know that this
is 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? And 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] 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 fanout,
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 real time
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. And since then, we’ve made
it even easier to search what you see. Snap a picture with Google Lens,
or simply circle the 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. [APPLAUSE] 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. [VIDEO PLAYBACK] – It looks like you’re about
to do a fun science experiment. – All right. Ready, Anja? Ready, Addy? – Yep. – OK. – 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. – I know which one of these
strawberries is ready to eat. – I’m trying to get
this remote to work. – It looks like someone is
ready to get their hands dirty and plant a green bean seedling. Pop 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. – What should I do to make
this even more impressive? – You could try using
a 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. – Whoa. – Can we do it again? – Go. – Oh, boy. How do I get strawberry
stains out of her shirt? – Try using a mix of 1
tablespoon white vinegar, half a teaspoon liquid
laundry detergent. [END PLAYBACK] [MUSIC PLAYING, APPLAUSE] 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 real-time 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 have been on the hunt for
a new rug for my living room. I’ll say, I have a light gray
couch, and I’m looking for a rug to brighten the room. What I need first is
visual inspiration. Search dynamically
generates a browsable mosaic of images and some
shoppable products personalized just for me. I see rugs from some of my
go-to brands and some more modern options, since I often
search for things in that style. Now, these are nice,
but I know most of them wouldn’t survive
a day in my home. So I’ll add, I have
four active kids and they like to
have friends over. Search understands this
involves plenty of messes. It recommends a low
pile and washable rug made from durable materials,
along with some products that I can shop. But I don’t know
a lot about rugs. So luckily, Search points
out some things to consider. And 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 of
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 are 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. I click on this
button to try it on. It asked me to upload
a picture, which takes me to my camera roll. I have many pictures here. I’m going to pick one that is
full length and a clear view of me. And 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 specifically
trained for fashion. Wow. And it’s back. [APPLAUSE, CHEERING] I have to say, I love a
live demo when it works. All right. More on how it works. It brings in advanced
3D shape understanding, which allows us to perceive
perceived shapes and depths more accurately, helping us better
visualize the human body. Our try-on experience
works with your photo. It’s not some pre-captured
image or a model that doesn’t look like you. And then, when it
comes to clothes that you’re interested
in, the AI model is able to show how this
material will fold, and stretch, and drape on people. This technology
is the most state of the art in the
industry at scale. And it allows us to visualize
how billions of apparel products look on a wide
variety of people. And you can see it here
how it really gives me a feel for how this
dress might look on me. All right. So I’m now set on the dress. And Search can help me find
it at the price that I want and buy it for me with our
new agentic checkout feature. So let me get back
here to the dress. And I’m going to click
this thing to track price. I pick my size. Then I have to set
a target price. I’m going to set
it to about $50. And tracking is happening. Search will now
continuously check websites where the dress is
available and then let me know if the price drops. So now let’s switch out
of our live demo mode, and then I’m going to
sprinkle some I/O magic. And let’s assume the
price is 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 just let the agent
just buy it for me. [APPLAUSE, CHEERING] With just one tap,
Search security buys it for me with Google Pay. And of course, 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, CHEERING] And now back to you, Liz. [MUSIC PLAYING] 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. [VIDEO PLAYBACK] [MUSIC PLAYING] – What else should I
do to make it stronger? – To make it stronger. Consider adding more
triangles to the design. [MUSIC PLAYING] [END PLAYBACK] [MUSIC PLAYING, 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 anticipate, a truly
universal assistant that empowers you. And today, we’re taking a new
step forward to that future. And we’re using the
Gemini app to get there. Our goal is to make Gemini
the most personal, proactive, and powerful AI assistant. And 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 are always in the driver’s seat? And with your permission, you
could share relevant Google information with it, making
it an extension of you. We call this personal context. And 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 be able to
add even more personal context from across Google to Gemini. So it 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 your information as well as connect
and disconnect different 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. But what if it could
see what’s coming and help you prepare
even before you ask? Imagine you’re a student. You’ve got a big
physics exam looming. And instead of
scrambling, Gemini sees it on your
calendar a week out. But it doesn’t just remind you. It comes with personalized
quizzes crafted from your materials, notes
from your professor, even photos, handwritten notes. That’s not just helpful. It’s going to feel like magic. And imagine the
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
that I’m into cycling, so it explains this 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 and the underlying model. Last month, we shipped
our latest 2.5 Pro model in the Gemini app. And it 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 a video
with our Veo model, to generate and edit images. It’s a new superpower
for everyone. And so these three Ps– personal, proactive,
and powerful– these are the frontiers
of AI assistants. And thanks to 2.5 Pro,
we’re making big strides across all three. So let’s talk more about how
all 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
over 45 languages, more than 150 countries. It’s so intuitive, so engaging. The conversations, in
fact, are five times longer than the text
conversations in the app. And I can tell you from
personal experience, it’s great for talking
through things on the drive into work in the morning. Now, as Sundar
mentioned, Gemini Live now includes camera and
screen sharing, both of which are incredible. All of it is rolling out free
of charge in the Gemini app on Android and iOS today. [APPLAUSE, CHEERING] And in the coming
weeks, you’ll be able to connect Gemini Live
to some of your favorite apps, like Calendar,
Maps, Keep, Tasks. So soon, you can just
point your camera and ask it to add an
invite to your calendar, and it’ll be done. Or if you need to decipher
your roommate’s handwriting for the shopping
list, Gemini Live can turn those scribbles into
a neat list in Google Keep. Our Gemini Live
roadmap is overflowing with exciting things. They’re 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 those experiences
will work great on Android across the entire ecosystem. So stay tuned for more. All right. Real-time 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, which is 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, it’s about
the science of comets moving throughout space. How do you get all that
brilliance distilled down into something
digestible, engaging, something you can share? This is where Canvas comes in. It’s Gemini’s interactive
space for cocreation. Canvas will now let you
transform that report with one tap into all kinds
of new things, like a dynamic web page, an
infographic, a helpful quiz, even a custom 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. You can get exactly 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 as you can share
apps like this, others can easily jump in
and view it, and modify it, and remix it. This is the power to
transform anything, and it’s a whole new
way to use Gemini. 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 is
that you can use this. And it understands the
context of the page that 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 US. [APPLAUSE, CHEERING] All right. We’ve taken some quizzes. We’ve talked to Gemini Live. We’ve learned about
comets and in campsites. Now it’s time to
create some things. Starting today, we’re bringing
our latest and most capable image generation model
into the Gemini app. It’s called Imagen 4, and
it’s a big leap forward. [APPLAUSE, CHEERING] The images are richer, with more
nuanced colors and fine grained 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 this model,
and the progression has gone from good
to great to stunning. And Imagen 4 is so much
better at text and topography. In the past, you might
have created something that looked good,
but adding words didn’t always work just right. So check this out. Maybe I want to create a
poster for a music festival. We’ll 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. So the image quality is higher. The speed is faster. The text is better. All of this lets
you make posters, party invites,
and anything else. And with Gemini’s
native image generation, you can easily edit these
images too, 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 quickly. All right. I want to show you
one last thing. Images are incredible,
but sometimes you need motion and sound
to tell the whole story. Last December, Veo
2 came out, and it redefined video generation
for the industry. And if you saw Demi’s sizzling
onions post yesterday, you know that we’ve been
cooking something else. Today, I’m excited to announce
our new state of the art model, Veo 3. [APPLAUSE, CHEERING] And like a lot of other things
you’ve heard about from stage today, it’s available today. [APPLAUSE, CHEERING] The visual quality
is even better. Its understanding of
physics is stronger, but here’s the leap forward. Veo 3 comes with Native
Audio generation. That means– [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
a nervous young badger in the forest. Take a listen. [VIDEO PLAYBACK] [MUSIC PLAYING] – They left behind a ball today. It bounced higher
than I can jump. – Oh, what manner
of magic is that? [END PLAYBACK] JOSH WOODWARD:
Pretty cool, right? Veo added not just the
sounds of the forest but also the dialogue. We’re entering a
new era of creation, with combined audio
and video generation that’s incredibly realistic. The quality is so good. It feels like you’re there
on the boat with this guy. [VIDEO PLAYBACK] – This ocean, it’s a force,
a wild, untamed might. And she commands your oar
with every breaking light. [END PLAYBACK] [APPLAUSE] JOSH WOODWARD: The
photorealistic generation, the emotion, the
movement of his mouth, and the ocean in the
background– it’s incredible how fast Veo continues to evolve
as a powerful, creative tool. And we’ve been working
closely with the film industry to imagine what’s possible
with Veo and to get this right. And you’ll hear more about
that in a few minutes. 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 these generative models are
unlocking creative expression, here’s Jason. [MUSIC PLAYING, APPLAUSE] JASON BALDRIDGE: Thanks, Josh. Whether you’re a creator,
a musician, or a 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, Shanka Mahadevan, putting Music AI Sandbox
and Lyria to use. [VIDEO PLAYBACK] – I’m Shanka Mahadevan, and
I’m a music composer, singer, producer, and a happy man. [LAUGHS] Working with Sandbox is great. We inputted our requirement,
and it gave us a bed. We used that bed and we
came up with this song. [VOCALIZING] For a musician, but 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. [NON-ENGLISH SINGING] [END PLAYBACK] [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. [VIDEO PLAYBACK] [MUSIC PLAYING] [END PLAYBACK] [APPLAUSE] JASON BALDRIDGE: 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’re 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. [VIDEO PLAYBACK] – 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. – 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. – Just the bliss
of the two of them. – Yeah. Veo is a generative video
model, but to me, it’s another lens through
which I get to imagine the universe around me. – 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. – 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 OK? – For every creature
that came before you, from every star that died
so that you could begin. [END PLAYBACK] [APPLAUSE, CHEERING] JASON BALDRIDGE:
Incredible work. [APPLAUSE, CHEERING] Eliza combined live action
performance with Veo viewer generated video, like
the microscopic worlds, the 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 built new capabilities
for filmmakers. 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. [MUSIC PLAYING, APPLAUSE] JOSH WOODWARD: Thanks, Jason. Based on our collaboration
with the creative community, we’ve been building a
new AI filmmaking tool for creatives, one 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 get 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 works. [APPLAUSE, CHEERING] 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 a custom gold gear
shift just by describing it. There it is. Pretty cool. Next, you 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. Now, here’s where it
gets really exciting. If I want to capture the
next shot of the scene, I can just hit the plus icon
to create the next shot. I can describe what I
want to happen next, like adding a 10-foot tall
chicken in the back seat, and Flow will do the rest. The character consistency,
the scene consistency, it just works. And if something isn’t, oh,
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 you extend a clip too. So I can get the perfect ending
that I’ve been working towards. Once I’ve got all the clips I
need, I can download the files. I can bring them into my
favorite editing software, add some music from Lyria,
and now the old man finally has his flying car. [VIDEO PLAYBACK] [MUSIC PLAYING] [END PLAYBACK] [APPLAUSE] JOSH WOODWARD: Pretty awesome. Pretty awesome. I want you to hear just a few
words from a few of our AI filmmakers who we’ve been
working with to shape Flow, how they describe
how it feels using it and how they’re
making it even better. Let’s take a watch. [VIDEO PLAYBACK] – I don’t know if I’m
on the right path, but I’m trying to find it. I’m questioning, searching,
and then something shifts. And I’m not trying anymore. I’m just doing. And all of the pieces
start falling into place. – It all feels pretty
clear in my head. I see these 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 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 I know
I’m in the right place. [MUSIC PLAYING] [END PLAYBACK] [APPLAUSE, CHEERING] JOSH WOODWARD: So amazing to
hear those filmmakers talk about bringing their incredible
visions to life and that feeling of building, of creating,
that’s exactly what we want to put in
your hands today. So I’m excited to share
that we’re upgrading. And two AI subscription
plans today. We will have Google AI Pro
and all new 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 formerly 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. The 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 get access to Flow
with Veo 3 available today. And 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 PLAYING, 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’re
building Android XR. [APPLAUSE, CHEERING] 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’re
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 all your
favorite Google apps for XR. And its 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, CHEERING] 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 building
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’re 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. OK. Who’s up for seeing an early
demo of Android XR glasses? [APPLAUSE, CHEERING] Let’s see how they work in
the most hectic environment possible right now. Backstage at I/O, our very
own superwoman, Nishida, is back there to show us how
these glasses work for real. Let me send her a text
now, and let’s get started. [VIDEO PLAYBACK] – Hey, everyone. Right now, you should be
seeing exactly what I’m seeing through the lens
of my Android XR glasses, like my delicious
coffee over here 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. – OK, I’ve sent
that message to him and muted all your
notifications. – Perfect. – Oh. Hey, Nishtha! – Hey, Dieter. – I see the lights
on your glasses. So I think it’s safe to say
that we’re live right now? – Yes, we’re officially
on with the I/O crew. – Hey, everybody. It is pretty great to
see I/O from this angle. Nishtha, you promised
me I could get my own pair of
Android XR glasses if I helped out back here. So what do you say? – Of course. Let’s get coffee after this, and
I’ll bring you those glasses. – Awesome.
We’ll see you then. Good luck. – Thank you. As you all can see, there’s
a ton going on backstage. And is that pro basketball
player, Giannis, wearing our glasses? – I love it. It frees up both of my
hands for double high fives. – Nice. Let me keep showing you guys
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? [AUDIO SKIPPING] – –Shoreline Amphitheatre,
which are often seen as homecoming
shows for the band. – No way. Can you show me a photo of one
of their performances here? – Sure, here’s one. Want me to play
one of their songs? – I’d love that. I can listen while I
make my way to the stage. – Right. Here’s “Under the Aurora”
by Counting Crows. [END PLAYBACK] SHAHRAM IZADI: OK. Who’s ready to
see these glasses? Here comes Nishtha. Welcome, Nishtha. NISHTHA BHATIA: Hey, everyone. [APPLAUSE] SHAHRAM IZADI:
Thanks for that star studded behind the scenes look. By the way, do you want to book
that coffee with Dieter now? NISHTHA BHATIA: Yes. The crew actually gave me some
awesome coffee backstage, so let me try something fun. Gemini, what was the
name of the coffee shop on the cup I had earlier? GEMINI: Mhm, 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 the
photos of that cafe? I want to check out the vibes. GEMINI: Definitely. Do these photos from Maps help? DIETER BOHN: Oh,
I know that spot. It’s a flower shop as well as a
coffee shop, but it is downtown. NISHTHA BHATIA: OK. Gemini, Show me what it
would take to walk here. GEMINI: Getting
those directions now. It’ll take you about an hour. NISHTHA BHATIA: OK. I can get some steps in. And these heads-up directions
and a full 3D map should make it super easy. [APPLAUSE, CHEERING] Go ahead and send Dieter an
invite for that cafe and to get coffee at 3:00 PM 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’re my personal
teleprompter, and I have prescription lenses. So I can see you all. OK, Nishtha, 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. SHAHRAM IZADI:
Here comes Dieter. [APPLAUSE, CHEERING] NISHTHA BHATIA: All right. Gemini– SHARHAM IZADI: Dieter, join us. NISHTHA BHATIA:
–take a photo for me. [APPLAUSE, CHEERING] All right, Gemini,
take a photo for me and add it to my favorites. SHAHRAM IZADI:
That looks amazing. [APPLAUSE, CHEERING] I’m completely starstruck. OK, one last thing. Sundar showed what’s possible
with live chat 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. I’m going to speak
Farsi, very poorly. And you’ll see the feed from
both of our glasses back here. And so you can all follow along. We’ll show an English
translation in real time. OK? Let’s give it a shot. Fingers crossed. [NON-ENGLISH SPEECH] – [NON-ENGLISH SPEECH] – [NON-ENGLISH SPEECH] See, we said it’s a risky demo. [APPLAUSE, CHEERING] Thank you. NISHTHA BHATIA: Thank you. SHAHRAM IZADI:
Thank you so much. [APPLAUSE, CHEERING] 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 that 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, CHEERING] We want you to be
able to wear glasses that match your personal taste. This is just a 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! [MUSIC PLAYING, APPLAUSE] SUNDAR PICHAI: Those XR
glasses are amazing– research to reality literally
right in front of our eyes. 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’ve all been waiting for, our AI counter. So let’s take a look at
one last leaderboard. Looks like, I guess,
we have a new entrant. Gemini takes the
lead, coming in at 95. Very exhilarating. [APPLAUSE, CHEERING] On a more serious
note, here’s everything we’ve announced today, from new
launches and product expansions 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 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 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. It’s a constellation
of satellites that use multispectral
satellite imagery and AI, aiming to provide near
real-time insights. Just look at the resolution. It can detect fires as
small as 270 square feet, about the 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, CHEERING] 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 real-time needs. We can imagine how this
could 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. It’s 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 deadliest diseases, advancing error-corrected
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. And the recent experience
brought that home for me. I was in San Francisco
with my parents. The first thing they wanted
to do was to ride in a Waymo, like a lot of other tourists. I had taken Waymos before. But watching my father,
who was in his 80s, in the front seat
be totally amazed, I saw the progress
in a whole new light. It was a reminder of
how incredible the power of technology is to inspire
to all and to move us forward. And I can’t wait to see
what amazing things will build together next. Thank you. [APPLAUSE, CHEERING] [VIDEO PLAYBACK] [MUSIC PLAYING] – 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 going to
change how we use our browsers. – It’s an AI agent that
gets things done for you. – NotebookLM Mindmaps
completely transforms learning. – Why is this person
following me wherever I walk? – That’s just your shadow. – Wait, you’re
going to turn right. – AI’s 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,
mind blowing to me. – The potential is
almost limitless. [END PLAYBACK] [MUSIC PLAYING]

It’s time to I/O! Tune in to learn the latest news, announcements, and AI updates from Google.

00:00:00 Opening
00:02:17 Introduction
00:19:29 Google DeepMind + Gemini for Developers
00:46:04 Search
01:11:06 Gemini
01:24:02 Generative Media
01:37:37 Android XR
01:51:09 Closing

To watch this keynote interpreted in American Sign Language (ASL), please click here:

For all things I/O, visit https://goo.gle/4jlp80v

#GoogleIO

Subscribe to our Channel: https://www.youtube.com/google
Find us on X: https://twitter.com/google
Watch us on TikTok: https://tiktok.com/@google
Follow us on Instagram: https://www.instagram.com/google
Join us on Facebook: https://www.facebook.com/Google