Google AI(@GoogleAI)

Hear the architects of Gemini reflect on their journey to continue pushing the frontier of AI, on th...

Google AI (@GoogleAI) — Fri, 29 May 2026 16:05:53 GMT

Hear the architects of Gemini reflect on their journey to continue pushing the frontier of AI, on this episode of Release Notes.

@JeffDean, @koraykv, @OriolVinyalsML, and @NoamShazeer sit down on camera together to share a behind-the-scenes look at the people behind the model, and how they saw the vision come together.

Your browser does not support the video tag.

🔗 View on Twitter

💬29🔄35❤️300👀45075📊64

⚡ Powered by xgo.ing

Tune in for the full story ↓ https://t.co/EGq2OA3A1n

Google AI (@GoogleAI) — Fri, 29 May 2026 16:05:53 GMT

Tune in for the full story ↓ youtube.com/watch?v=8hfpLa…

💬4🔄1❤️34👀27130📊9

⚡ Powered by xgo.ing

Draw a path that a drone can follow https://t.co/dpOgAcl7yt

Google AI (@GoogleAI) — Fri, 29 May 2026 00:30:29 GMT

Draw a path that a drone can follow
x.com/bilawalsidhu/s…

Bilawal Sidhu@bilawalsidhu

Gave google omni a sketched camera path and asked it to generate drone POV footage.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬2🔄7❤️65👀26946📊10

⚡ Powered by xgo.ing

Watch your avatar speak Spanish, English and Japanese https://t.co/8BRriqnfzO

Google AI (@GoogleAI) — Fri, 29 May 2026 00:30:28 GMT

Watch your avatar speak Spanish, English and Japanese
x.com/DotCSV/status/…

Carlos Santana@DotCSV

Sigo jugando con Omni! Efectivamente el modelo desbloquea un montón de casos de uso (e.g. traducción) que antes requerían de concatenar varios modelos diferentes:

Traducción → Voz cloning → Avatar lip-syncing...

Ahora todo se reduce a un prompt

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬8🔄27❤️365👀51305📊36

⚡ Powered by xgo.ing

Some fun Gemini Omni use cases from the community 🧵👇

Google AI (@GoogleAI) — Fri, 29 May 2026 00:30:26 GMT

Some fun Gemini Omni use cases from the community 🧵👇

💬32🔄58❤️675👀139667📊144

⚡ Powered by xgo.ing

We wanted to see if we could take simple, physical materials (like cardboard and markers) and use AI...

Google AI (@GoogleAI) — Thu, 28 May 2026 16:58:26 GMT

We wanted to see if we could take simple, physical materials (like cardboard and markers) and use AI to bring them to life. What was the result? A short film starring a bunch of TPUs getting ready for the big stage at Google I/O 2026!

Working with director Laurie Rowan and Nexus Studios, we kept human artistry at the center of the film by blending puppetry and 3D animation with our models to do the following ↓

Nano Banana: Generated beautifully stylized first frames from the raw puppet footage and basic 3D animations.

@GoogleAIStudio: Built a custom tool inside the platform to test these frames at scale, ensuring pixel-perfect consistency

Gemini Omni & experimental @GoogleDeepMind Models: Merged the base animation and stylized frames to elevate the final piece to a cinematic level.

Our AI pipelines were specifically designed to protect the crafty details that give these films their heart, like the tiny human imperfections of puppetry, or the nuance an animator can build into an expression.

Your browser does not support the video tag.

🔗 View on Twitter

💬83🔄95❤️406👀107375📊125

⚡ Powered by xgo.ing

Look back at last week’s I/O announcements with @NotebookLM. You can listen to an audio overview, w...

Google AI (@GoogleAI) — Wed, 27 May 2026 21:27:20 GMT

Look back at last week’s I/O announcements with @NotebookLM.

You can listen to an audio overview, watch the video recap, and even check out our detailed slide deck summarizing all of the biggest news and launches.

Check it out here: blog.google/innovation-and…

💬16🔄30❤️195👀29961📊40

⚡ Powered by xgo.ing

https://t.co/j6Qu6uAg1b

Google AI (@GoogleAI) — Tue, 26 May 2026 21:08:38 GMT

x.com/i/article/2059…

💬39🔄258❤️1712👀1450635📊559

⚡ Powered by xgo.ing

https://t.co/JMZXBOJtQQ

Google AI (@GoogleAI) — Fri, 22 May 2026 17:09:53 GMT

x.com/i/article/2057…

💬61🔄61❤️408👀120644📊101

⚡ Powered by xgo.ing

We are also launching Science Skills, a specialized bundle that integrates insights from 30+ major l...

Google AI (@GoogleAI) — Wed, 20 May 2026 18:07:32 GMT

We are also launching Science Skills, a specialized bundle that integrates insights from 30+ major life science models and databases with agentic platforms like @Antigravity to allow researchers to perform complex, manual workflows in minutes.

To learn more on how to use Science Skills visit: antigravity.google/use-cases/scie…

💬5🔄14❤️72👀21573📊15

⚡ Powered by xgo.ing

We're building Gemini for Science with and for the scientific community. In collaboration with 100+ ...

Google AI (@GoogleAI) — Wed, 20 May 2026 18:07:32 GMT

We're building Gemini for Science with and for the scientific community. In collaboration with 100+ institutions and a trusted tester community that ranges from PhD students to Nobel laureates, we want to make sure this tech is responsible and rigorous enough to tackle real-world problems.

Read the full update here: blog.google/innovation-and…

💬6🔄10❤️56👀14325📊13

⚡ Powered by xgo.ing

For centuries, the scientific method has been our best tool for progress. But today, there’s so much...

Google AI (@GoogleAI) — Wed, 20 May 2026 18:07:31 GMT

For centuries, the scientific method has been our best tool for progress. But today, there’s so much data out there that it’s impossible for any one researcher to connect all the dots. We want to fix that:

Introducing Gemini for Science, a collection of science tools and experiments designed to accelerate the speed and scale of scientific exploration.

Read on to learn more about each announcement in this inaugural set 🧵👇

Your browser does not support the video tag.

🔗 View on Twitter

💬35🔄107❤️568👀51494📊121

⚡ Powered by xgo.ing

We partnered with artists, designers, and builders to create new AI tools that solve real problems i...

Google AI (@GoogleAI) — Wed, 20 May 2026 15:56:20 GMT

We partnered with artists, designers, and builders to create new AI tools that solve real problems in their creative workflows.

Here’s what’s new:
— Introducing Google Pics in @GoogleWorkspace: A brand-new image creation & editing tool. Move and resize objects, add text, and translate just by hovering and clicking

— Big updates to @GoogleFlow: 1) You can now create with Gemini Omni Flash in Google Flow 2) Google Flow Agent is a multi-step creative partner that reasons and plans complex tasks with you. 3) Google Flow tools are custom tools you can “vibe code” for animations, video effects, text layering & more

— Design live with @StitchbyGoogle: Now, you can use text or voice prompts to edit layouts in real time then export those designs straight to code

— More creative control in @GoogleFlowMusic: Edit songs section by section, remix the style of full songs, and create music videos with our new Gemini Omni Flash model

Your browser does not support the video tag.

🔗 View on Twitter

💬126🔄87❤️1045👀13944249📊241

⚡ Powered by xgo.ing

New upgrades to the @GeminiApp are you helping you get more done: ✨Gemini Spark is your 24/7 person...

Google AI (@GoogleAI) — Tue, 19 May 2026 22:08:03 GMT

New upgrades to the @GeminiApp are you helping you get more done:

✨Gemini Spark is your 24/7 personal AI agent that can take action on your behalf, under your direction. It  seamlessly integrates with @Gmail, @GoogleDocs, and Slides to automate your workflows and, best of all, it can keep working even when your laptop is closed.

☀ ️Daily Brief is our newest out-of-the-box agent that gives you a personalized digest based on your goals, and suggests next steps.

Daily Brief is rolling out starting today to all Google AI subscribers (18+) in the Gemini app, starting in the US. Gemini Spark is starting to roll out next week.

Your browser does not support the video tag.

🔗 View on Twitter

💬27🔄45❤️407👀37655📊71

⚡ Powered by xgo.ing

https://t.co/XDYi2WR3mg

Google AI (@GoogleAI) — Tue, 19 May 2026 21:24:11 GMT

x.com/ThisIsNickyS/s…

Nicky Saunders 🏁🦁🏁@ThisIsNickyS

My first attempt using Google’s new AI video model: Omni
😳

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄4❤️64👀28132📊7

⚡ Powered by xgo.ing

https://t.co/xFh7r8Sb8h

Google AI (@GoogleAI) — Tue, 19 May 2026 21:22:10 GMT

x.com/bearlyai/statu…

Bearly AI@bearlyai

The physics engineer for Gemini Omni are very impressive. Water has always been difficult for AI to generate well.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄1❤️11👀8743📊2

⚡ Powered by xgo.ing

https://t.co/8YnysXRT7P

Google AI (@GoogleAI) — Tue, 19 May 2026 21:19:33 GMT

x.com/LexnLin/status…

Leon Lin@LexnLin

cutting frames and perspectives using Gemini Omni

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄1❤️57👀19870📊7

⚡ Powered by xgo.ing

Today, we launched a brand-new intelligent Search box. Here's what that means: An upgrade to the ...

Google AI (@GoogleAI) — Tue, 19 May 2026 21:12:37 GMT

Today, we launched  a brand-new intelligent Search box.

Here's what that means:

An upgrade to the Search experience with our most advanced Gemini 3.5 models, bringing with them our latest agentic capabilities

You can ask across modalities (text, images, files, and videos) and Search can reason across them all

We're combining AI Overviews and AI Mode into one, seamless AI Search experience. So you can ask follow-up questions, build context, and received even more tailored and personalized responses

This new AI Search experience is live today across desktop and mobile, worldwide.

Your browser does not support the video tag.

🔗 View on Twitter

💬29🔄55❤️520👀42804📊83

⚡ Powered by xgo.ing

A few weeks ago, we asked our community to use @GoogleAIStudio or Canvas in @GeminiApp to help us cr...

Google AI (@GoogleAI) — Tue, 19 May 2026 20:48:28 GMT

A few weeks ago, we asked our community to use @GoogleAIStudio or Canvas in @GeminiApp to help us create the Google I/O countdown.

Thanks SO much to everyone who submitted, and special shoutout to the creators whose submissions helped us set the right ~vibes~ on the stage today:

@thgie_8_eight@r_mevo@EdinsonNM@gunny_5@xabila@GuyMosheTamam@mikkelhundborg@rajatxr
Shahab Uddin
Charles Zuo

Your browser does not support the video tag.

🔗 View on Twitter

💬13🔄11❤️114👀17596📊21

⚡ Powered by xgo.ing

https://t.co/vyXXPrGXOs

Google AI (@GoogleAI) — Tue, 19 May 2026 20:08:58 GMT

x.com/IamEmily2050/s…

Emily@IamEmily2050

Gemini Flash Omni is the first step toward the true Omni model, and a Pro version will be available soon.

Your browser does not support the video tag.

🔗 View on Twitter

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄2❤️44👀22696📊4

⚡ Powered by xgo.ing

https://t.co/7Erpr2MAMU

Google AI (@GoogleAI) — Tue, 19 May 2026 20:08:57 GMT

x.com/raza8542121/st…

Raza@raza8542121

First attempt with Gemini Omni Flash🚨

Prompt: 
A cinematic macro shot of a sleek, glass sculpture of a lion standing on a wooden table. The glass gradually melts into a flowing, golden liquid, which then reorganizes itself into a complex, intricate mechanical clockwork lion, all in one continuous, fluid 10-second motion.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬4🔄12❤️98👀41257📊13

⚡ Powered by xgo.ing

https://t.co/HAOjjJGrCy

Google AI (@GoogleAI) — Tue, 19 May 2026 20:08:57 GMT

x.com/mrfanduuuuu/st…

Fandu@mrfanduuuuu

Gemini Omni made me this video to explain photosynthesis👀

Google is wining hard 🔥

lingemini.google.com/share/cdba7ac4…kG

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄6❤️85👀32484📊10

⚡ Powered by xgo.ing

https://t.co/k27T8IeUy8

Google AI (@GoogleAI) — Tue, 19 May 2026 20:08:57 GMT

x.com/venturetwins/s…

Justine Moore@venturetwins

@GoogleDeepMind 3) Video editing

You can upload real videos to Omni and ask for edits - changing the action, style, or subject. Or you can annotate on top of a video.

In this video, I asked to "change my hat every time I clap."

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬2🔄4❤️73👀40885📊8

⚡ Powered by xgo.ing

Some fun Gemini Omni use cases from the community👇🧵 (We’ll keep updating this thread throughout t...

Google AI (@GoogleAI) — Tue, 19 May 2026 20:08:56 GMT

Some fun Gemini Omni use cases from the community👇🧵

(We’ll keep updating this thread throughout the day)

💬33🔄67❤️1036👀176258📊222

⚡ Powered by xgo.ing

https://t.co/dhAaJ7mu5W

Google AI (@GoogleAI) — Tue, 19 May 2026 20:08:56 GMT

x.com/chrisfirst/sta…

CHRIS FIRST@chrisfirst

Google Omni Flash is able to edit videos accurately without distorting your video.

> Make everyone in this shot flamingos. Wearing the same outfit.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬4🔄9❤️166👀42139📊17

⚡ Powered by xgo.ing

We were able to sit down with the @GoogleDeepmind team behind the new Gemini Omni Flash model to hea...

Google AI (@GoogleAI) — Tue, 19 May 2026 19:48:09 GMT

We were able to sit down with the @GoogleDeepmind team behind the new Gemini Omni Flash model to hear all of their behind-the-scenes stories, memorable moments, and many, many (occasionally embarrassing) video generations.

Watch the full Release Notes episode here: goo.gle/49adTFp

Your browser does not support the video tag.

🔗 View on Twitter

💬46🔄71❤️813👀5172168📊130

⚡ Powered by xgo.ing

Conversational editing: Gemini Omni allows you to edit your videos using natural language (like Nano...

Google AI (@GoogleAI) — Tue, 19 May 2026 19:17:59 GMT

Conversational editing: Gemini Omni allows you to edit your videos using natural language (like Nano Banana, but for video). So you can easily change your characters, settings, and styles by just describing what you want.

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄11❤️140👀22185📊16

⚡ Powered by xgo.ing

Google AI Plus, Pro, and Ultra subscribers can Gemini Omni Flash today on the @geminiapp, @GoogleFlo...

Google AI (@GoogleAI) — Tue, 19 May 2026 19:17:59 GMT

Google AI Plus, Pro, and Ultra subscribers can Gemini Omni Flash today on the @geminiapp, @GoogleFlow, @GoogleFlowMusic, and for no cost on @Youtube Shorts and the YouTube Create app.

Your browser does not support the video tag.

🔗 View on Twitter

💬10🔄11❤️194👀22757📊33

⚡ Powered by xgo.ing

Reference anything: Gemini Omni extends Gemini's native multimodality, allowing you to blend combina...

Google AI (@GoogleAI) — Tue, 19 May 2026 19:17:59 GMT

Reference anything: Gemini Omni extends Gemini's native multimodality, allowing you to blend combinations of text, audio, image, and video inputs into a high-quality, consistent video.

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄9❤️156👀20695📊17

⚡ Powered by xgo.ing

By now, you've probably heard about Gemini Omni, our new model designed to create anything from any ...

Google AI (@GoogleAI) — Tue, 19 May 2026 19:17:58 GMT

By now, you've probably heard about Gemini Omni, our new model designed to create anything from any input, starting with video.

But... what's the big deal?

Let’s break it down 🧵👇

Your browser does not support the video tag.

🔗 View on Twitter

💬81🔄265❤️2508👀222255📊470

⚡ Powered by xgo.ing

It’s time for #GoogleIO! Join us virtually. 10:00AM - Consumer Keynote 1:30PM - Developer Keynote ...

Google AI (@GoogleAI) — Tue, 19 May 2026 16:02:57 GMT

It’s time for #GoogleIO! Join us virtually.

10:00AM - Consumer Keynote
1:30PM -  Developer Keynote

(Times in PT)

x.com/i/events/20532…

💬23🔄33❤️181👀22143📊41

⚡ Powered by xgo.ing

Happy Friday! 🎉We’re officially 11 days away from I/O (but the launches keep rolling in). Here’s wh...

Google AI (@GoogleAI) — Fri, 08 May 2026 16:34:31 GMT

Happy Friday! 🎉We’re officially 11 days away from I/O (but the launches keep rolling in). Here’s what happened this week:

— The @googlehealth app, featuring a personalized health coach built with Gemini that uses your wearables, favorite health & fitness apps, and medical records to deliver proactive wellness guidance that fits your life

— Multi-Token Prediction (MTP) drafters in @googlegemma 4, which can speed up your workflows by up to 3X

— Automatic source organization and customizable Mind Maps in @NotebookLM

— Gemini API File Search tool updates with multimodal support, custom metadata, and page citations

— Webhooks (now available in the Gemini API) replace continuous polling with push-based notifications

— Some of our most popular AI features, like Nano Banana, Veo, and @googlephotos Remix are now available on Google TVs

💬54🔄52❤️689👀56189📊108

⚡ Powered by xgo.ing

@GoogleAIStudio @GeminiApp We can’t wait to see where your creativity takes you. Vibe code your cou...

Google AI (@GoogleAI) — Fri, 01 May 2026 16:10:11 GMT

@GoogleAIStudio@GeminiApp We can’t wait to see where your creativity takes you.

Vibe code your countdown idea in @GoogleAIStudio or Canvas in @GeminiApp, then submit it here:
goo.gle/codethecountdo…

💬7🔄8❤️47👀14929📊11

⚡ Powered by xgo.ing

@GoogleAIStudio And this sample project was created on Canvas in @GeminiApp. It’s a high-speed rhyth...

Google AI (@GoogleAI) — Fri, 01 May 2026 16:09:24 GMT

@GoogleAIStudio And this sample project was created on Canvas in @GeminiApp. It’s a high-speed rhythm game where you tap to the beat and collect power-ups to remix the track. Watch as the numbers appear as melody plays!

You can actually play the game here:  gemini.google.com/share/b16dad5e…

💬7🔄13❤️86👀23855📊16

⚡ Powered by xgo.ing

I/O is less than 3 weeks away 🤯 We want YOU to help us create the countdown that will play before t...

Google AI (@GoogleAI) — Fri, 01 May 2026 16:04:25 GMT

I/O is less than 3 weeks away 🤯 We want YOU to help us create the countdown that will play before the keynote begins.

Using @GoogleAIStudio or Canvas in @GeminiApp vibe code your most creative countdown concept and send it to us by May 6th.

The only rule is that your build has to feature a large number between 1 and 10. Check the replies in this thread for sample projects to draw inspiration from or remix.

You can find more info and directions on how to submit your builds here:goo.gle/codethecountdo…3

💬70🔄81❤️671👀131048📊137

⚡ Powered by xgo.ing

Last week, we made Gemini Embedding 2, our first natively multimodal embedding model, available to t...

Google AI (@GoogleAI) — Thu, 30 Apr 2026 17:28:19 GMT

Last week, we made Gemini Embedding 2, our first natively multimodal embedding model, available to the general public. Since then, developers have used it to build video analysis tools, visual shopping assistants, and more.

But you might be wondering... what is an embedding model? 🤔 Let’s break it down! 

1. What is it?
Think of an embedding model as a "universal translator." It takes text, images, video, and audio data and turns them into a long string of numbers, like a unique digital fingerprint.

2. How does it work?
Historically, search has been text only. Now, instead of just matching data by keyword, Gemini Embedding 2 maps multiple modalities in the same space based on meaning. It "feels" the connection between a video of a soccer goal and the words "game-winning shot" without needing tags.

For example, "ocean" and "waves" are placed close together, but "ocean" and "toaster" are miles apart.

3. How can you use it?
Developers have been using it to incorporate smarter search functionality into their builds. This means creating tools where you can snap a photo of a product and type "find this in yellow," or search through thousands of hours of video by describing what happens in a scene.

4. Ready to try it out for yourself?
You can start using it today via the Gemini API or the Gemini Enterprise Agent Platform.

Your browser does not support the video tag.

🔗 View on Twitter

💬139🔄380❤️2603👀211782📊585

⚡ Powered by xgo.ing

https://t.co/z6Kfkn9xu6

Google AI (@GoogleAI) — Wed, 29 Apr 2026 17:50:30 GMT

x.com/i/article/2049…

💬37🔄140❤️909👀109510📊177

⚡ Powered by xgo.ing

Our teams have been busyyy! Here are some key updates from the past week: — @GoogleCloud unveiled ...

Google AI (@GoogleAI) — Fri, 24 Apr 2026 22:20:42 GMT

Our teams have been busyyy! Here are some key updates from the past week: 

— @GoogleCloud unveiled a suite of AI innovations at our Cloud Next event, including our eighth generation TPUs (TPUt for inference + TPUi for reasoning), Gemini Enterprise Agent Platform, Agentic Data cloud, Workspace Intelligence, and beyond

— Gemini Embedding 2, our natively multimodal embedding model, became generally available via the Gemini API and in Gemini Enterprise Agent Platform (the evolution of Vertex AI)

— @StitchbyGoogle open-sourced the draft specification for DESIGN.md, so it can be used across any single tool or platform

— New autonomous search agents, Deep Research and Deep Research Max, launched to bring MCP support, native visualizations, and unprecedented analytical quality to research workflows across the web or custom sources

— Google AI Pro and Ultra subscribers now get increased usage limits and access to Nano Banana Pro and Gemini Pro models in @GoogleAIStudio

— @GoogleDeepMind introduced Decoupled DiLoCo, our new resilient and flexible way to train advanced AI models across multiple data centers

💬39🔄48❤️432👀54018📊82

⚡ Powered by xgo.ing

Last week, we launched Gemini 3.1 TTS, our latest and best text-to-speech model. This new model intr...

Google AI (@GoogleAI) — Thu, 23 Apr 2026 18:08:15 GMT

Last week, we launched Gemini 3.1 TTS, our latest and best text-to-speech model. This new model introduces [awe] audio tags, an intuitive way to guide vocal style, pace, and delivery.

Here are some tips on the best ways to use audio tags in your prompts:

1. All inline tags must be enclosed in square brackets, such as [screams] or [whispers]

2. Insert these tags exactly where you want the transition to occur and make sure to avoid placing tags directly next to each other

3. Use tags like [slow] or [fast] to control the pace of the delivery, or even [short pause] or [long pause] to ramp up the anticipation in dramatic moments

4. The model also offers granular control over vocalizations, allowing you to direct the delivery with cues like [cackles] or [whispers]

5. An ideal audio tag formula could look something like: [encouraging] Let’s try that last sentence again to make sure that you nailed it. [slow] "L'oiseau s'est envolé." [short pause] Perfect! [laughs] You're a natural.

No matter what you’re developing — from [scholarly] a language learning tool, to [mysterious] an interactive podcast app, to [friendly] more adaptive customer service offerings, and beyond —  these prompting tips will equip you to start building with Gemini 3.1 TTS.

Your browser does not support the video tag.

🔗 View on Twitter

💬37🔄87❤️657👀57434📊133

⚡ Powered by xgo.ing

Calling all builders 🛠️📣 Google AI Pro and Ultra subscribers will now get increased usage limits a...

Google AI (@GoogleAI) — Mon, 20 Apr 2026 21:21:50 GMT

Calling all builders 🛠️📣 Google AI Pro and Ultra subscribers will now get increased usage limits and access to Nano Banana Pro and Gemini Pro models in @GoogleAIStudio — no API key required. 

Sign in with your subscriber account today to take your ideas from prototype to production.

💬72🔄143❤️1481👀94298📊236

⚡ Powered by xgo.ing

@GoogleAIStudio Check out our blog post to learn more: https://t.co/9FskTNe8vO

Google AI (@GoogleAI) — Mon, 20 Apr 2026 21:21:50 GMT

@GoogleAIStudio Check out our blog post to learn more: blog.google/innovation-and…

💬3🔄8❤️80👀26613📊12

⚡ Powered by xgo.ing

Beyond generating high-fidelity visuals, we wanted to test the limits of what Nano Banana Pro can do...

Google AI (@GoogleAI) — Mon, 20 Apr 2026 17:28:39 GMT

Beyond generating high-fidelity visuals, we wanted to test the limits of what Nano Banana Pro can do. We worked with design partners Porto Rocha to build out a hypothetical brand called YOYOYO to see how the model would handle the task. Here’s what we found:

🎨Brand consistency: Across logos, colors, and typography, the model maintained a strict, cohesive brand identity (even for wildly diverse concepts)

🛍️Environmental realism: We asked to see the products in storefront and studio mockups. It nailed accurate lighting, shadows, and physical proportions - even when upscaled for massive retail displays

🪀Spatial accuracy: We tested spatial volumes for physical packaging. The generated proportions were so precise that we were able to 3D-print the functional yo-yo

How have you been pushing the limits of Nano Banana Pro? Let us know in the replies below!

Your browser does not support the video tag.

🔗 View on Twitter

💬57🔄114❤️1341👀120783📊292

⚡ Powered by xgo.ing

What a week! Here’s everything we shipped: — Gemini 3.1 Flash TTS, our latest text-to-speech model,...

Google AI (@GoogleAI) — Fri, 17 Apr 2026 16:58:13 GMT

What a week! Here’s everything we shipped:

— Gemini 3.1 Flash TTS, our latest text-to-speech model, featuring native multi-speaker dialogue and improved controllability and audio tags for more natural, expressive voices in 70+ languages

— Gemini Robotics-ER 1.6 by @GoogleDeepMind, an upgrade designed to help robots reason about the physical world

— The @GeminiApp for Mac desktop (tip: Use Option + Space to access the app via shortcut)

—  Personal Intelligence in @GeminiApp has new integrations with @GooglePhotos and Nano Banana 2, making it easier to create relevant, personalized images. Available for AI Pro, Plus, and Ultra subscribers in the US

— A couple fun additions in @GoogleAIStudio to make building easier, including Design previews and tab tab tab functionality

— Skills in @GoogleChrome, which let you save and reuse your most helpful Gemini prompts and run them in your browser with a single click

💬82🔄79❤️873👀100884📊163

⚡ Powered by xgo.ing

Gemini 3.1 Flash TTS is rolling out in Google Vids and is available today in preview via the Gemini ...

Google AI (@GoogleAI) — Wed, 15 Apr 2026 16:07:55 GMT

Gemini 3.1 Flash TTS is rolling out in Google Vids and is available today in preview via the Gemini API and in @GoogleAIStudio. 

Whether you’re creating a pitch deck or recording a passion project, transform your scripts into studio-quality narration: blog.google/innovation-and…

💬8🔄13❤️106👀24536📊22

⚡ Powered by xgo.ing

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model ye...

Google AI (@GoogleAI) — Wed, 15 Apr 2026 16:07:37 GMT

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet.

This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded directly in your text. Want a different tempo or tone? [amazement] Just tag the audio to steer the AI-speech output!

The model supports 70+ languages (24 of which are high-quality evaluated languages, including: Japanese, Hindi, and Arabic). Watch the audio tags in action in the demo below ↓

Your browser does not support the video tag.

🔗 View on Twitter

💬117🔄308❤️2304👀200515📊452

⚡ Powered by xgo.ing

Prefer watching on @YouTube while scrolling through the comment section? We get it: https://t.co/Vfc...

Google AI (@GoogleAI) — Mon, 13 Apr 2026 18:58:46 GMT

Prefer watching on @YouTube while scrolling through the comment section? We get it: youtu.be/b1Pvt072wKQ?si…

💬1🔄7❤️31👀36113📊7

⚡ Powered by xgo.ing

Got a doodle for your next project laying around? Turn it into working software using @GoogleAIStudi...

Google AI (@GoogleAI) — Mon, 13 Apr 2026 18:58:45 GMT

Got a doodle for your next project laying around? Turn it into working software using @GoogleAIStudio and Nano Banana.

Watch us vibe code a weather-responsive outfit selector app from a single, hand-drawn sketch:

Your browser does not support the video tag.

🔗 View on Twitter

💬25🔄34❤️225👀46786📊58

⚡ Powered by xgo.ing

TGIF! Here are some of our favorite updates from the past week: — Notebooks in @GeminiApp, an integ...

Google AI (@GoogleAI) — Fri, 10 Apr 2026 18:28:12 GMT

TGIF! Here are some of our favorite updates from the past week:

— Notebooks in @GeminiApp, an integration with @NotebookLM that enables you to retrieve context from your private notebooks or convert your active chats into grounded sources for new research

— The @GeminiApp on web now generates customizable interactive visualizations, including 2D and 3D models, directly in your chat to help you deconstruct complex concepts

— The new AI-powered @GoogleFinance tool is shipping to 100+ countries, delivering market research, advanced charting, expanded real-time data, and more

💬32🔄46❤️276👀51523📊62

⚡ Powered by xgo.ing

A playable, digital piano built with Gemma 4 E2B (2B). https://t.co/aUZlhF3ER2

Google AI (@GoogleAI) — Fri, 10 Apr 2026 15:33:55 GMT

A playable, digital piano built with Gemma 4 E2B (2B).

x.com/0xCVYH/status/…

CV.YH@0xCVYH

Google lancou "Agent Skills" junto com o Gemma 4

Um app Android onde voce importa skills e o Gemma 4 E2B (2B) roda localmente no celular, raciocinando e usando as skills

962 likes em poucas horas. Isso e IA agentica rodando no bolso, sem cloud, sem API, sem custo

O modelo de 2B parametros e suficiente pra tarefas praticas quando tem tools bem definidas

Ja ta na Play Store. O futuro dos agentes nao e so desktop — e mobile-first

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬5🔄6❤️54👀31648📊9

Google AI(@GoogleAI)

Read more about all the fun ways we used AI to bring I/O to life this year: https://t.co/jE7rLCVnfs

Hear the architects of Gemini reflect on their journey to continue pushing the frontier of AI, on th...

Tune in for the full story ↓ https://t.co/EGq2OA3A1n

Draw a path that a drone can follow https://t.co/dpOgAcl7yt

Watch your avatar speak Spanish, English and Japanese https://t.co/8BRriqnfzO

Some fun Gemini Omni use cases from the community 🧵👇

We wanted to see if we could take simple, physical materials (like cardboard and markers) and use AI...

Look back at last week’s I/O announcements with @NotebookLM. You can listen to an audio overview, w...

https://t.co/j6Qu6uAg1b

https://t.co/JMZXBOJtQQ

We are also launching Science Skills, a specialized bundle that integrates insights from 30+ major l...

We're building Gemini for Science with and for the scientific community. In collaboration with 100+ ...

For centuries, the scientific method has been our best tool for progress. But today, there’s so much...

We partnered with artists, designers, and builders to create new AI tools that solve real problems i...

New upgrades to the @GeminiApp are you helping you get more done: ✨Gemini Spark is your 24/7 person...

https://t.co/XDYi2WR3mg

https://t.co/xFh7r8Sb8h

https://t.co/8YnysXRT7P

Today, we launched a brand-new intelligent Search box. Here's what that means: An upgrade to the ...

A few weeks ago, we asked our community to use @GoogleAIStudio or Canvas in @GeminiApp to help us cr...

https://t.co/vyXXPrGXOs

https://t.co/7Erpr2MAMU

https://t.co/HAOjjJGrCy

https://t.co/k27T8IeUy8

Some fun Gemini Omni use cases from the community👇🧵 (We’ll keep updating this thread throughout t...

https://t.co/dhAaJ7mu5W

We were able to sit down with the @GoogleDeepmind team behind the new Gemini Omni Flash model to hea...

Conversational editing: Gemini Omni allows you to edit your videos using natural language (like Nano...

Google AI Plus, Pro, and Ultra subscribers can Gemini Omni Flash today on the @geminiapp, @GoogleFlo...

Reference anything: Gemini Omni extends Gemini's native multimodality, allowing you to blend combina...

By now, you've probably heard about Gemini Omni, our new model designed to create anything from any ...

It’s time for #GoogleIO! Join us virtually. 10:00AM - Consumer Keynote 1:30PM - Developer Keynote ...

Happy Friday! 🎉We’re officially 11 days away from I/O (but the launches keep rolling in). Here’s wh...

@GoogleAIStudio @GeminiApp We can’t wait to see where your creativity takes you. Vibe code your cou...

@GoogleAIStudio And this sample project was created on Canvas in @GeminiApp. It’s a high-speed rhyth...

I/O is less than 3 weeks away 🤯 We want YOU to help us create the countdown that will play before t...

Last week, we made Gemini Embedding 2, our first natively multimodal embedding model, available to t...

https://t.co/z6Kfkn9xu6

Our teams have been busyyy! Here are some key updates from the past week: — @GoogleCloud unveiled ...

Last week, we launched Gemini 3.1 TTS, our latest and best text-to-speech model. This new model intr...

Calling all builders 🛠️📣 Google AI Pro and Ultra subscribers will now get increased usage limits a...

@GoogleAIStudio Check out our blog post to learn more: https://t.co/9FskTNe8vO

Beyond generating high-fidelity visuals, we wanted to test the limits of what Nano Banana Pro can do...

What a week! Here’s everything we shipped: — Gemini 3.1 Flash TTS, our latest text-to-speech model,...

Gemini 3.1 Flash TTS is rolling out in Google Vids and is available today in preview via the Gemini ...

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model ye...

Prefer watching on @YouTube while scrolling through the comment section? We get it: https://t.co/Vfc...

Got a doodle for your next project laying around? Turn it into working software using @GoogleAIStudi...

TGIF! Here are some of our favorite updates from the past week: — Notebooks in @GeminiApp, an integ...

A playable, digital piano built with Gemma 4 E2B (2B). https://t.co/aUZlhF3ER2