Google Labs
@GoogleLabs
Followers
63K
Following
726
Media
793
Statuses
2K
Google’s home for our latest AI tools and experiments.
Joined July 2010
Whisk Animate is now available globally to Google One AI premium subscribers!. With Veo 2, turn your Whisk-generated images into vivid eight-second animated clips - perfect for reimagining your images in different styles or bringing new ideas to life. 🎥
82
337
3K
Meet Whisk! 🎉 Our new experiment that lets you use images as prompts to visualize your ideas and tell your story. Try it now:
81
363
2K
Turn the static into the cinematic with Whisk Animate!. Check this thread to see some of our favorite examples of the magic in action 👀. From sprout to full bloom with just one prompt 🌱
41
188
2K
Today we announced Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips from text or image prompts. 🎥 . Sign up to try Veo 2 in VideoFX ↓
77
316
2K
Introducing Daily Listen: an experimental AI-powered audio show giving you short, timely updates about things YOU care about, right in your Google app. 🎧Try it & tell us what you think!👇
69
179
2K
Imagine listening to a lively discussion about your latest research project, summarized and analyzed by two AI hosts 🎧That's the power of #NotebookLM's Audio Overview. Upload PDFs, Google Docs, Slides, and try it for yourself. ✨Learn more at:
95
288
2K
Here’s a quick preview of Whisk Animate, which lets you turn images you create in Whisk into 8 second clips using our Veo 2 model. Stay tuned for updates on when this will be made more widely available.
81
167
1K
We know you’ve been waiting for this! Whisk is going global and is now available in over 100 countries 🌍! We can't wait to see where your imagination takes you. Get started today at
98
192
1K
Introducing the AI Futures Fund, a new program where startups can work with us to build the future of AI technology. From early access to @GoogleDeepMind models to Cloud credits, we’ll help get your startup to the next level. Learn more and apply ⬇️
75
191
1K
This is KITSUNE - a tale of love between two souls. 🦊 💫. Written, created and directed by @henrydaubrez. All shots generated with Veo 2 using VideoFX. Watch with sound on. 🔊
76
166
1K
Introducing Project Mariner: an agent that helps you accomplish complex tasks in your browser 💻✨It’s a research prototype built with Gemini 2.0. Learn more:
20
198
956
We are less than ONE WEEK out from this year's #GoogleIO. In last year's keynote, we unveiled @NotebookLM’s Audio Overviews. This year we have cooked up even more fun stuff in the Lab. 😉😉😉. Any guesses for what kinds of experiments we've been working on?.
71
60
921
NotebookLM, our AI-powered research and writing assistant, is now available in 200+ new countries and territories! Lots of new updates…. Now running Gemini 1.5 Pro. You can add Google Slides and web URLs as sources. Directly scroll to passages with new inline citations.
13
133
754
Our latest Google Labs Experiment is here! #GenChess turns your ideas into playable art pieces using Google’s Imagen 3 model. Create and play today →
82
171
745
Check out instructions @lucas0choa + @GautamBose18 shared for anyone to make their own hand wash timer using @arduino. Shared on @Hacksterio here →.
14
247
727
Unlock deeper insights with NotebookLM: Now analyze YouTube videos & audio files alongside your docs. Plus, easily share your Audio Overview with a new sharing option! . Learn more:
27
117
716
We're releasing a few more #NotebookLM features today – we've been so inspired by all the ways this community has been using the tool, and we're excited to see where you take it next ✨.
✨ New features coming to NotebookLM ✨.🗣️ Customize Audio Overviews and guide the conversation.🤝 Collaborate with teammates in the NotebookLM Business pilot program.🎧 Listen to Audio Overviews while continuing to work .See what else is new ↓
16
84
613
Sodar - use WebXR to help visualise social distancing guidelines in your environment. Using Sodar on supported mobile devices, create an augmented reality two meter radius ring around you. #hacktohelp
68
222
567
Little Language Lessons is a collection of bite-sized learning experiments built with the Gemini API - try it today →
14
112
583
We’re excited about this one! Jules uses Gemini 2.0 to offload tedious tasks like bug fixes so devs can focus on more critical issues. Bonus: it integrates directly with @GitHub 😎Join the waitlist:
Meet your new coding sidekick! 🤝. From the minds at @labsdotgoogle and @googledeepmind, Jules is an experimental AI-powered code agent integrated with GitHub. Available to trusted testers, it's designed to help devs fix bugs and other code issues. →
12
64
526
Be one of the first to try AI Mode – a new experiment bringing advanced capabilities from Gemini 2.0 to help with even more of your questions, right in Google Search. Rolling out first to Google One AI Premium subscribers in Labs. Sign up for early access
🔍 Power users have been asking for AI responses on more of their searches. So we're introducing AI Mode, a new experiment in Search. Ask whatever’s on your mind, get an AI response and keep exploring with follow-up questions and helpful links. Learn more ↓.
15
54
476
In our latest #LabSession, we collaborated with coding educator @shiffman to create #ShiffBot – an experimental #Gemini-powered chatbot that uses Dan's teaching style to help you learn to code in #p5js without just giving you the answers. 🚂 Learn more at
51
95
423
It’s here! Thrilled to collab with @jacobcollier on our latest #LabSession exploring the magical possibilities of generative music and #MusicFXDJ. Watch full video: Tune in 10/24 at 5 PM ET as Jacob livestreams a MusicFX DJ sesh on his YT channel.
27
85
359
Introducing #ImageFX ✨ a new image generation tool powered by Imagen 2, Google's most advanced text-to-image model. We’re excited to add this to our suite of generative AI tools at Labs, and to help bring your most creative ideas to life. Try it out:
35
122
358
What happens when the alphabet meets AI? #GenType is a type generator powered by Imagen 2 that allows you to craft, refine, and download one-of-a-kind AI generated alphabets. Try it out and share your results:
38
81
367
It’s here! Our redesigned site is now live, here for you to discover the most exciting AI experiments from Google. Be sure to check it out ⬇️
15
46
373
Thrilled to share our latest #LabSession with Grammy winner & Indian film composer Shankar Mahadevan! Shankar brought a wealth of knowledge to refine Music AI Sandbox, an experimental tool helping songwriters, musicians, and producers realize their vision. Watch full vid:
27
96
322
Happy International Dino Day! We’re celebrating by bringing back GenDino, the classic Chrome Dino Game remixed with Imagen 2 and…you!. Create and play your own version of this iconic game now!. This is a limited drop Labs experiment🔥 catch it while you can! 🎮 And don’t forget
27
70
323
Happening today at 2 PM PST / 5 PM EST, @jacobcollier is going live on his YT channel to make music with our latest AI-music tool, #MusicFXDJ
69
68
246
Before refine: Baby Bear grew up a little too fast .After refine: Baby Bear looks just right 👌. Share #Whisk images you’ve refined to perfection.
11
33
330
Curious to learn more about Whisk? Join the Google Labs Discord server to attend a live demo & AMA with the minds behind the magic of Whisk, happening Dec 17th at 9:30am PT. Head to and find the Discord logo to join.
Meet Whisk! 🎉 Our new experiment that lets you use images as prompts to visualize your ideas and tell your story. Try it now:
10
24
299
It’s kind of magical how two cultures over ten thousand miles apart come together on #FoodMood and end up on your plate. Add more recipes to the mix. 🍽️
2
29
297
9
45
279
Calling all data analysis fans: be among the first to experience @GoogleColab’s new tools, powered by Gemini 2.0, to accelerate your workflow 📊🚀:
.@GoogleColab will feature agentic coding capabilities using Gemini 2.0. Describe your data analysis goals, and watch your notebook take shape automatically. Get early access by joining the trusted tester program.
4
43
281
Come down the rabbit-hole with Infinite Wonderland to see what happens when artists @shawnax, @_EricHu, @erikinternet & @helloharuko use AI to endlessly reimagine the timeless classic, Alice’s Adventures in Wonderland, in their own unique styles →
38
44
227
Catch up on our collaboration with @jacobcollier.to build MusicFX DJ. Check out the livestream recap on our Youtube, where he uses the tool to create a track live! Craft your own songs with MusicFX DJ at
12
38
239
We are so excited to share our latest #LabSession with award-winning songwriter and activist @JustinTranter. Justin brought a wealth of knowledge to help refine Music AI Sandbox, a tool to help songwriters realize their vision. Watch full vid:
20
72
220
It’s officially been a month since I/O! We had a great time hosting @LupeFiasco and @bonniecwoo as guests at the conference. Here’s a fun recap of what they experienced, from Infinite Wonderland to GenType to MusicFX DJ mode. Links in the thread to try the tools yourself ⤵️
18
27
207
WebXR Experiments is a collection of AR and VR experiences made for the web. Try them now to tunnel, measure, explore and more in Chrome on an Android mobile device → #webXR
10
63
223
1️⃣ Open #ImageFX. 2️⃣ Type the prompt you think will recreate this image. 3️⃣ Post your result in the thread.
16
18
229
Lab Sessions are collaborative AI experiments with visionaries across disciplines. In "Journalist x LLMs," @cleoabram and author @stevenbjohnson explore how NotebookLM might accelerate Cleo’s research process and second brain workflow.
14
44
152
#ImageFX is getting an upgrade with the addition of Imagen 3! Get ready to generate even higher-quality visuals with richer details and better text rendering. Just Imagen the possibilities…. Join our waitlist ->
21
18
184
Get a first glimpse of #Imagen3 from our ImageFX trusted testers – we're loving @malfvisuals' portraitures, titled “Ethereal Elegance”.
15
22
182
Introducing editing controls in #ImageFX 🖌️. Brush over and highlight specific areas in your images, so you can re-prompt and edit them until you create what you’re imagining. Add, remove, and change whatever you like. Try it now, available in 110 countries ->
9
42
182
Working with Justin Tranter was an absolute joy. We’re looking forward to continually exploring the future of creativity alongside some of its strongest advocates. Watch Justin put Music AI Sandbox to practice in our latest #LabSession:
70
103
176
The Whisk community is getting festive with our ornament template! 🎄✨ Check out some of these holiday creations and join our Discord to share your own at
10
17
180
Teammate @stevenbjohnson talking all things #NotebookLM on Hard Fork today – give it a listen! 🎧.
It’s Hard Fork Friday! This week on the show, Casey reports from Meta Connect, and we talk to author/Googler @stevenbjohnson about NotebookLM, the hit new AI product that can turn any documents you give it into a podcast. It’s really wild.
22
23
143
Your pieces, your move. 😉 We've teamed up with @theworldchess to bring custom chess pieces created by #GenChess directly to your board! Start your match at or create your own unique set at
13
22
174
🔍AI Mode in Search is now available for all Labs users in the US! Try it today →
Starting today, AI Mode in Google Search is open to all Labs users in the US (no more waitlist). Plus, we’re adding new features to help you get things done - from shopping to planning your next local outing. More details below 🧵.
6
17
173
In our latest #LabSession, we partnered with @jacobcollier to evolve #MusicFXDJ, our generative music tool that helps anyone create a continuous flow of music. 🎧 The full film drops 10/23 & tune into Jacob's YT livestream on 10/24 at 2 PM PST / 5 PM EST
5
20
160
#NotebookLM's Product Manager @raiza_abubakar dives deep into the NotebookLM universe on the Behind The Product podcast -- check it out ✨.
I loved talking with @lennysan (big fan!!) on the Behind the Product podcast to talk all things @NotebookLM! . We dove deep into the origin story, future roadmap, the magic of Audio Overviews, and how we're building at @labsdotgoogle . Huge thanks to Lenny for having me! Give.
2
6
143
New to our community? Curious what we've been up to in our world of AI tools and experiments?. Check out our sizzle reel to learn what we’re about 🔥
6
21
146
The Whisk Plushie Challenge is here!. Design a plushie inspired by spring using #Whisk for your chance to bring your idea to life. 5 winners will have their designs turned into real plushies 🏆. We can't wait to see what you create! Details here:
15
24
148
6
75
127
Join us for a virtual #Whisk craft session. We'll be celebrating spring by building a digital collage together. Where: Our Discord channel When: 1pm PST / 4pm EST tomorrow 3/20. Who: You 🫵
2
16
132
Surface Floater - WebGL artwork creating a physics system that surrounds a 3D model by @lusionltd →
3
27
117
1 Prompt. 26 letters. Any kind of alphabet you can imagine. #GenType empowers you to craft, refine, and download one-of-a-kind AI generated type, building from A-Z with just your imagination. Watch our Creative Lab teammates @trudypainter and @soybean_gx demo this latest
10
18
112
We’re loving all of the submissions to the Whisk Plushie Challenge! Remember to share your entries in our Discord server to be considered for the Fan Favorite Award ⭐. The challenge closes soon, so be sure to get those creations in!
The Whisk Plushie Challenge is here!. Design a plushie inspired by spring using #Whisk for your chance to bring your idea to life. 5 winners will have their designs turned into real plushies 🏆. We can't wait to see what you create! Details here:
1
11
117
That's some tour guide! 🙌 Check out #ProjectAstra’s new capabilities built with Gemini 2.0 – including more seamless conversations, improved memory, and access to Google tools like Search, Lens, and Maps. Learn more about our latest work with @GoogleDeepMind at.
We explored London with a little help from Project Astra. 🇬🇧. With Gemini 2.0, our early research prototype can have more natural conversations, comes with improved memory and can use @Google tools - making it more useful for everyday life. 🤝
4
8
112
We’re in our “merging things from different eras” era. #Whisk.Show us what you’ve been Whisking!
10
11
111
#TextFX’s Simile tool is like your well-read, poetic, sometimes verbose friend that’s a little extra but you love that about them.
6
13
104
We’ve been inspired by all the small hacks being made to help with the challenges people are facing with COVID-19. So we’ve started a #HackToHelp resource page for others who might want to help in any way they can →
5
44
95
The #WhiskersClub — an excuse to share our Whisk-ified pet pics with you, and an invitation for you to share yours with us. We’re ready. 👀🍿
6
7
96
Make a silent film by talking to Chrome. Introducing Peanut Gallery, a new experiment using the Web Speech API. http://t.co/JQvUYuxlF3.
2
90
97
oimo.js, a lightweight 3D physics engine in JavaScript. http://t.co/4NngaxOK3q
#threejs
http://t.co/8Qc2vVCunm.
6
52
85
Each day, our Discord community does a ‘Today's Special’ challenge. Here are a few from our recent prompt: Windowscapes! 🪟 These stunning images were all made using Whisk or ImageFX. See more on “Relaxing Evening”, Whisk - richeklein
6
14
90
Today’s Special: create a #GenChess set inspired by nature.🍁. We’re inspired by a Maple Leaf. What are you making? Share below! .
6
7
82
Infinite Bad Guy is an AI experiment by @YouTubeMusic that uses machine learning to seamlessly align thousands of covers of @billieeilish’s “Bad Guy” into the world’s first infinite music video. Play it now → #InfiniteBadGuy
9
18
82
Project Mariner leverages Gemini 2.0's advanced capabilities to understand complex instructions, reason, and take action across websites. 🧠🌐 It achieves an 83.5% score on the WebVoyager benchmark acting as a single agent, demonstrating its proficiency in real-world web tasks.
6
12
84
We've updated http://t.co/WEAaxoTqxx with @Polymer and a refreshed design. Read about it at http://t.co/y0tHhpGIxV
http://t.co/QA6VoOHk9T.
3
45
74
An easier way to filter through huge piles of images? Yes, please! Our friends @trippedout and @khyatitrehan from the Creative Lab made this prototype of a personal, multimodal search engine. Built with @googlecloud’s #MulitmodalEmbeddings API.
4
9
79
What started as a still image is now an epic sci-fi scene, all powered by Whisk Animate! 🛸
1
7
79
Input an image for the subject, scene, and style or roll the dice if you’re feeling lucky. 🍀 Then, you can remix 🔄 them to create something uniquely your own, from a digital plushie to an enamel pin or sticker. Read more
3
6
74
Want to bring #TeachableMachine into your own web creations? We’re working on a library called teachablemachine.js. Get a sneak peak at what's possible with the remixable Hello Wizard demo ->
3
19
70
Survivors of the Lahaina wildfires harness #ImageFX to build “Postcards from the Future,” an activity that has inspired dialogue and planted seeds for renewal in their community. Led by AI educator @GabrielMY. A thread:
5
21
71
Drawalong AR: An experiment to put YouTube drawing tutorials on the page in front of you → Made with @amandarachlee
3
21
71
A peek into our #GenType Craft Night, hosted at Creative Lab, for those who weren’t there in person 👀
5
12
71
Land Lines, an experiment exploring @GoogleEarth satellite images thru gesture by @zachlieberman & Data Arts Team .
2
29
64
Teachable Machine 2.0 makes it fast and easy to create machine learning models for your projects, no coding required. Train a computer to recognize your images, sounds, & poses, then export your model for your sites, apps, and more →
3
22
63