Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

With advanced video understanding, Gemini 2.0 Flash Experimental can: 🔍 Look up key moments 📝 Give shot-by-shot summaries 🖥️ Analyze screen recordings And much more. →

Google DeepMind

1,390,849 subscribers

59,736 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Umesh1 year ago

Great update! Countless applications! Is it possible to give an image as input and ask it to find if the person in the given image appears on the video?

AssemblyAI1 year ago

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

AI Leaks and News1 year ago

The team is doing some incredible things!

Luis Fernando1 year ago

Beautiful 😍

Prashant Rai1 year ago

Amazing! December has never felt this warm as AI made it.

madpencil_1 year ago

Cooked FR! 🔥

Luca Iaconelli1 year ago

Amazing 🔥

Prasenjit1 year ago

The most important thing analyzing video recording, which is amazing.

Médéric Hurier (Fmind)1 year ago

Impressive demo, like the other ones. Good job on your AI progress!

Chansoo Byeon1 year ago

hey @GoogleDeepMind, could you please tell @YouTube, @Google & @sundarpichai to STOP censoring people?

QuantumMindX1 year ago

But when will more languages be supported for live chat?

Related Videos

Get personal with Google Gemini’s newest capability. ✨ Powered by our Gemini 2.0 Flash Thinking Experimental model, it can analyze your Search history with your permission to better understand interests and give more helpful answers. 🔍

Get personal with Google Gemini’s newest capability. ✨ Powered by our Gemini 2.0 Flash Thinking Experimental model, it can analyze your Search history with your permission to better understand interests and give more helpful answers. 🔍

Google DeepMind

177,858 views • 1 year ago

Get up to speed on complex topics using Deep Research—coming to Pixel users with Gemini Advanced 🔍Browses up to 100s of websites in minutes 📝Generates a report with key findings & links 🧠Saves you time (+ brain power) *See video for info & learn more:

Get up to speed on complex topics using Deep Research—coming to Pixel users with Gemini Advanced 🔍Browses up to 100s of websites in minutes 📝Generates a report with key findings & links 🧠Saves you time (+ brain power) *See video for info & learn more:

Made by Google

183,714 views • 1 year ago

Google drops Gemini 2.0 Flash Thinking a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more now available in anychat, try it out:

Google drops Gemini 2.0 Flash Thinking a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more now available in anychat, try it out:

AK

141,723 views • 1 year ago

We're upgrading Deep Research in Google Gemini with Gemini 2.0 Flash Thinking Experimental - and now all users can try it at no cost. From planning and searching to synthesizing findings, it can create even more insightful reports on just about any topic in minutes. →

We're upgrading Deep Research in Google Gemini with Gemini 2.0 Flash Thinking Experimental - and now all users can try it at no cost. From planning and searching to synthesizing findings, it can create even more insightful reports on just about any topic in minutes. →

Google DeepMind

98,574 views • 1 year ago

We partnered with ICC to show how Gemini 3 Pro can analyze video content. By uploading a segment of the Cricket World Cup, Gemini can seamlessly process visual and audio data to identify key players, explain techniques, and highlight crucial turning points. 🏏

We partnered with ICC to show how Gemini 3 Pro can analyze video content. By uploading a segment of the Cricket World Cup, Gemini can seamlessly process visual and audio data to identify key players, explain techniques, and highlight crucial turning points. 🏏

Google Gemini

4,322,587 views • 6 months ago

This is dope update for Gemini macOS app 🔥 You can now long press the Fn key and simply talk to Gemini from anywhere on your Mac. By default, it works as an intelligent dictation tool that: - Removes "ums" and "ahs" - Cleans up mid sentence corrections - Formats your text automatically - Pastes polished text directly where your cursor is Enable Gemini Reasoning, and it can do even more by understanding what's on your screen. For example, you can: - Summarize documents, PDFs, and images - Rewrite highlighted text in any tone - Turn notes into polished emails or executive summaries - Generate and edit images using voice commands Instead of switching between apps, you can just speak naturally and Gemini handles the rest. This update is rolling out globally in English for the Gemini app on macOS, with more languages coming soon. Video credit: Google Blog

This is dope update for Gemini macOS app 🔥 You can now long press the Fn key and simply talk to Gemini from anywhere on your Mac. By default, it works as an intelligent dictation tool that: - Removes "ums" and "ahs" - Cleans up mid sentence corrections - Formats your text automatically - Pastes polished text directly where your cursor is Enable Gemini Reasoning, and it can do even more by understanding what's on your screen. For example, you can: - Summarize documents, PDFs, and images - Rewrite highlighted text in any tone - Turn notes into polished emails or executive summaries - Generate and edit images using voice commands Instead of switching between apps, you can just speak naturally and Gemini handles the rest. This update is rolling out globally in English for the Gemini app on macOS, with more languages coming soon. Video credit: Google Blog

AshutoshShrivastava

14,630 views • 20 days ago

5⃣ Deep Research is even smarter, rolling out for everyone to try. Today, we're giving Gemini users the ability to try Deep Research, your personal AI research assistant, at no cost. 🧠✨ Gemini Deep Research has been upgraded to 2.0 Flash Thinking Experimental. With this model’s advanced reasoning, Gemini is even better at all stages of research, from planning to delivering even more insightful and detailed reports. Gemini Advanced and qualifying enterprise users have expanded access to Deep Research to save even more time on their most complex projects. Try Deep Research:

5⃣ Deep Research is even smarter, rolling out for everyone to try. Today, we're giving Gemini users the ability to try Deep Research, your personal AI research assistant, at no cost. 🧠✨ Gemini Deep Research has been upgraded to 2.0 Flash Thinking Experimental. With this model’s advanced reasoning, Gemini is even better at all stages of research, from planning to delivering even more insightful and detailed reports. Gemini Advanced and qualifying enterprise users have expanded access to Deep Research to save even more time on their most complex projects. Try Deep Research:

Google Gemini

258,461 views • 1 year ago

wow.. this AI is crazy you can now use Google Gemini 2.0 image editor on FLORA and its much more advanced you can edit image with simple text and turn it into commercial video directly it's free to use for a limited time now, link in comment 10 examples:

wow.. this AI is crazy you can now use Google Gemini 2.0 image editor on FLORA and its much more advanced you can edit image with simple text and turn it into commercial video directly it's free to use for a limited time now, link in comment 10 examples:

el.cine

1,371,782 views • 1 year ago

One prompt → your next landing page. We hooked up Gemini 3.7 Flash with Nano Banana and Omni in @Antigravity to build an interactive landing page from scratch, generating the copy, images, and video in a single shot.

One prompt → your next landing page. We hooked up Gemini 3.7 Flash with Nano Banana and Omni in @Antigravity to build an interactive landing page from scratch, generating the copy, images, and video in a single shot.

Google

406,272 views • 2 days ago

wow.. this AI is crazy you can now use ChatGPT image 2.0 on infinite canvas and its much more advanced you can edit image with simple text and turn it into commercial video directly

wow.. this AI is crazy you can now use ChatGPT image 2.0 on infinite canvas and its much more advanced you can edit image with simple text and turn it into commercial video directly

Abhishek

31,491 views • 3 months ago

If you try nothing else today, give the demo at a go - it lets you stream video and audio directly to Gemini 2.0 Flash and get audio back, so you can have a real-time audio conversation about what you can see with the model Feels like science fiction!

If you try nothing else today, give the demo at a go - it lets you stream video and audio directly to Gemini 2.0 Flash and get audio back, so you can have a real-time audio conversation about what you can see with the model Feels like science fiction!

Simon Willison

208,990 views • 1 year ago

Seedance 2.0 in native 4K is finally cinema-ready. Precise detail, crops that stay sharp in post, and VFX that holds up on the big screen. Genuinely the first AI video built for cinema and commercials. Showcased in a shot with hay nyash.

Seedance 2.0 in native 4K is finally cinema-ready. Precise detail, crops that stay sharp in post, and VFX that holds up on the big screen. Genuinely the first AI video built for cinema and commercials. Showcased in a shot with hay nyash.

Higgsfield AI 🧩

440,848 views • 1 month ago

We’re building AI agents to help you navigate the virtual world of video games. 🎮 With Gemini 2.0’s capabilities, they can watch what’s happening on screen in real time, and offer up suggestions for your next move. See it in action ↓

We’re building AI agents to help you navigate the virtual world of video games. 🎮 With Gemini 2.0’s capabilities, they can watch what’s happening on screen in real time, and offer up suggestions for your next move. See it in action ↓

Google DeepMind

40,424 views • 1 year ago

Introducing the Circle MCP. You can connect your community to Claude, ChatGPT, or Gemini and use it to look up members, queue up posts, analyze threads, create spaces, develop courses, send DMs, bulk-create tags, and 100+ other things from your own AI ecosystem. It comes with both read AND write access, which makes it a lot more fun than other MCPs!

Introducing the Circle MCP. You can connect your community to Claude, ChatGPT, or Gemini and use it to look up members, queue up posts, analyze threads, create spaces, develop courses, send DMs, bulk-create tags, and 100+ other things from your own AI ecosystem. It comes with both read AND write access, which makes it a lot more fun than other MCPs!

Sid Yadav

19,920 views • 4 months ago

TPUs incoming 🔥 Stitch is now using Gemini 2.5 Pro Experimental Mode by default . Users have preferred the results of experimental mode 3x versus standard mode. Everything is now generated with Gemini 2.5 Pro, making the output more creative and—most importantly—much easier to edit ✨. This mode hasn't gained the ability to export to Figma, nor theming yet. That's still available in standard mode for now if you need it! Enjoy the new power and let us know what you think! 🚀 [Attached video is sped up. Experimental mode generations are very thorough - taking ~50s]

TPUs incoming 🔥 Stitch is now using Gemini 2.5 Pro Experimental Mode by default . Users have preferred the results of experimental mode 3x versus standard mode. Everything is now generated with Gemini 2.5 Pro, making the output more creative and—most importantly—much easier to edit ✨. This mode hasn't gained the ability to export to Figma, nor theming yet. That's still available in standard mode for now if you need it! Enjoy the new power and let us know what you think! 🚀 [Attached video is sped up. Experimental mode generations are very thorough - taking ~50s]

Stitch by Google

46,901 views • 11 months ago

Seedance 2.0 and 2.0 Fast have arrived on Leonardo. Now you can take this tool and start directing every shot with more control. Here’s what creators are saying 2.0 is really good at: - Editing your videos using image and video references so you don’t have to prompt from scratch. - Controlling camera motion with precision. - Reproducing specific pans, zooms, tracking shots, etc. from video references. - Keep characters consistent from scene to scene. Any scene you can imagine is yours to create. Start creating.

Seedance 2.0 and 2.0 Fast have arrived on Leonardo. Now you can take this tool and start directing every shot with more control. Here’s what creators are saying 2.0 is really good at: - Editing your videos using image and video references so you don’t have to prompt from scratch. - Controlling camera motion with precision. - Reproducing specific pans, zooms, tracking shots, etc. from video references. - Keep characters consistent from scene to scene. Any scene you can imagine is yours to create. Start creating.

Leonardo.Ai

104,943 views • 4 months ago

🎬 I just built a custom GPT designed specifically for creating high-end TV commercial ad prompts for Seedance 2.0. 📺 Cinematic commercial storytelling 🎥 Shot-by-shot ad structure with timestamps 🎭 Character emotions, acting, and dialogue 🎬 Professional film camera language (angles, movement, pacing) ⚡ Consistent, production-ready prompts for ads and branded content Create luxury commercials, product ads, fashion campaigns, cinematic promo videos, and social media ads without writing messy prompts manually. Built for fast AI video production workflows. Works with Seedance 2.0, Grok, ChatGPT, Gemini, and other AI generation tools as well.

🎬 I just built a custom GPT designed specifically for creating high-end TV commercial ad prompts for Seedance 2.0. 📺 Cinematic commercial storytelling 🎥 Shot-by-shot ad structure with timestamps 🎭 Character emotions, acting, and dialogue 🎬 Professional film camera language (angles, movement, pacing) ⚡ Consistent, production-ready prompts for ads and branded content Create luxury commercials, product ads, fashion campaigns, cinematic promo videos, and social media ads without writing messy prompts manually. Built for fast AI video production workflows. Works with Seedance 2.0, Grok, ChatGPT, Gemini, and other AI generation tools as well.

Gumvue Studio

15,003 views • 3 months ago

Gemini DeepThink is Insane 🫡 You can generate a website with planets that can be control by hand gesture, it detects hand gestures using your camera and interact this is crazy it took one shot . This was created by one simple prompt thats it , btw i was shy sharing video there is mess all around 🙂

Gemini DeepThink is Insane 🫡 You can generate a website with planets that can be control by hand gesture, it detects hand gestures using your camera and interact this is crazy it took one shot . This was created by one simple prompt thats it , btw i was shy sharing video there is mess all around 🙂

Chetaslua

31,018 views • 8 months ago