Google DeepMind

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵

[pumped] gemini 3.1 flash text-to-speech just landed in ai studio. you can now trigger specific vocal delivery like pace and accent by including [tags] in front of dialogue. iterate in composer view then export the code to start building.

Big news: "Dear Upstairs Neighbors" is premiering at @Tribeca! 🎬 Inspired by a sleepless pandemic night, our 45-person crew of Pixar alumni, an Academy Award winner, researchers, and engineers developed new workflows to bring original artwork and paintings to life. @GoogleDeepMind

Instead of writing complex code, the team interacted with Spot using plain English. We built a bridge between Gemini Robotics ER and Spot's system, giving the AI a basic set of tools to move freely, take photos, and grab things - enabling it to carry out more complex tasks. Find out more → goo.gle/4tP7Aif

We teamed up with @BostonDynamics to power their robot Spot with Gemini Robotics embodied reasoning models. This means it can better understand its surroundings, identify objects and follow simple commands - like tidying up a room.

Here’s where to find it: Developers: Preview via Gemini API and @GoogleAIStudio Enterprise: Rolling out in preview on Vertex AI Everyone: Rolling out to @Google Vids Find out more → goo.gle/3Orfb7I

🔵 More natural sounding speech 🔵 Support for 70+ languages like Hindi, Japanese, and German 🔵 SynthID watermarking on all outputs

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵

True multimodal AI needs to understand the world spatially 🎯 🚀 Excited to release #CVPR2026 TIPSv2 from @GoogleDeepMind, a foundational image-text encoder with spatial awareness, leading to strong overall results and massive gains on patch-text alignment. 🔥 1/N

Ready to build smarter robots? The model is available now on @GoogleAIStudio and the Gemini API. Find out more → goo.gle/4dGSh6y

This is also our safest robotics model yet. Gemini Robotics-ER 1.6 understands physical constraints like avoiding liquids or items over 20kg when carrying out instructions. It is also 10% better at detecting human injury risks in videos.

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵

Building a voice agent? Gemini 3.1 Flash Live (Thinking) just topped @sierraplatform's τ-Voice Leaderboard benchmarking realtime voice agent performance! #leaderboard?benchmark=voice" target="_blank" rel="nofollow noopener">taubench.com/#leaderboard?b…

Start building with Gemma 4 ↓ goo.gle/41IC3lY

Gemma 4 punches above its weight, outperforming models 10x its size without the need for massive compute. With 10M+ downloads in its first week and 500M+ for the Gemma family overall, we’re excited to see this level of engagement within the open research community.

Google Vids is an easy-to-use video editing suite, and we just added new AI capabilities, starting with: High-quality video generation with Veo 3.1, available to everyone at no cost 🎬 ✨ Find out what else is new 👇 then get started creating at vids.new