Adrià Recasens

This April I will be running the @LLHalf in memory of my nephew Guifré and in support of the work that @tommys does for those who suffered baby loss. If you are interested on contributing, here is my fundraising page! llhm.tommys.org/fundraising/ar…

Gemini 3.1 Flash Live is our highest quality audio & voice model yet - and a big leap towards building next-gen voice-first agents. Lower latency, better precision, more natural interactions... try it now with Gemini Live in the @GeminiApp or build with it in @GoogleAIStudio!

@OriolVinyalsML @la_UPC Moltes felicitats!

On my way to Barcelona to receive a Doctor Honoris Causa from my alma mater, @la_UPC. Truly honored! 🎓 Join Thursday for my Master Class, "From AI to AGI: The Quest for True Intelligence." Hope to see you there! telecos.upc.edu/ca/esdevenimen… "Create an image at 41.4036° N, 2.1744° E, January 1st, 1983, 15:00 hours."

@BieXiaoyu @GoogleDeepMind Of course, no problem!

@arecasens @GoogleDeepMind Hi Adrià! I’m a postdoc working on generative AI for audio, and this role looks like a perfect fit with my background and interests. Mind if I DM you a couple of quick questions?

We are hiring! I'm looking for a Research Scientist to work on Gemini Audio in @GoogleDeepMind London ♊️🔊 Feel free to reach out if you have any questions! job-boards.greenhouse.io/deepmind/jobs/…

🔊Native audio outputs in Gemini 2.5 give developers new ways to build richer applications with conversation and speech. ↓ blog.google/technology/goo…

Very nice demo of many of the capabilities available with native audio out, try it yourself in aistudio.google.com/apps/bundled/m…

We are shipping! 🚢🚢🚢 Native audio output is now available in the Live API. Very natural interaction with the option of using Google Search or thinking for more refined answers. Try it out in aistudio.google.com/live and let us know what you think!

Happy to see the first feature powered by Gemini native audio outputs ship out to public - especially since it's MASSIVELY multilingual. Lots more coming soon 😉

NotebookLM parla català! Molt content de veure com Gemini contribueix a que NotebookLM parli més de 50 idiomes!

Introducing Gemini 2.5 Pro Experimental! 🎉 Our newest Gemini model has stellar performance across math and science benchmarks. It’s an incredible model for coding and complex reasoning, and it’s #1 on the @lmarena_ai leaderboard by a drastic 40 ELO margin. Only a handful of model releases have leaped ahead so strongly in ELO. 📈 ELO score differences map directly to win rate: e.g. a 400 ELO difference yields a ~91% win rate. Incredible that since 1.5, just a year ago, we jumped 200 ELO (300 since 1.0). Here’s a fun example where Gemini 2.5 Pro writes code to create an animated swarm of colorful boids swimming in a rotating hexagon. 💫 Try the model for free today in AI Studio. It’s also available to Gemini Advanced users in @geminiapp. aistudio.google.com/app/prompts/ge… Blog: goo.gle/4c3NitO

Gràcies a @parentesismedIA pel reconeixement!

New Gemini 2.0 modalities will enable entirely new interfaces! ✨ that's why I love this early experimentation my teammate @trudypainter is doing with native audio output in her VoiceCursor prototype. I've been playing with this UI and it really feels like a magical piece of paper coming to life. Excited for native audio to roll out more widely so more people can start experimenting.

Gemini 2.0 Flash Experimental has the ability to produce native audio in a variety of styles and languages - all from scratch. 🗣️ Here’s how this is different to traditional text-to-speech systems ↓ aistudio.google.com/live

Congrats to the #Veo2 team, brilliant work! This is so far my favorite example, combining generation and reasoning 🤯🤯🤯

Gemini 2.0 Flash's video understanding is here 🚀 Think: search in videos via timecodes, extract text from moving camera footage, analyze screen recordings in real-time interactions with native audio out 🔊 Come and try it aistudio.google.com 😀 youtu.be/Mot-JEU26GQ?si…

A very interesting opportunity to work at the intersection of data and scaling. Paul's insights have been crucial to the success of Gemini 2.0 flash (and 1.5 and 1.0 and... 👀). He makes for an excellent mentor/manager! Come help us push the frontier further 🦾.

Great work by many amazing folks to put this together - looking forward to when it's available to everyone ♊️

"Say this in a whisper ..." 💬 Native audio output was definitely my favorite Gemini 2.0 demo to make. Being able to steer the voice so expressively with just prompts felt totally new. 🙂x.com/googleaidevs/s…

Finally, native audio generation with Gemini! m.youtube.com/watch?v=qE673A…

Gemini 2.0 Flash comes with native audio output, and it’s actually wild 🤯 we are working hard to roll this out quickly to more folks!