Jason Baldridge

Research scientist at Google DeepMind in London working on generative media.

[Jason Baldridge @jasonbaldridge]

Our team has been working incredibly hard on creating Lyria 3 this past year! (And it's been pretty much my full focus since moving to London last summer.)

Really excited to get this out and for people to start playing with it and creating. Check it out in Gemini App today!

[Google DeepMind @GoogleDeepMind]

We just dropped Lyria 3: our latest generative music model. 🔊

It can turn photos and text into dynamic tracks - complete with vocals and lyrics. 🧵

[Google Earth @googleearth]

Today we’re bringing AI image generation with Nano Banana to Google Earth, letting you virtually reimagine anywhere in the real world. 🍌 https://t.co/zsgvAnbYrl

For the first time, you can generate custom images using Google Earth’s satellite, aerial, and 3D imagery. 🌎

[Harshith @HarshithLucky3]

Lyria 3.5 in Google Flow Music ❤️❤️

Deepmind really cooked with this one 🔥🔥

really I didn't expected the lyrics could be this good

Video and song generated by producer itself

[Google Flow Music @googleflowmusic]

🎧 Now playing: "De Volta"

Created with Lyria 3.5 🔥

[Jason Baldridge @jasonbaldridge]

I’m so proud of the team’s fast follow of Lyria 3 with Lyria 3.5! It’s a big improvement and a fantastic model. Flow Music still supports editing and many controls too.

I’ve redone some of my previous creations: this Portuguese track came out very nicely: https://t.co/V7Bqawq8oN

[Google Labs @GoogleLabs]

Expecting A Minor update? We prefer to B Major. 🎶

@GoogleDeepMind just released Lyria 3.5, and we’ve plugged it directly into @GoogleFlowMusic to power your next session.

What this means for your tracks:

✨ Better prompt adherence: Flow Music understands your creative direction with much more accuracy. Set exact BPMs and export stems for full-length songs!

🎤 Upgraded vocals: More expressive, dynamic, and rich singing.

🎸 Richer musicality: Arrangements flow more naturally from note to note.

Hear it for yourself and start creating at https://t.co/3XMUc2pkzU 👇

[Google Flow Music @googleflowmusic]

Meet Lyria 3.5, the newest music model from @GoogleDeepMind, now powering Flow Music:

🎤 Vocals: More expressive, dynamic singing
🎸 Musicality: Richer arrangements with tracks that flow naturally.
🎛️ Controls: Better at following creative directions - now featuring BPM control and exportable stems for full-length songs!

Try it now at https://t.co/hqlIaESXXJ! 🧵

[Google Flow Music @googleflowmusic]

Spaces, our vibe coding tool for building any custom instrument or music app, just got a massive upgrade. 🚀

You can now do it all right inside Spaces:

🎵 Generate & edit songs (cover, replace, extend)
🎛️ Split stems
🖼️ Generate images
✍️ Generate lyrics
🎥 Generate videos

[Google Flow @FlowbyGoogle]

“AI moves fast. Stories stay.”

Our resident filmmaker @henrydaubrez created a beautiful film that explores the question: What if illness wasn’t invisible?

Watch the full film and get insights into his process in the thread below.

https://t.co/x8GeSbDKhO

[Demis Hassabis @demishassabis]

Congratulations @KanishkaNarayan on your new role as UK's AI Minister in the Cabinet, great news for the UK AI ecosystem!

[Henry Daubrez 🌸💀 @henrydaubrez]

Five months after wrapping it, OVERGROWN 🌱 is finally out.

My longest film to date.

A 13-minute allegorical drama about living with cancer and chronic illness.
Six months of work.
300+ shots.
Every shot started as an image before becoming video.

I’d probably make it differently today but AI moves fast.
Stories stay.

Full film in the first reply. 👇

[Google Flow @FlowbyGoogle]

🚨 Google AI Subscribers: Unlock free generations! 🚨

From today to August 31, we’re supercharging accounts with 50 Google Flow credits free of charge EVERY. SINGLE. DAY. 🤯

Remember: these credits expire at the end of each day and do not roll over, so be sure to use them!

What are you creating first? Get started at https://t.co/hemtnixzDr

[Google AI @GoogleAI]

Today, we're introducing not one but TWO new models, striking the balance between efficiency and quality to enable you to build production AI agents.

— Gemini 3.6 Flash: Addresses efficiency feedback we received from Gemini 3.5 Flash with upgrades in coding, knowledge work, and multimodal tasks faster, more accurately, and with substantially fewer tokens per task

— Gemini 3.5 Flash-Lite: Our fastest, most cost-effective 3.5-class model yet built for agentic workflows, hitting ~350 output tokens/sec with improved coding and overall quality

Start building with these today via the Gemini API in @GoogleAIStudio or try them out in the @GeminiApp

[Google @Google]

For over 60 years, @Pele’s legendary "lost goal" at Rua Javari lived in the memories of those who were there.

In close collaboration with historians, experts and Pelé’s family, we used @GoogleDeepMind technology to bring this iconic moment to life. ⚽️ See the film ↓

[Google Flow Music @googleflowmusic]

Huge update! 🎹 You can now upload your own beats and instrumentals directly into Flow Music.

Upload your tracks, remix them, and take your sound to the next level.

[Josh Woodward @joshwoodward]

Thanks to the 1,400+ replies in the first 12 hours! I read all of them last night, and another 300+ came in overnight that I’ll catch up on today. Here’s the Top 10 stack rank from your feedback so far, along with where we stand on each:

1) Make Google Workspace integrations work more reliably: This is the clear #1 request, and all of us agree. On it. A set of improvements went into Gemini Spark recently, but this needs to be much better across the entire app.

2) More reliable tool calling: Strongly agree. We know we need to improve here, and you should expect to see noticeable gains soon.

3) Projects & folder organization for chats: Notebooks have been a positive step, but not enough. We’ll rethink this UX and will report back.

4) Add MCPs and Custom Skills: We’ve rolled out early support in Gemini Spark with custom MCPs, custom skills, and a few connected apps, but we're working to make this more widely available and adding more MCPs.

5) Deep Research improvements: You asked for export reports to NotebookLM and the ability to switch between Deep Research mode and Flash/Pro models in the same chat. I wasn’t aware of these pain points. Both are good ideas, and we’ll figure something out.

6) Remove watermarks from Nano Banana: We’ll chat about this later today to see where we can make adjustments while navigating AI rules, which vary by country.

7) Edit any message in chat history: On it. We’ll aim to do this, plus keep our existing chat branching feature.

8) Improve in-app voice dictation accuracy: We're prioritizing this area overall. We’ll dig into these specific replies, and I might DM a few of you to get more info if we need it.

9) Fix mobile app scrolling bugs: Doing this.

10) Fix "Celebrity Likeness" guardrails: We plan to keep this as-is right now.

Thanks again!

[Google DeepMind @GoogleDeepMind]

🏛️ We’re unveiling a new way to converse with the ancient world.

By grounding Gemini directly in our expert models Aeneas and Ithaca, our Predicting the Past Skill in Google @antigravity lets historians study Greek and Latin texts using plain English. 🧵

[Vivek Kumar @vivek_kumar]

We are expanding the Sound Team at @GoogleDeepMind! 🔊

We are building AI that doesn't just generate sound, but deeply understands and interacts with it.

Looking for a Research Scientist to help us push the absolute frontier in audio.

(Link to apply in the first reply)

[Google AI @GoogleAI]

As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that adds a hidden digital watermark to AI content.

Here’s a summary of SynthID’s journey and where the provenance technology (the documented history and origin of digital content) is today:

— SynthID watermarking was originally built for images, but now supports video, audio, and text.

— The technology has watermarked over 100 billion images and videos, alongside 60,000 years of audio.

— You can now verify content with SynthID directly in Google Search, Gemini in Chrome, and the @GeminiApp, where it has been utilized over 50 million times.

— We’ve also adopted C2PA Content Credentials across a growing number of our generative AI tools. This includes the images and videos created within the Gemini app. So now, in addition to the SynthID watermark, you can also see where an image or video originated and how it’s been altered.

— We have open-sourced our text watermarking technology, and we are working with companies like @OpenAI, @NVIDIA, and @Apple to apply SynthID to generative media.

Let us know what you think of the tool so far!

[fofr @fofrAI]

You can bootstrap your agent quickly with the Omni API using the skill we published:

https://t.co/z3qn2ElzWR

It includes:

- video editing
- text to video
- video generation with image references
- first frame to video

But it also has some helper tools for:

- prepping input videos for editing (10s, 720p)
- audio stripping if you want to generate new audio
- video inspection

[Oliver Wang @oliver_wang2]

1/2 Introducing Nano Banana 2 Lite! We are working hard at the next frontier model, but in the meantime enjoy this fast and cheap Nano Banana (Pico Banana?). It returns images in only a few seconds, and with most of the smarts of the NB2 model! https://t.co/0j9RABWCxS

[Greg Lukianoff @glukianoff]

Free speech has to win in court. It has to win on campus. And it has to win in the culture.

That’s why @theFIREorg doesn’t just defend rights quietly. We make the case publicly and relentlessly.