Discover the latest developer tools, resources, events, and announcements to help you build smarter, ship faster. 🚀
- Tweets 13,023
- Following 315
- Followers 2,578,535
- Likes 5,264
Pinned Tweet
Say hello to our new Gemini 3.8 text-to-speech models.
Whether you need creative nuance or massive scale, build custom voice apps with more precise control using our most expressive models yet:
🔊 Gemini 3.8 Flash TTS: Designed for creatives, this model lets you use natural language to create custom vocal personas and direct cues, pacing, and dialects to build immersive apps and narrative games.
🔊 Gemini 3.8 Flash-Lite TTS: Built to scale high-volume audio pipelines, such as bulk audiobook production and audio dubbing.
Try building with the new audio models now via the Gemini API in @GoogleAIStudio.
blog.google/innovation-and-a…
52
83
747
64,628
Google for Developers retweeted
Building Android apps with AI is more open and flexible than ever before.
New: You can now build with your agent of choice inside Android Studio!
Bring Your Own Agent is rolling out in preview with the latest Canary build. Featuring Claude Agent, Codex, @Antigravity, and more.
Build your way → goo.gle/4xOgmiP
8
33
310
58,673
Gemma 4 is now running locally on-device in the @Antigravity SDK. 🙌
Build fully local or hybrid multi-agent workflows that pair cloud models with a @GoogleGemma 4 workforce. Audit, patch, and test your code with total data privacy and zero API fees—all powered by LiteRT under the hood.
55
132
1,304
99,712
Read the blog to get started: goo.gle/4h70LoQ
2
5
39
6,798
Say hello to our new Gemini 3.8 text-to-speech models.
Whether you need creative nuance or massive scale, build custom voice apps with more precise control using our most expressive models yet:
🔊 Gemini 3.8 Flash TTS: Designed for creatives, this model lets you use natural language to create custom vocal personas and direct cues, pacing, and dialects to build immersive apps and narrative games.
🔊 Gemini 3.8 Flash-Lite TTS: Built to scale high-volume audio pipelines, such as bulk audiobook production and audio dubbing.
Try building with the new audio models now via the Gemini API in @GoogleAIStudio.
blog.google/innovation-and-a…
52
83
747
64,628
Looking to level up your skills and connect with fellow builders? #DevFest season is here 💫
Join local Google Developer Groups to learn from interactive workshops, share technical knowledge, and expand your network.
Find an event near you and register today: goo.gle/devfest
3
15
55
20,725
Google for Developers retweeted
10,000 installs and counting! 📈 We created Modern Web Guidance to bring web platform expertise right into your agent workflows. Have you tried pairing these skills with Chrome DevTools for agents to audit performance and automatically fix code?
Check it out and join 10K+ web developers who are coding smarter → goo.gle/4yEVz1h
23
140
1,072
75,539
See how AI models can help you with multi-day engineering workflows with Android Bench 2.0.
The updated benchmark evaluates long-horizon tasks like building apps and features from scratch, migrating cross-platform codebases to Android, and making complex architectural transitions, with continuous completion scoring that shows which tasks models perform well on.
Check out what's new 👇
📢 Introducing Android Bench 2.0.
We've leveled up our AI evaluation framework to handle real-world, multi-day engineering challenges—from building apps from scratch to migrating cross-platform codebases to Android.
Let’s dive into what’s new. 🧵👇🏽
ALT Android Bench 2.0 dashboard with category filter buttons.
19
27
234
38,890
Open tooling builds stronger developer ecosystems.
We teamed up with @speakeasydev to ship the new Google GenAI SDKs for our Interactions, Agents, and Webhooks APIs. Read why we believe SDK generation belongs in the open and explore Speakeasy's newly open-sourced OpenAPI generator suite:
nitter.net/GoogleAIStudio/status/…
25
31
218
41,702
Want to try Gemini 3.5 Transcribe, 3.8 Live, 3.8 Live Extended Thinking, and meet the folks who built them? 🎙️
Join us for Gemini Audio | At Night, an evening exploring the next frontier of voice-first AI.
Connect with the product and research teams behind our latest Gemini Audio models, test live interactive demos, and network with fellow builders and founders.
📍 The Pearl, San Francisco
🗓️ Thursday, Sept 24 | 6:00 PM to 10:00 PM
RSVP today: goo.gle/4xpdcBn
ALT A graphic for Gemini Audio with the words "At Night" prominently displayed in large white text. Above it, a smaller logo features a four-pointed star next to the words "Gemini Audio," all set against an abstract background of flowing blue light and subtle dot patterns.
14
43
382
35,862
Building voice AI with Gemini?
Join us live on Discord with @thorwebdev from @GoogleDeepMind and @hermes_f from Agora.
We’ll cover the latest real-time capabilities, natural turn-taking, interruptions, tool use, evals, and what it takes to ship dependable voice agents.
📅 Thursday, Sep 17 at 9 AM PT / 12 PM ET
Link: bit.ly/4xAzPDQ
2
11
32
6,108
🗣️ Introducing Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking.
These advanced audio models are built for natural conversation, featuring major upgrades in turn-taking and near real-time reasoning. They also significantly streamline how you build intelligent voice agents.
Until now, advanced reasoning and reliability came at the cost of high latency and the complexity of cascaded, multi-model pipelines. Stitching together separate speech-to-text, reasoning, and text-to-speech models adds delay and inflates costs.
By replacing that stack with a single multimodal API call, these two models make building highly responsive voice agents simpler and cost-effective.
🧵 Here’s what you can build with them:
26
44
546
86,667
Gemini 3.8 Live Extended Thinking goes even further for complex and multi-step workflows that demand deeper reasoning.
Instead of silent loading states, you can create agents that reason and speak simultaneously. They narrate their logic out loud using natural verbal cues, keeping users engaged during heavy computational tasks.
Watch it act as a workshop companion, processing visual input and guiding a cyberdeck build on the fly:
1
5
43
5,410
Start building smarter voice applications seamlessly with Gemini 3.8 Live and 3.8 Live Extended Thinking.
Available today through the Gemini API via @GoogleAIStudio and coming soon to the Gemini Enterprise Agent Platform.
Read the blog more details ↓
blog.google/innovation-and-a…
2
21
4,191
It's been a busy couple of weeks for the @antigravity team. Here's a few updates they've made ⬇️
> AlphaGenome Atlas Skills are launched to accelerate genomic discovery using AI agents.
> /boost command for tackling complex developer tasks through a focused multi-agent reasoning workflow.
> /teamwork-preview is improved and powering breakthroughs in mathematics, hardware simulation and open source optimization.
> Interactive Generative UI Artifacts creation is now available, ranging from data visualizations to 3D explanatory simulations that can be rendered seamlessly inline and in your artifacts panel.
> Updated Git Version Control System and Terminal, giving more flexibility to track changes to your repository and running tests, scripts, and commands directly in the embedded terminal.
41
36
542
77,237
Google for Developers retweeted
Build stateful, production-grade AI agent networks with Gemini Enterprise Agent Platform and @antigravity.
This hands-on, 4-part live technical series covers programmatic logic with ADK, long-term state management, and secure deployment on Google Cloud → goo.gle/4cMRgsv
16
63
487
34,344
Go from idea → interactive prototype in minutes with @stitchbygoogle.
🔖 Bookmark this post for inspiration, and get started on your next design project: stitch.withgoogle.com
9
31
156
27,561
From simulations to visual reasoning, see what developers are building with Gemini 3.8 Flash. ⚡️
Check out some builds and experiments from the community and get inspired 🧵↓
20
16
289
74,455
Black hole visualizer
Gemini 3.8 Flash is wayy better than 3.7 Flash..
This is one of the best Gargantuan Black Hole simulation I've ever gotten with any Gemini Model !
I've tried it many times before with earlier Flash models before this but the results were too bad to even show..
I'm impressed of this one truly!
I have so many things that it has built. I've been at it for more than 16 hrs and I'll be sharing all of it and will also call out some posts in the process..
1
2
34
11,292
Semiconductor fabrication plant visualization
Just tried Gemini 3.8 Flash and wow, I’m genuinely impressed, It finished everything in under 2 minutes and the quality was way better than I expected, For now it’s only in Chat, but it should be coming to Antigravity and AI Studio later, Really excited to test it there too!
4
21
7,580