Google for Developers

Discover the latest developer tools, resources, events, and announcements to help you build smarter, ship faster. 🚀

[Google for Developers @googledevs]

Gemini 3.5 Live Translate is now available in public preview on the Gemini API and Google AI Studio. 💬

This model translates speech as it streams, giving developers a blazing-fast, low-latency engine to build some seriously cool audio apps. See it in action 👇

[Google for Developers @googledevs]

@janis_neimanis Yes, that language pair is supported. 🎉

[Google for Developers @googledevs]

Gemini 3.5 Live Translate is now in Public Preview via the Gemini API, delivering low-latency speech-to-speech translation across 70+ languages and 2,000 language pairs! 🌍

Challenge time: What is the most niche, unique, or complex language pair your application needs to translate? Tell us in the comments, and we’ll let you know if the model supports it!

Full blog link: https://t.co/w1sf5OxbmU

[Google for Developers @googledevs]

@chetan_crasta Try it out in AI Studio and let us know what you think: https://t.co/HqPyDhIR1B

[Google for Developers @googledevs]

Explore how you can build digital dubbing tools, conversational experiences, and more in AI Studio: https://t.co/H9X06E1gLu

Get more in the blog: https://t.co/BKrPEifrUi

[Google for Developers @googledevs]

Gemini 3.5 Live Translate is now available in public preview on the Gemini API and Google AI Studio. 💬

This model translates speech as it streams, giving developers a blazing-fast, low-latency engine to build some seriously cool audio apps. See it in action 👇

[Google for Developers @googledevs]

@GrabSG You can also try it on Google Translate now! This demo shows the new listening mode, featuring automatic language detection and earpiece routing for clear audio outdoors.

[Google for Developers @googledevs]

Here we see how the model handles multi-language continuous speech translation, detecting the language being spoken and manages natural turn-taking during long sessions. Now available in Google Meet for select Google Workspace customers, followed by a broader rollout later this year.

[Google for Developers @googledevs]

@Seconalz Congrats, keep up the good work!

[Google for Developers @googledevs]

Gemini models are now accessible to millions of Apple developers through Apple’s Foundation Models framework and natively within Xcode. You can now easily swap between local and cloud inference using a shared API surface to build next-generation agentic app experiences, increase development velocity, and offload heavy workloads to the cloud. Additionally, you can use agentic coding assistance from Gemini in Xcode to accelerate multi-step development tasks.

Check out the full announcement to get started: https://t.co/q0TM4EjpqC

[Google for Developers @googledevs]

Catch up on announcements and highlights from I/O by selecting an audio overview, powered by Gemini in NotebookLM.

Get all of the NotebookLM podcasts:
AI → https://t.co/dep0GliR7x
Android podcast → https://t.co/w1ROWAOE8p
Chrome podcast → https://t.co/SEPOpavqkt
Cloud podcast → https://t.co/cCtz92vWVa

Check out the full notebook for even more I/O nuggets → https://t.co/juNliY4YVf

[Google for Developers @googledevs]

Equip agents to use data more effectively by providing clear instructions through MCP. ✨

Learn more about how MCP can provide agents with a deeper understanding of API meanings and situational context through GEAR → https://t.co/FVQHoJtcRt

[Google for Developers @googledevs]

Package.json defines what versions are allowed. Another file can define what version actually gets installed.

[Google for Developers @googledevs]

New package management challenge: package.json didn’t change, but local and CI installed different versions. One committed file explains it. Can you spot which one?

[Google for Developers @googledevs]

We asked people when they knew they wanted to be a developer. ✨

When was that "aha" moment for you? Share your story in the comments!

[Google for Developers @googledevs]

Why have one AI agent handle everything when you can build a team? 🤝

Multi-agent architecture allows a main agent to spin up specialized sub-agents and handle complex tasks in parallel - making workflows faster and more efficient inside Google AI Studio.

Check out the full I/O session: https://t.co/J9YyLBd2r3 🧵👇

[Chrome for Developers @ChromiumDev]

See what it actually takes to prep for a #GoogleIO session, from backstage mic checks to the post-session high-fives. @Una, @matthiasrohmer, @tomayac, and Mark Thompson share an insider look behind this year's biggest event.

[Google for Developers @googledevs]

The new @GoogleColab bridges the gap between local environments and the cloud, providing a zero-friction execution platform for developers and AI agents alike. The CLI Supports:

⚡️ Agent-driven Colab workflows
⚡️ Instant GPU/TPU provisioning
⚡️ Remote script execution
⚡️ Interactive runtime access (console/REPL)

Learn more in the blog: https://t.co/n8TOYStlrp

[Google for Developers @googledevs]

Download the model weights on @HuggingFace: https://t.co/3E60X9VhuI

Read more in the blog: https://t.co/vKtSKunb6F

[Google for Developers @googledevs]

Gemma 4 quantization-aware training (QAT) models are now available, bringing AI performance directly to edge devices and consumer GPUs. These checkpoints are optimized with quantization-aware training to dramatically reduce memory requirements and unlock high-speed local inference. 🧵

[Google for Developers @googledevs]

Ecosystem integrations are live today across popular developer tools including Hugging Face, Llama.cpp, Ollama, MLX, LM Studio, NVIDIA, vLLM, Unsloth, and LiteRT-LM.