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 👇

Create instant multi-language apps using the Gemini Live API on June 16 → goo.gle/gemini-live-translat… Join our interactive Discord stage session to learn about: ⚡ Low-latency translation models 🗣️ Realtime communication workflows 🛠️ Multi-language developer tools

What will you build this weekend? 🛠️ Gemini 3.5 Live Translate is officially in Preview via the Gemini Live API and Google AI Studio! Skip the fragmented multi-model stack. Stream audio in,get translated audio out. 👇Tap the link to try it out in Google AI Studio: goo.gle/43zzW55 Start building apps: goo.gle/4v7Ufmr

Building for the world, together. 🌍 So inspiring to see what our community created at the Google I/O Hackathon hosted by @Cerebral_Valley and @GoogleDeepMind. Incredible energy, brilliant builders, and innovative projects powered by Gemini 3.5 Flash. Until next time! Check out the winners gallery page: goo.gle/4v0Zynj

Most agent demos are stateless. Ask → answer → context gone. Production agents need to run for days — pausing, resuming, persisting state. @addyosmani joins @smithakolan on the Agent Factory to build three real agents with ADK 2.0 and Gemini 3.5 Flash, including one that runs Doom in the browser. Check out this episode and more in the Agent Factory series → goo.gle/3QdbgMw

🤖 Power Agentic Commerce using your existing backend with the new Universal Commerce Protocol. 💻 Code and troubleshoot faster using the AI-driven Developer MCP server. 📱 Enhance your checkouts with dynamic Android callbacks, social app support, and cross-device authentication! Read our latest blog post to dive into all the new developer features at I/O and get started today ➡️ goo.gle/49tgZ7B

From prompt to production-ready agents. Watch this quick walkthrough to see how Managed Agents in the Gemini API handle the infrastructure layer for you. One simple API call delivers an autonomous agent running inside a remote Google hosted environment. ⚡ Powered by Gemini 3.5 Flash & the Antigravity harness. 📁 Code-first approach: Customize your agent via AGENTS.md and SKILL.md. 🌐 Mount files instantly via Google Cloud Storage or GitHub repositories. Stop managing servers. Focus entirely on agent behavior. Build today: ai.studio/managed-agents

Prepare your site for AI agent interaction with Lighthouse → goo.gle/3ReK3JD If you want AI agents to actually navigate your site properly, the new experimental audit in Lighthouse lets you see: ☀️ Discoverability for AI agents ⚡ WebMCP integration 👀 AI accessibility #GoogleIO

Want 4x faster local inference on dedicated GPUs for your interactive apps? DiffusionGemma is an experimental, open 26B MoE model that generates entire blocks of text simultaneously instead of token-by-token. By shifting the local decoding bottleneck from memory-bandwidth to compute, it hits speeds over 700 tokens/sec on a single NVIDIA RTX 5090 GPU. This diffusion unlocks unique local workflows like real-time inline editing, code infilling, and instant self-correction. 📥 Download the Apache 2.0 weights on @HuggingFace: goo.gle/4xqzKTA 📖 Read the full technical announcement on the blog: goo.gle/4ursgwI

Keep your code readable and spend less time parsing text 📝 Build clear code by keeping it short for local scopes, dropping repetition, and omitting variable types from the name.

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: goo.gle/3QzaHwN