Gemini 2.x for Developers

Discover Gemini, Google’s most capable generative AI model. Learn to build real-time voice and video apps with the Multimodal Live API, use Google Search and Maps to ground responses, and detect objects in images and video using natural language prompts. Explore Gemini’s improved multimodal understanding, coding, and complex instruction following – making it ideal for developing AI agents. Experience preview features like customizable speech generation (control tone, pace, accent, and intonation) and image generation. Plus, learn where all the great notebooks and tutorials are for learning more. After this session, you’ll be ready to build with Gemini on Google Cloud and beyond.