Generate high-quality videos from text and image prompts with Veo 2, a video generation model, now generally available in the Gemini API and Google AI Studio to enhance your content creation and marketing efforts.

The Apigee Extension Processor enhances Apigee's capabilities by enabling it to manage gRPC streaming and integrate with Google Cloud services through Cloud Load Balancing, allowing for applying Apigee policies to a wider range of backend services, and improving secure access to Google Cloud infrastructure.

Updates to the Gemini API, including the production readiness of Veo 2 for video generation, the preview of the Live API for real-time interactions, and the upcoming Gemini 2.5 Flash model, alongside the existing Gemini 2.5 Pro aim to enhance developer capabilities in building AI applications with improved thinking models, dynamic interactions, and high-quality video generation.

The Agent Development Kit (ADK), an open-source framework from Google designed to simplify the development of multi-agent systems, providing tools for building, interacting, evaluating, and deploying agents.

Agent2Agent (A2A) protocol is an open standard designed to enable AI agents from different vendors and frameworks to collaborate and exchange information across enterprise platforms aiming to foster a future of seamless AI agent interoperability and enhanced automation.

The Google Developer Program is evolving with AI-powered tools like Gemini Code Assist and expanded resources, including new Premium and Enterprise offerings, access to product previews, and increased workspace capacity, making it easier for developers to build and innovate.

Google Cloud Dataflow's Managed I/O simplifies using Apache Beam I/O connectors by automatically updating connectors to the latest versions and providing a standardized API, optimizing connectors specifically for Dataflow, ensuring efficient performance and reducing the need for manual configuration, freeing users to focus on pipeline logic.

The Gemini API and ESP32 microcontroller simplify custom voice commands for IoT devices, leveraging speech recognition for devices to understand and react to custom commands, bridging the gap between digital and physical worlds.

Google DeepMind releases TxGemma, built on Gemma, which predicts therapeutic properties, and Agentic-Tx, powered by Gemini 2.0 Pro, which tackles complex research problem-solving with advanced tools.

The Google I/O 2025 puzzle used the Gemini API to generate dynamic riddles for bonus worlds, enhancing player engagement and scalability. Here's what our developers learned on using the Gemini API effectively, including creativity, design, and implementation strategies.