Build agents with Gemini API
Google launches Gemini 3.1 Flash Live as its latest multimodal real-time conversational model
“Google AI Studio is really the best place to get started with all of the Google DeepMind models.”
Google I/O session demonstrated building agents with the Gemini API, highlighting Gemini 3.1 Flash Live as the multimodal real-time conversational model powering the Gemini app. The session showcased agent tool-calling capabilities including function calls to generate audio via Lyra 3. While technically substantive, this is developer evangelism content rather than a novel announcement.