Explore low-latency multimodal and voice-first workflows with Gemini 3.1 Flash Live Preview.
Explore low-latency multimodal and voice-first workflows with Gemini 3.1 Flash Live Preview.
This project is part of the Foundations category and is recommended for learners at Levels 0-2. Expected difficulty: Beginner
Learn the latest OpenAI mini and nano model setup, structured outputs, and fast prompt patterns.
Build triage, handoff, and tool-calling workflows with the OpenAI Agents SDK.
Build multimodal, multilingual, and hybrid-thinking applications with Gemma 4.