youtube
*Build a real-time voice agent with Gemini 3.1 Flash Live and Stream's Vision Agents SDK.*
Stefan Blos, Senior Developer Advocate at Stream, walks through what's possible with early access to the Gemini 3.1 Flash Live model: object detection, AI image polish with Nano Banana, web search, and a guided multi-step workflow, all driven by a single voice conversation.
*What's covered:* Setting up the Vision Agents SDK with the Gemini plugin, defining tools for image generation and product search, building a video processor to analyze live frames, orchestrating multi-step agent workflows with instruction following, and connecting everything to a Next.js frontend via WebSocket events.
Grab your Gemini API key at Google AI Studio and explore the Vision Agents SDK from Stream to get started.
*Resources:*
✅Gemini Hacker Starter Repo →
✅GitHub examples →
✅Stream SDK →
What are you building with Gemini Live? Drop it in the comments.
Subscribe to Google for Developers →
Speaker: Stefan Blos at Stream
Products Mentioned: Google AI, Gemini
|
2026/03/27
youtube
![Tableau Full Course 2026 [FREE] | Tableau Data Visualization Course | Tableau Tutorial | Simplilearn](https://i.ytimg.com/vi/lvYiNAbrrys/sddefault.jpg)
![Social Media Marketing Full Course 2026 [FREE] | Social Media Marketing Tutorial | Simplilearn](https://i.ytimg.com/vi/HfFIjL6Jfa0/sddefault_live.jpg)
![AI for Business Full course in 11 Hours [ 2026] | How AI Could Empower Businesses | Edureka Live](https://i.ytimg.com/vi/cG1W_AgYRRo/sddefault.jpg)
