Build a voice agent with Gemini 3 Flash Live and LiveKit.
Jesse Hall from LiveKit walks through everything you need to get a working voice agent running locally, then take it to production. Speech-to-speech audio, no text in the middle, with better instruction following, smarter tool calling, and reduced speaker drift across long sessions.
What's covered: Project setup with LiveKit Agents and the Google plugin, system prompt best practices for voice, native audio capabilities, server-side and client-side tool calling, Google Search integration, and live testing with multilingual switching and function chaining.
Grab your Gemini API key at Google AI Studio and your LiveKit credentials at cloud.livekit.io to get started.
Resources:
✅Livekit Gemini Playground →
✅Gemini Hacker Starter Repo →
✅GitHub examples →
What are you building with Gemini Live? Drop it in the comments.
Subscribe to Google for Developers →
Speaker: Jesse Hall from LiveKit
Products Mentioned: Google AI, Gemini
|
🔥AI-Powered Digital Marketing Certificat...
AWS Security Hub Extended: Full-Stack En...
Gemini 3.1 Flash Live lets you build age...
🔥Data Analyst Masters Program (Discount ...
🔥Generative AI, Machine Learning, And In...
*Build a real-time voice agent with Gemi...
In this #Shorts video on Best Job Platfo...
🔥AI-Powered Digital Marketing Certificat...
Experian's Data Office (UK&I) needed to ...
Moments Lab specializes in video underst...
Cochlear, a global leader in implantable...
Audible engineers were losing hours ever...
Security leadership has never been just ...
Simplify your design challenges with Sti...
📌Generative AI Course: Masters Program :...