Gemini Live API: Get Started With Voice Agents & AI Apps

Build real-time voice and video AI apps and agents using the Gemini Live API. This overview covers the API, speech-to-text, text-to-speech, pipelines, and real-time voice AI. You will learn to use the Live API to generate your first audio.

TIMSTAMPS
00:00 Cold open
00:12: Agents and voice apps with Gemini Live API
00:40 Practical Gemini voice agent demo
01:15 Speech-to-Text/ Text-to-Speech VS Realtime (Speech-to-Speech))
02:06 Gemini Live API: Key Features
02:48 Google AI Studio: Live voice agent demo
04:38 Gemini Live API: Quick Start
09:49 Recap

RELATED LINKS

Build voice agents with Stream: https://getstream.io/video/voice-agents/

Live audio starter app: https://aistudio.google.com/apps/bund...

Live API cookbook: https://colab.research.google.com/git...