-
Supporting Materials
- Github: @google-gemini/live-api-web-console
- AI Studio: Native Audio Function Call Sandbox - official product template for building your own
- Google I/O Developer's Keynote (May, 2025)
- Google - The Keyword: Google introduces Gemini 2.0: A new AI model for the agentic era
- Youtube: Building with Gemini 2.0: Native Tool Use
- Social
- John Maeda's SXSW 2025 Design in Tech Report: How AI will turn Designers into "Autodesigners" featured multiple demonstrations [(18:19) | [(49:14)]
- Jeff Dean at AGI House presenting a demo on top of the console
- On I/O Main Stage and vibe coding with p5js by People/Trudy Painter
- 3D Avatars - icosahedron People/Alexander Chen
very cool! when people use LLMs like this repeatedly and with very low latencies like it's some kind of free, persistent, almost disposable resource it gives me the "feel the AGI" feels. — Andrej Karpathy (@karpathy) January 10, 2025
- Launched in December 2024, I worked alongside Deepmind's Gemini team for their upcoming release of the Gemini 2.0 Flash model, part of the release was Google's first low-latency conversational LLM, the "Gemini Live API" and the quick follow-up of a new Unified SDK. As others were focused on python, I was most excited about what conversational AI meant for the web and I knew there were a few complex pieces to work through related to WebSocket management and audio processing.
- Since the initial launch of this project it has had an outsized impact. It has been used in Projects/Gemini Robotics as well as in IO 2025 Demos in the developer keynote and AI sandbox. It is often found at the forefront of where AI finds personality.
- Along with designer People/Hana Tanimura and creative director People/Alexander Chen I began to build what has become one of Deepmind's most popular github repositories.
- Since building this console, numerous demos have been built on top of it. Initially Alex and I produced a few playful demos