# walkie-talkie

- **Event:** [Google I/O Hackathon](https://cerebralvalley.ai/e/google-io-hackathon)
- **When:** Sat, May 23 at 9:00 AM – 10:00 PM (PDT)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Lily Zhang](https://cerebralvalley.ai/u/lilyzhng)
- **GitHub:** https://github.com/lilyzhng/walkie-talkie
- **Demo video:** https://www.youtube.com/watch?v=nkG2ME7mrAc
- **Gallery:** https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery/69

A **dual-model voice agent**: press to talk, the front-end handles the conversation, the background does the work.

1. **Front-end model** handles real-time voice interaction (listen, speak, pivot mid-conversation)
2. **Background model** handles tool execution in a persistent sandbox (files, charts, generative UI)

LLM products today split into two camps: **full-duplex** (live voice) and **turn-based** (chat + tools). One is great at talking, the other is great at doing. Nothing sits in between.

Walkie-Talkie stitches both: natural real-time voice up front, powerful tool execution in the back. Gemini 3.5 Flash as the background brain keeps latency low.

---

Markdown version of https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery/69. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt