walkie-talkie
A **dual-model voice agent**: press to talk, the front-end handles the conversation, the background does the work.
Core trick
A realtime voice model keeps talking while background agents run tool calls in a sandbox and push results back mid-conversation.
Description
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.
README excerpt
# GeniusOS A real-time thinking partner orchestrating a dual model setup of `gpt-realtime-2` and Codex. It pairs a live voice interaction model with parallel background agents that handle tool calling, code execution, and generative UI, so the conversation never stops while work happens behind the scenes. ## Why users need this Today, using an AI agent means watching it work. You prompt, you wait, you read, you prompt again. Voice doesn't fix this if it's still turn-based. What people actually want is to think out loud while things get done. GeniusOS lets you talk through a problem, ask for a chart, pivot to a different question, request a code change, all in one continuous conversation, while each task runs in the background and results surface as they complete. ## The architecture When Thinking Machines released their interaction model, I recognized the same architecture I'd been building independently. Their thesis: for interactivity to scale with intelligence, it must be part of the model itself. I don't fully agree. Model plus harness becomes a powerful, collaborative agent. These are two means to the same end. Interactivity is a type of user experience, and as long as users get that experience, it doesn't matter whether the system uses a full-duplex model or cascaded scaffolding. GeniusOS proves this with OpenAI's realtime voice stack. `gpt-realtime-2` handles the hard interaction problems (sub-230ms responses, pause detection, mid-sentence pivots, simultaneous lis