# OpenAI says GPT-Live splits talking from thinking

_OpenAI's Aarti says GPT-Live pairs full duplex talk with backend delegation, fixed by SpawnThinking and Decisions triggers._

**Published:** 2026-11-12
**Source:** https://www.startuphub.ai/ai-news/artificial-intelligence/2026/openai-says-gpt-live-splits-talking-from-thinking

---

[OpenAI](https://www.youtube.com/watch?v=5YXlrzC_RYE)'s Aarti said GPT-Live 1 delegates more reliably with a special SpawnThinking token.

She framed GPT-Live as full duplex talk plus delegation to a backend model.

  
    

![Answering your questions about GPT-Live](https://img.youtube.com/vi/5YXlrzC_RYE/maxresdefault.jpg)

    
      
        
      
    
  
  Answering your questions about GPT-Live

Turn-based Realtime had to guess when you finished, so mm-hmms triggered false takeovers and noisy rooms broke it.

For intake needing name, date, time and address, Aarti said to send commentary for the next question and thinking updates that list the full order and block redelegation until confirmation.

Prompting can tell it to ignore side chat.

Aarti played Brise and Sillage, two new French voices, and said custom voices can come from prompt to voice or consented recordings.

Yelp uses it for reservations, Fin for support, Speak for lessons and [Cognition](https://www.startuphub.ai/ai-news/funding-round/2026/cognition-secures-1b-at-26b-valuation-amidst-ai-boom) for Devin voice.

OpenAI notes in release notes voice use in ChatGPT nearly doubled since GPT-Live launched, so keep frontend prompts short, save key facts outside auto compaction and use Decisions triggers to force missed delegation.

---

Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.

© StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.