Morning Edition · Tuesday, August 4, 2026Published at 2:16 AM EDT · New York
OpenAI Details the Full-Duplex Stack Behind GPT-Live, Built in Six Months
The system removes the separate voice-activity detector entirely and trains a speech-native model that listens and speaks at the same time.
OpenAI published an engineering account on August 3 of how it built the realtime system behind GPT-Live, the voice stack it shipped on July 8. The architecture is turnless and full duplex, meaning the model listens and speaks simultaneously…
Continue the AI Intelligence Brief
Track frontier labs, chips, export controls, model releases, regulation, and AI infrastructure.
- 5 AI intelligence signals a day
- Frontier labs, compute, and chips
- Model releases and AI infrastructure
- Source-grounded analysis with confidence labels
The Global Intelligence Brief stays free.
Part of a tracked trend
Speech-Native Models Replace Cascaded Voice Pipelines
Voice AI keeps moving from chained recognition, reasoning and synthesis components toward single models trained directly on audio, compressing latency and displacing the vendors that sell the individual stages.
More from this edition
- Alibaba Ships Qwen3.8-Max at 2.4 Trillion Parameters and Promises the Weights Next Week
- OpenAI Publishes Lean-Checked Proofs for Ten Open Mathematics Problems From an Unreleased Model
- OpenAI Publishes Internal Messages to Rebut Apple's Trade-Secret Suit
- Tencent's Hyra Agent Claims Record Results on 29 of 55 Open Mathematics Problems
- An Open-Source Runtime Streams Mixture-of-Experts Weights From SSD to Run an 80-Billion-Parameter Qwen on a Mac
- Meta Sells Its Best Model by the Token After Years of Giving Weights Away
- New Papers Push Back on Paying Frontier Prices to Grade Model Output
- Meta's Segmentation and Vision Models Move Into Assistive Robotics and National Laboratory Science
- Researchers Propose an Executable Benchmark for the Decisions Agents Make Before They Answer
- Agent Tooling Turns Toward Traces and Verified Skill Claims
- OpenAI Publishes a Telco Deployment With Revenue Numbers Attached
Comments
0No comments yet.