# OpenAI describes GPT-Live's turnless speech model and low-latency architecture

> An engineering write-up on GPT-Live, which supports continuous voice interaction using a turnless speech model and a low-latency architecture. The source describes the system but names no API surface, availability, or pricing.

| | |
|---|---|
| **Tool** | OpenAI |
| **Version** | — |
| **Kind** | announcement |
| **Published** | 2026-08-03 |
| **Observed** | 2026-08-11 |
| **Significance** | 3/5 |
| **Breaking** | no |
| **Categories** | capability, docs |

> **Note:** this classification is below our confidence threshold and is pending human review.

## What changed


- GPT-Live supports continuous voice interaction rather than turn-taking
- Uses a turnless speech model
- Low-latency architecture for faster conversational response
- Built over roughly six months; no API or availability detail in source


## Sources

- [blog_rss](https://openai.com/index/continuous-voice-interaction-with-gpt-live) — retrieved 2026-08-11


## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/openai/openai-describes-gpt-live-s-turnless-speech-model-and-low-latency-architecture
Entity: https://changelogs.info/openai
Event ID: `evt_2026-08-03_openai_how-we-built-a-realtime-system-for-responsive-voice-ai-in-six-months`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.