How OpenAI built a realtime system for responsive voice AI in six months
Human speakers effortlessly hand off to each other in a fraction of a second, but previous voice AI systems couldn’t keep up with this rhythm. Their turn-based architecture relied on tiny models known as turn detectors, which faced an unenviable task: guess too soon, and the user gets cut off; guess too late, and the response feels sluggish. Only after the detector made its decision could the much larger LLM get to work.GPT‑Live, our third-generation voice system, removes the turn detector from the audio path.
- ▪Human speakers effortlessly hand off to each other in a fraction of a second, but previous voice AI systems couldn’t keep up with this rhythm.
- ▪Their turn-based architecture relied on tiny models known as turn detectors, which faced an unenviable task: guess too soon, and the user gets cut off; guess too late, and the response feels sluggish.
- ▪Only after the detector made its decision could the much larger LLM get to work.GPT‑Live, our third-generation voice system, removes the turn detector from the audio path.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,439 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | OpenAI |
| Canonical URL | https://openai.com/index/continuous-voice-interaction-with-gpt-live/ |
| Publication time | Mon, 03 Aug 2026 22:54:08 +0000 |
| Retrieval time | 2026-08-03T23:05:41.025Z |
| Last seen | 2026-08-03T23:05:41.025Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | cTI5XRnbmnRT · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
August 3, 2026EngineeringHow we built a realtime system for responsive voice AI in six monthsBy Justin Uberti and Zahan Malkani, Members of Technical StaffLoading…ShareMoving from turn taking to streamingMoving from turn taking to streamingEnabling continuous inferenceMaking the media flow quicklyKeeping the (stateful) conversation goingDelegation without blocking the conversationMaking delegation fast enough to feel naturalDeriving discrete turns from continuous speechStarting sessions with a faster protocolSafely testing GPT-Live in production with real dataResponsive, from client to modelMoving from turn taking to streamingEnabling continuous inferenceMaking the media flow quicklyKeeping the (stateful) conversation goingDelegation without blocking the conversationMaking delegation fast…
Excerpt limited to ~120 words for fair-use compliance. The full article is at OpenAI.
Discussion
0 commentsMore from OpenAI
