OpenAI Launches Full-Duplex Speech Model
智东西 · wechat · 2026-07-09
OpenAI has launched GPT-Live, its first full-duplex real-time speech model capable of listening and speaking simultaneously, available in two versions: GPT-Live-1 and GPT-Live-1mini. It can listen, think, and respond while the user is still talking, supporting interruptions, additions, and follow-up questions for a conversational rhythm that feels much closer to a real human.
The model also decouples real-time conversation from deep reasoning: GPT-Live handles the voice interaction, while complex searches and reasoning are processed in parallel by a backend model, GPT-5.5. Currently, GPT-Live is live on the ChatGPT App and web, with API access rolling out later.
Related event: OpenAI Launches GPT-5.6, ChatGPT Work, and Desktop App Overhaul(136 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11