
10 Sep 2026
OpenAI launches GPT-Live-1 in the API
10 Sep 2026: a full-duplex voice model for developers. OpenAI prices the voice layer at $0.05 a minute. Listen and speak at once, take interruptions, and hand reasoning to a backend agent. That is the product.
10 Sep 2026: OpenAI published “Build more natural voice experiences with GPT-Live-1 in the API.” The same day’s API changelog listed gpt-live-1 as generally available on v1/live/sessions.
OpenAI: GPT-Live-1 is a full-duplex voice model. It can listen and speak at the same time. Interruptions are handled in one model, not a chained speech-to-text / LLM / text-to-speech stack.
Price on the launch post and the model card: $0.05 per minute for the front-end voice layer, billed per second. Backend model and tool usage is charged separately.
Developer docs: the voice model can delegate reasoning and tool use to a backend agent — a managed Responses model, or the app’s own agent via client delegation. Interrupting speech does not automatically cancel that backend work.
This is a developer product announcement, not a consumer ChatGPT update. The Speak “almost 80% fewer interruptions” line and the Full Duplex Bench gains are OpenAI’s customer and lab numbers. This desk did not rerun them.
A dated API launch for full-duplex voice, with a public price. The interruption and bench claims stay OpenAI’s.
Sources
- OpenAI — Introducing GPT-Live-1 in the API
openai.com
- OpenAI Developers — GPT-Live 1 model
developers.openai.com
- OpenAI Developers — Changelog (Sep 2026)
developers.openai.com
- OpenAI Developers — Getting started with GPT-Live
developers.openai.com
- OpenAI Developers — Delegation and tools in GPT-Live
developers.openai.com



















