GPT‑Live‑1 in the API
OpenAI has launched GPT-Live-1 in its API, introducing full-duplex voice capabilities for developers. This model allows for more natural, interruptible voice interactions in applications.
Why it matters
Advancements in full-duplex AI voice models significantly lower latency and improve the user experience for voice-enabled business and educational tools.
GPT‑Live‑1 brings ChatGPT’s natural, full-duplex conversations to the API, with more control over how voice agents speak and act.
Share Simplify your voice-agent architecture and reduce voice latency Simplify your voice-agent architecture and reduce voice latency Measuring the full-duplex advantage What customers are saying New voice options Pricing & Availability Simplify your voice-agent architecture and reduce voice latency Measuring the full-duplex advantage What customers are saying New voice options Pricing & Availability We’re launching GPT‑Live‑1 in the API, giving developers a powerful, natural voice model for building voice-enabled apps and business workflows. First introduced in ChatGPT , GPT‑Live‑1 is capable of listening and speaking at the same time, and, as seen with Codex and ChatGPT Work (opens in a new window) , can delegate deeper reasoning and actions to the models and tools it is paired with.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in