What happened
OpenAI says GPT-Live-1.1, which has powered voice in ChatGPT Plus and Pro since October 15th, can now power developers' apps. OpenAI says developers can use it to build voice agents that understand details such as letters and numbers, follow instructions, and delegate complex workflows to a backend model of their choice.
Why it matters
GPT-Live-1.1 extends voice from ChatGPT Plus and Pro to app developers, who can use it to build agents that handle precise details, follow instructions, and delegate workflows to a backend model of their choice.
Sound familiar? GPT-Live-1.1 has powered voice in ChatGPT Plus and Pro since October 15th. Now it can power your apps.
Build better voice agents that can reliably understand precise details like letters and numbers, follow instructions, and delegate complex workflows to the backend model of your choice without breaking the flow of conversation.
3 reports
The story so far
OpenAI has made GPT-Live-1.1 available in its API and added a Standby configuration for managing inactivity in the GPT-Live API. Available for both GPT-Live-1 and GPT-Live-1.1, Standby lets developers set an idle timeout of 5–60 seconds; after that period of silence, the model temporarily pauses while the WebRTC call stays open at $0.02 per minute, compared with the standard $0.05, until someone speaks again. GPT-Live-1.1 has powered voice in ChatGPT Plus and Pro since October 15, OpenAI said. The company said the model speaks with more natural and consistent accents across languages, completes tasks more reliably, and allows developers to build voice agents that understand details such as letters and numbers, follow instructions, and delegate complex workflows to a backend model of their choice.
