GPT-Live API adds Standby mode for idle voice sessions
Idle time is often the hidden cost driver in voice agent deployments, and halving-plus the per-minute rate during silence changes the economics of long, real-world calls with pauses. Teams running voice assistants or phone-based agents on GPT-Live should review their timeout settings to balance cost savings against session persistence. Compared with tearing down and re-connecting WebRTC sessions on every pause, this keeps context intact while trimming the bill.
OpenAI introduced Standby, a new configuration in the GPT-Live API that lets developers manage periods of user inactivity without ending a live voice conversation. The feature is available for both GPT-Live-1 and GPT-Live-1.1.
Developers can set an idle timeout between 5 and 60 seconds. When no one speaks for that period, the model temporarily pauses while the underlying WebRTC call remains open at a reduced rate of US$0.02 per minute, compared with the standard US$0.05 per minute, until someone speaks again and the conversation resumes.
The update targets a common pain point in voice agents: paying full per-minute rates while users think, search for information, or step away. For developers building customer-service bots, voice assistants, or call-centre integrations on GPT-Live, Standby cuts idle costs by 60% while keeping sessions alive, removing the need to drop and re-establish calls during natural pauses.
Standby is a new configuration in the GPT-Live API that lets developers manage periods of inactivity without interrupting the conversation. It's available for both GPT-Live-1 and GPT-Live-1.1. Set an idle timeout of 5-60 seconds. After that period of silence, the model temporarily pauses, but the WebRTC call stays open at a lower rate ($0.02 per minute vs. the standard $0.05) until someone speaks again.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include GPT-Live, OpenAI, WebRTC.
Primary source verification: published directly by @OpenAIDevs with first-party authority.