OpenAI adds standby mode for GPT-Live WebRTC sessions
In brief
OpenAI now supports standby configuration for GPT-Live WebRTC sessions, pausing model inference during inactivity and resuming when someone speaks.
How it works
You can configure standby mode on GPT-Live-1 and GPT-Live-1.1 WebRTC sessions. The configuration pauses active inference during silent periods. It automatically resumes processing as soon as speech is detected.
Developers building real-time voice applications using OpenAI's Live API.
Availability
Sources
4 merged into this cardMore from OpenAI
OpenAI GPT-Live-1.1 voice model
OpenAI released GPT-Live-1.1 on its API, updating its live voice model with better pronunciation, accent consistency, and transcription across multilingual conversations.
OpenAI Codex Security Plugin Demo
OpenAI released a video demonstration covering the setup, workflow, and result review process for the Codex Security Plugin.