OpenAI GPT-Live-1.1 voice model
In brief
OpenAI released GPT-Live-1.1 on its API, updating its live voice model with better pronunciation, accent consistency, and transcription across multilingual conversations.
How it works
Pass gpt-live-1.1 into an existing v1/live/sessions configuration to use the updated model. You can describe in plain language within the prompt when the model should delegate tasks to your backend. For WebRTC sessions, you can also configure standby to pause inference during inactivity and resume when someone speaks.
Developers building multilingual voice agents and real-time audio applications on the OpenAI API.
Availability
Sources
4 merged into this cardMore from OpenAI
OpenAI adds standby mode for GPT-Live WebRTC sessions
OpenAI now supports standby configuration for GPT-Live WebRTC sessions, pausing model inference during inactivity and resuming when someone speaks.
Codex: Refreshable OpenTelemetry HTTP Headers
Codex now automatically refreshes authentication headers for OpenTelemetry HTTP exporters, ensuring continuous telemetry without token expiration issues.