OpenAI Ships GPT-Live-1.1 for Voice Agents, Cuts Idle Cost to $0

OpenAI Ships GPT-Live-1.1 for Voice Agents, Cuts Idle Cost to $0.02/Min


OpenAI has released GPT-Live-1.1 in its API under the model ID gpt-live-1.1. The new voice model is a full-duplex system for multilingual conversations—it can listen while it speaks. According to the OpenAI team, it delivers more natural and consistent accents across languages and completes tasks more reliably than its predecessor. The release also introduces standby, a cheaper billing state for idle sessions, which meaningfully lowers the cost of idle time for teams running voice agents.


TL;DR


  • Size: Live sessions hold a 128,000-token default context window.
  • Runs on: OpenAI's cloud only, via v1/live/sessions. Clients connect over WebRTC or WebSocket. No open weights and no quantized variants.
  • Performance: OpenAI claims better accents, transcription, letter and number handling, and task completion than GPT-Live-1, though no scores have been published.
  • Best: Standby bills idle WebRTC time at $0.02 per minute versus $0.05 active—a 60% lower rate.
  • Worst: OpenAI published zero benchmark scores for 1.1. Image, video, and structured outputs are not supported.


via MarkTechPost

Related