GPT-Live-1.1: OpenAI's full-duplex voice model reaches the API with cheaper standby
OpenAI's full-duplex voice model is now available through the API, with a standby mode that bills idle WebRTC time at $0.02/min instead of $0.05.
Why it matters
Voice agents can now stay connected through long silences at 60% lower idle cost, without dropping and rebuilding the conversation.
What you could build with it
A telehealth startup could build a voice-first intake agent that listens while patients speak, interrupts politely to clarify symptoms, and idles cheaply at $0.02/min while patients pause to find documents.
Does it hold up?
Too early to judge for the standby path, which is brand new; the voice model itself has powered ChatGPT voice since 15 Oct, so the conversation quality is proven.
Built with GPT-Live-1.1
- OpenAI GPT-Live just made silence 60% cheapermedium · Hands-on guide to the standby mode with a working ASP.NET Core sample, wake_policy and idle_timeout configuration, and the cost math.
- GPT-Live-1.1 pricing: OpenAI reduces standby costs by 60%article · Breakdown of the $0.02 standby vs $0.05 active rates, the 5-60 second idle timeout, and WebRTC-only applicability.
- GPT-Live-1.1 launches with full-duplex voice AIarticle · Launch coverage: simultaneous speaking and listening, sub-200ms response initiation, and 12 supported languages.
- mikhailpetrusheuski/gpt-live-standby-aspnetcoregithub · ASP.NET Core sample wiring GPT-Live standby sessions with configurable wake policy and idle timeout, from the Medium guide.
Learn more
First spotted on article: source.
More AI models
MiniMind: train your own 64M LLM from scratch in about 2 hoursA complete, from-scratch LLM training pipeline at 64M parameters - pretraining, SFT, LoRA, DPO, PPO/GRPO, tool use and…models · JEV 0.82VoiceStudio: the open-source, fully-local ElevenLabs alternativeA desktop app bundling 20 local speech-generation engines and 10 transcription options behind one UI — voice cloning…models · JEV 0.76Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73tiny-voca: a fully open 4.5M-parameter TTS trained for under $10 of computeA fully open 4.5M-parameter English TTS — code, weights and dataset under Apache 2.0 — trained from scratch in 7.7…models · JEV 0.67Qwen4-Max: Alibaba's new flagship model goes liveAlibaba's 2.4T-parameter flagship is now generally available via API, with a 1M-token context, native vision, and…models · JEV 0.67
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.