On November 19 OpenAI made its full-duplex voice model GPT-Live-1.1 available in the API (model ID gpt-live-1.1 on v1/live/sessions). It has powered voice in ChatGPT Plus and Pro since October 15 and, compared with GPT-Live-1, transcribes more accurately, keeps accents and voice more consistent across languages, and lets developers describe in plain language when to delegate to a backend model. OpenAI also added Standby: after 5 to 60 seconds of silence a WebRTC session pauses inference and is billed at $0.02 per minute instead of $0.05 until someone speaks again.
Key Takeaways
- ✓Official: announced by @OpenAIDevs on November 19, logged in the OpenAI developer changelog the same day, with a model page at developers.openai.com/api/docs/models/gpt-live-1.1
- ✓Capabilities: full duplex, listens while it speaks; versus GPT-Live-1 it transcribes more accurately, keeps accent and voice more consistent across languages, and reliably catches precise details such as letters and numbers
- ✓Delegation: describe in plain language in the session configuration when to hand reasoning or tool use to a backend model of your choice without breaking the conversation
- ✓Standby: WebRTC sessions on GPT-Live-1 and 1.1 can set a 5 to 60 second idle timeout; while paused they bill at $0.02 per minute and resume when someone speaks
- ✓Pricing: billed by session duration at $0.05 per active minute, not rounded up to the next minute; backend model and tool usage are billed separately, and the two models have separate concurrent-session limits

Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Voice agents for support, phone and companion apps often hold connections open for long stretches that are mostly silence yet billed at full rate, and multilingual sessions suffer from accent drift and misheard letters and numbers. OpenAI is opening GPT-Live-1.1, which has powered voice in ChatGPT Plus and Pro since October, to API developers and adding a Standby mode aimed at idle cost.
How it works
GPT-Live-1.1 is a full-duplex voice model with audio and text input and output that listens while it speaks. It runs on the v1/live/sessions endpoint with streaming and function calling. Developers describe in plain language in the session configuration when the model should hand complex work to a backend model for reasoning or tool use, without breaking the flow of conversation. Standby is a new session setting for GPT-Live-1 and GPT-Live-1.1 WebRTC sessions: set an idle timeout of 5 to 60 seconds, after which the model pauses inference while the call stays open, resuming when someone speaks.
Benchmarks
OpenAI published no benchmark scores this time, only qualitative claims: versus GPT-Live-1 it transcribes more accurately, keeps accents and voice more consistent across languages, and completes tasks more reliably. Pricing is explicit: $0.05 per active minute and $0.02 per standby minute, with session duration not rounded up, and backend model and tool usage billed separately.
What developers should do
Existing Live session integrations can switch the model to gpt-live-1.1 and spell out delegation rules in the prompt. Long-running phone or support calls can enable Standby to cut idle cost. GPT-Live-1.1 and GPT-Live-1 have separate concurrent-session limits, so check your organization's limits page before rolling out.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.