Almost 80% fewer interruptions during thinking pauses, in early evaluations. That is Speak's number, a language-learning app, and it isn't about speed. The voice tutor talks over you far less often while you are still thinking.
Anyone who has learned a language by voice with a machine knows the problem. You pause to find the word, and it is already answering. For the machine, silence is the end of a sentence.
Fact
The facts: on 10 September 2026 OpenAI launched GPT-Live-1 in the API, a voice model first introduced in ChatGPT that listens and speaks at the same time. It handles incoming and outgoing audio in a single model rather than a chain of speech recognition, language model and synthesis, and can delegate reasoning and tool calls to a model behind it, for example GPT-6 Astra or a third-party model. It supports telephony, setting tone, pace and style through the system prompt, better handling of background noise and silence, and long sessions. The price is $0.05 per minute for the voice layer. Per OpenAI, GPT-Live-1 improves Full Duplex Bench performance by 30 percentage points over GPT-Realtime-2.1. The company quotes Speak, which says that in early evaluations, with its language tutor, interruptions during thinking pauses fell by almost 80% compared with previous turn-based systems. The choice of voices has been expanded across accents, dialects and languages, with more languages promised over the coming months.
Full duplex, in plain words
Until now voice agents worked like a two-way radio: you talk, release the button, it talks. Full duplex is the telephone. Both of you can speak at once, interrupt each other, say "uh-huh" in the middle of the other person's sentence, without the conversation falling apart.
Conversation is also knowing when to be quiet.
The clever part is the split. The voice model keeps the conversation alive while the heavy thinking can go to another model at the back. So you can put a lighter model on booking an appointment and a heavier one on a complex problem.
The benchmark numbers are OpenAI's. The price of $0.05, that is 5 cents a minute, is for the voice only; the model at the back is paid separately and its bill depends on how much it thinks.
If you are building a voice assistant for customers in your own language, first check whether that language is supported. Then test not the speed but how patient it is when the person on the other end is searching for a word.
Official primary sources
OpenAI - Build more natural voice experiences with GPT-Live-1 in the API, 10.09.2026The visual is generated code-art, no third-party images.