OpenAI Announces GPT-Live: Full-Duplex Voice Model for Natural Conversation Experience
Digests in this section are compiled by an automated pipeline; sources are listed at the end of each post. Posts are removed after 7 days.
OpenAI today announced GPT‑Live, a next-generation voice model designed to make talking with AI feel like having a real conversation.
GPT‑Live is built on a full-duplex architecture, meaning it can listen and speak at the same time. During conversations, GPT‑Live can show it’s paying attention with phrases like “mhmm” or “yeah”, engage in quick back-and-forth, or just stay quiet when you need a moment to think. The result is a voice experience that feels refreshingly natural.
GPT‑Live is also OpenAI’s smartest voice model yet. For questions that require web search, deeper reasoning, or more complex work, it delegates to OpenAI’s latest frontier model behind the scenes and brings the result back into the conversation when ready. While it works, GPT‑Live can keep talking with you and maintain the flow of conversation.
At launch, GPT‑Live will use GPT‑5.5 in the background. As OpenAI releases new frontier models, they will continuously update the model used by GPT‑Live.
These advances power a new ChatGPT Voice experience that is more intelligent and natural to use. Over time, this research is expected to unlock the ability to use voice for increasingly complex, longer-running, and more agentic work.
OpenAI is beginning to roll out two versions of GPT‑Live – GPT‑Live‑1 and GPT‑Live‑1 mini – to ChatGPT users globally. They also plan to bring them to the API soon, and developers and enterprises can sign up to be notified.
Older generations of voice AI systems brought us closer to that vision, but with important tradeoffs. Cascaded voice systems relied on a series of models acting one after another to process each turn. The original ChatGPT Voice chained three models together: a speech-to-text model to transcribe speech, a large language model to produce a response, and a text-to-speech model to convert back to speech. This approach enabled talking to frontier AI models for the first time, but the complexity came at a cost: information could be lost across models, and responses were slow and stilted.
Turn-based voice models like ChatGPT Advanced Voice Mode processed and generated audio within a single model, reducing latency and making conversations smoother—but they still operated through discrete turns. The model had to wait for the user to stop speaking before responding, resulting in rigid back-and-forth.
GPT‑Live addresses these limitations through two architectural changes.
First, OpenAI built GPT‑Live for continuous interaction using a full-duplex architecture. Instead of processing a sequence of separate messages, GPT‑Live continuously processes input while generating output. The model can therefore make interaction decisions many times per second: whether to speak, continue listening, pause, interrupt, or invoke a tool.
Second, they decoupled GPT‑Live—which handles continuous interaction—from deeper work. When a question requires search, reasoning, or more agentic capabilities, GPT‑Live can delegate the task to another model like GPT‑5.5. This allows it to keep the conversation going, even as it handles multiple tasks in the background.
Human evaluations show that GPT‑Live‑1 and GPT‑Live‑1 mini are strongly preferred over Advanced Voice Mode in matched conversations measuring overall preference, turn-taking, interruptions, conversational flow, and how natural each interaction felt.
GPT‑Live‑1 substantially outperforms Advanced Voice Mode on GPQA, which tests expert-level scientific reasoning across biology, chemistry, and physics. It also shows strong gains on BrowseComp, which tests agentic web search and the ability to find difficult-to-locate information. GPT‑Live‑1 outperforms Advanced Voice Mode on τ³-Voice Telecom, which tests voice agents on realistic, multi-turn telecom support tasks.
GPT‑Live‑1 (instant) and GPT‑Live‑1 mini use the GPT‑5.5 Instant model in the background, while GPT‑Live‑1 Medium and GPT‑Live‑1 High use the GPT‑5.5 Thinking model with medium and high reasoning effort.
Each week, more than 150 million people talk to ChatGPT using features like Voice and Dictation. They use it to get hands-free everyday help, to practice languages, tell bedtime stories, or just chat during their commute.
Starting today, when you tap the Voice button to talk with ChatGPT, you’ll get an improved experience powered by GPT‑Live—with more natural conversations, smarter answers, better listening, and visual responses.
Talking with ChatGPT should now feel much more like a real conversation. You can interrupt with a question, pause to gather your thoughts, or ask ChatGPT to slow down. It naturally acknowledges what you’re saying with phrases like “mhmm” or “got it,” so you know it’s following along.
ChatGPT Voice can now draw on the latest frontier models, giving you smarter answers when you need them. You can also choose the level of reasoning that fits your needs: Instant for fast responses, or Medium and High when you want ChatGPT to spend more time thinking.
GPT‑Live was designed to be safe by default. It builds on the safety advances from the latest models while adding dedicated safety training across key risk areas and new safeguards designed specifically for voice.
Because voice conversations unfold in real time, OpenAI also built safeguards that can act while the model is speaking. When the system detects potentially unsafe output, it can steer the model toward a safer response, surface additional safety messaging or resources, or end the voice conversation in higher-risk cases.
GPT‑Live is rolling out now to ChatGPT users globally across iOS, Android, and ChatGPT.com. GPT‑Live‑1 will become the default model powering ChatGPT Voice for Go, Plus, and Pro users, and GPT‑Live‑1 mini will become the default for Free users.