Contents
- 1. What is GPT-Live — the "listen while speaking" full-duplex voice
- 2. How it differs from the old Advanced Voice Mode
- 3. How it works — per-second decisions and delegation to GPT-5.5
- 4. Two models and availability by plan
- 5. The main advances
- 6. Current limitations — worth being honest about
- 7. Where it shines
- 8. API availability and how it differs from GPT-Realtime
- Summary
- FAQ
On July 8, 2026, OpenAI released "GPT-Live", a new model that overhauls the voice experience in ChatGPT worldwide (OpenAI's official announcement). Announced just ahead of the general availability of GPT-5.6 the following day, its headline feature is a full-duplex architecture that lets it "listen and speak at the same time."
Until now, AI voice has been turn-based: "it waits for you to finish talking, then responds." GPT-Live, by contrast, behaves like a human conversation partner — it backchannels, absorbs interruptions, and doesn't cut off the silences while you think. In this article we explain, based on the official announcement, what GPT-Live is, how it differs from the old Advanced Voice Mode, how it works, which plans can use it, and what it still can't do.
The end of turn-taking
— toward human-like conversation that listens while it speaks
1. What is GPT-Live — the "listen while speaking" full-duplex voice
GPT-Live is a new series of voice models that powers voice conversations in ChatGPT. Replacing the previous voice feature (Advanced Voice Mode), it rolled out worldwide to ChatGPT on iOS, Android, and the web starting July 8, 2026.
Its core is a "full-duplex" design. Like a phone call, it keeps generating output (the AI's voice) while it processes input (your voice) at the same time. Because of that —
- It can offer backchannels like "mhmm" and "yeah" while you're still talking
- If you interrupt mid-sentence, it actually listens and changes course while it's speaking
- If you fall silent to think, it doesn't mistake that for "you're done" and cut you off
In short, GPT-Live delivers real-time conversation with no "waiting your turn."
2. How it differs from the old Advanced Voice Mode
The previous AI voice (Advanced Voice Mode) was turn-based (half-duplex). By design, it had these weaknesses.
| Aspect | Old: Advanced Voice Mode | New: GPT-Live |
|---|---|---|
| Basic method | Turn-based (half-duplex) — waits for you to finish | Full-duplex — speaks while listening at the same time |
| Detecting the end of a turn | Based on silence | Judges from tone of voice and shifts in breathing |
| Thinking pauses | Tends to mistake them for "done" and interrupt | Waits without cutting in |
| Backchannels | Essentially none | Returns "mhmm," "yeah," and the like |
| Interruptions | Can cut off unnaturally | Absorbs them and adjusts |
| Decision frequency | Per turn | Multiple times per second (speak / listen / pause / interrupt / call a tool) |
According to OpenAI, in a comparison where humans evaluated 5-to-10-minute conversations under the same conditions, both GPT-Live-1 and GPT-Live-1 mini were clearly preferred over Advanced Voice Mode. Improvements were also reported on GPQA (expert-level scientific reasoning), BrowseComp (agentic web search), and customer-support-style tasks.
3. How it works — per-second decisions and delegation to GPT-5.5
GPT-Live generates voice output while continuously processing voice input, and decides "what to do right now" many times per second — speak, keep listening, pause, interrupt, or call a tool. This high-frequency decision-making is what produces the human-like tempo.
Another key part of the design is that "deep processing is delegated to a model behind the scenes." GPT-Live handles the responsiveness of the conversation, and when web search, deep reasoning, or complex work is needed, it hands the task off to a larger model behind the scenes (GPT-5.5 at launch), then returns to the conversation once results come back. It's a mechanism that combines "thinking" with an uninterrupted conversation.
4. Two models and availability by plan
| Plan | Default voice model |
|---|---|
| Free | GPT-Live-1 mini |
| Go / Plus / Pro | GPT-Live-1 |
The key point is that even the free plan can use the mini version of GPT-Live. Natural full-duplex conversation isn't limited to paid tiers. If you want higher-quality conversation and reasoning, GPT-Live-1 is the default on Go/Plus/Pro. It's available on ChatGPT for iOS, Android, and ChatGPT.com, rolled out in stages worldwide.
5. The main advances
Responds with "mhmm" while you're talking. It creates the sense of being heard.
Responses are near-instant. The tempo comes close to a human conversation.
Even if you cut in mid-conversation, it listens and course-corrects.
It doesn't misjudge a thinking pause as "you're done" — it waits for you.
6. Current limitations — worth being honest about
Expectations can run ahead of reality, so it's worth being honest about what it can't do at launch.
- 🟡 No video or screen sharing yet: at launch it's voice-centric, and video input and screen sharing aren't included.
- 🟡 Full multilingual support is still to come: it hasn't yet reached the same level of quality across all languages (full multilingual parity is not there yet).
- 🟡 No API yet: a developer API is "coming soon," and as of this writing it's unreleased with no announced pricing (see chapter 8).
- 🟡 Staggered rollout: it may take time to reach all users.
These are expected to expand in future updates, but it's good to understand that "video and screen sharing right now" is not on the table.
7. Where it shines
- Hands-free consulting and thinking out loud: organize your thoughts by voice while walking or working. Because your silences aren't cut off, your train of thought is less likely to break.
- Language conversation practice: with backchannels and natural interruptions, you get practice that's closer to a real conversation.
- Research and summarizing by voice: deep search is delegated to GPT-5.5 behind the scenes, so you can look things up while you talk.
- Accessibility: in situations where typing is hard, a snappy voice interface helps.
8. API availability and how it differs from GPT-Realtime
The GPT-Live API is not available as of this writing ("coming soon," no pricing announced). Developers and businesses will have to wait by signing up for notifications. Note that "embedding full-duplex voice into your own app right now" still isn't possible.
Summary
- GPT-Live is a new model that changes ChatGPT's voice from "turn-based" to full-duplex (listening while speaking) (July 8, 2026, worldwide).
- With backchannels, interruption handling, and tolerance for silence plus latency <250ms, it achieves a conversational tempo close to a human's. It was clearly preferred over Advanced Voice Mode.
- GPT-Live handles conversational responsiveness, while deep reasoning and search are delegated to GPT-5.5 behind the scenes (choose the depth with Instant/Medium/High).
- Free defaults to GPT-Live-1 mini, and Go/Plus/Pro to GPT-Live-1. Available on ChatGPT for iOS/Android/web.
- Current limitations: no video or screen sharing, full multilingual support not yet reached, and no API. For the API, GPT-Realtime-2.1 is provided separately.
FAQ
Q1. Can I use GPT-Live for free?
Yes. On the free plan, GPT-Live-1 mini is the default voice model. On Go/Plus/Pro, the higher-end GPT-Live-1 is the default. It's available on ChatGPT for iOS, Android, and web (staged rollout).
Q2. What exactly is "full-duplex"?
It's a method that can listen and speak at the same time, like a phone call. Unlike the old turn-based approach (waiting for you to finish before responding), it can return backchannels while you're talking, absorb interruptions, and wait through your thinking silences without cutting in.
Q3. What's the single biggest difference from the old Advanced Voice Mode?
How it detects the end of a turn. The old approach was silence-based, so it tended to mistake a thinking pause for "done" and interrupt. GPT-Live judges from tone of voice and shifts in breathing and makes decisions many times per second, so it's less likely to cut you off and feels more natural. It's also clearly preferred in human evaluations.
Q4. Can it answer difficult questions?
Yes. GPT-Live handles conversational responsiveness, and when web search or deep reasoning is needed, it delegates the processing to GPT-5.5 behind the scenes and brings the results back into the conversation. You can choose the depth of reasoning from Instant / Medium / High.
Q5. Can it do video or screen sharing?
Not at launch. GPT-Live is voice-centric; video, screen sharing, and full multilingual support are currently not provided. Expansion is expected in future updates.
Q6. Can I integrate it into my own app via API?
The GPT-Live API is not available as of this writing (coming soon, no pricing announced). If you want to implement low-latency voice via API right now, consider the separate GPT-Realtime-2.1 / mini (a voice-agent foundation for the API). GPT-Live is consumer-facing while GPT-Realtime is for developers — the roles are split.
Q7. How does it compare to Google's Gemini Live?
Gemini's strength is also multimodal, including voice and video, and it supports live conversation. GPT-Live's current strength is the naturalness of full-duplex conversation and low latency, but since video and screen sharing aren't supported yet, there are areas where Gemini has the edge. For more, see the GPT-5.6 vs Gemini comparison.
Related articles
- GPT-5.6 Release: Complete Guide — the leading models of the same period
- GPT-5.6 Sol vs Gemini — the multimodal/voice comparison axis
- What is Google Gemini — the basics of the competitor
