TellWorldAI World Archive
Ask中文
News
Models
Organisations
People
Papers & concepts
Products & agents
Chips & robots
History
Topics
Ask中文

Home›Models

Model

GPT-Live-1

GPT-Live-1 is OpenAI's full-duplex voice model family, launched 8 July 2026, which lets ChatGPT listen and speak at the same time and replaced the earlier chained speech pipeline in ChatGPT Voice.

Status AvailableModality Text, Audio Era Generative AI for everyone

License
Proprietary
Access
API, App
Release date
Developer
OpenAI

What GPT-Live-1 is

GPT-Live-1 is a family of voice models from OpenAI with two members: the larger GPT-Live-1 and the smaller GPT-Live-1 mini. OpenAI launched the family on 8 July 2026 to power ChatGPT Voice[1][4].

Where it comes from

Before GPT-Live, ChatGPT Voice was built as a chain of three models: a speech-to-text model turned what the user said into text, a large language model wrote the reply, and a text-to-speech model read that reply out loud[6]. Each stage has to wait for the one before it, so the conversation falls into strict turns: the user speaks, the system waits, the system speaks.

In July 2026, OpenAI deprecated its earlier realtime and audio models, such as gpt-realtime and gpt-4o-realtime[5].

How it works

GPT-Live uses a full-duplex architecture, meaning it can listen and speak at the same time, so interruptions are handled more naturally[1][2]. According to OpenAI, the model can show it is paying attention with phrases like "mhmm" or "yeah", keep up with quick back-and-forth, or stay quiet while the user is thinking[6].

When a request needs deeper thinking, the voice model hands it to a reasoning model — GPT-5.5 at launch — and keeps talking while that model works[1]. The user does not sit through a long silence while the system works out an answer.

Rollout in ChatGPT

Inside ChatGPT, GPT-Live-1 mini replaced Advanced Voice Mode as the default voice model, while paid plans got the larger GPT-Live-1[1]. At launch the model did not support video or screen sharing in ChatGPT[1].

In OpenAI's own tests, people preferred GPT-Live-1 in 75.7% of comparisons and GPT-Live-1 mini in 69.2%[1].

Watermarking and the API

On 31 July 2026, OpenAI began adding SynthID watermarking to supported audio generated with GPT-Live through ChatGPT Voice and the API, and opened API access for provenance verification[6].

GPT-Live became generally available in the API on 10 September 2026, priced at $0.05 per minute of live session, with backend models and tools billed separately[3][4]. The API model takes audio and text in and produces audio and text, supports function calling, and is served through a dedicated Live endpoint[3].

Where it sits

GPT-Live is not a fixed snapshot of a single model. OpenAI said it would keep updating the frontier model behind GPT-Live as new models shipped[6]. The interesting design choice is that the conversational layer and the reasoning layer are separated: the voice model stays responsive and keeps the exchange going, while the harder work is passed to another model. That is what makes a speech interface feel less like waiting for a machine to finish and more like talking to someone who is still listening.

CapabilitiesMultimodalAgents & tool use

ApplicationsConsumer apps

Version history

22
  1. 2018
    • Jun 11, 2018 GPT-1

      GPT-1 was OpenAI's first generative pre-trained transformer, published in June 2018. It showed that one language model, pre-trained on unlabelled text and then fine-tuned, could improve results on many language tasks.

  2. 2019
    • Feb 14, 2019 GPT-2

      GPT-2 is a large language model that OpenAI announced in February 2019. Its largest version has 1.5 billion parameters. OpenAI first withheld the full model, then released it in stages through November 2019.

  3. 2020
    • May 28, 2020 GPT-3

      GPT-3 is an autoregressive language model with 175 billion parameters, described in a May 2020 paper. It could perform new tasks from a few examples in the prompt, without any gradient updates, and it was first offered through OpenAI's API.

  4. 2022
    • Mar 15, 2022 GPT-3.5 (text-davinci-002/003)

      GPT-3.5 is the family of OpenAI language models between GPT-3 and GPT-4, released through API models such as text-davinci-002 and text-davinci-003 and underlying the first version of ChatGPT.

  5. 2023
    • Mar 1, 2023 GPT-3.5 Turbo

      GPT-3.5 Turbo was the chat-optimised GPT-3.5 model OpenAI released through its API on 1 March 2023, priced at a tenth of the cost of earlier models and later replaced in ChatGPT by GPT-4o mini.

    • Mar 14, 2023 GPT-4

      GPT-4 is OpenAI's large multimodal model, released on 14 March 2023. It accepts image and text input, scored near the top of human test-takers on a simulated bar exam, and was succeeded by GPT-4 Turbo, GPT-4o and GPT-5.

    • Nov 6, 2023 GPT-4 Turbo

      GPT-4 Turbo is a cheaper, more capable version of OpenAI's GPT-4, announced on 6 November 2023 with a 128,000-token context window and lower API prices.

  6. 2024
    • May 13, 2024 GPT-4o

      GPT-4o is a multimodal model from OpenAI, released in May 2024, that takes text, audio, image and video as input and generates text, audio and image output within one neural network. It was removed from ChatGPT in February 2026.

    • Jul 18, 2024 GPT-4o mini

      A small, low-cost language model OpenAI released on 18 July 2024, priced far below GPT-4o and reported at 82% on MMLU; it replaced GPT-3.5 Turbo in ChatGPT on launch day.

    • Sep 12, 2024 OpenAI o1

      OpenAI o1 is the first reasoning model series from OpenAI, introduced in September 2024. It thinks through a long internal chain of thought before answering, and it was the base for later reasoning models such as o3.

  7. 2025
    • Feb 27, 2025 GPT-4.5

      GPT-4.5 is a large language model OpenAI released on 27 February 2025 under the code name "Orion". It was its largest chat model at the time, priced far above GPT-4o, and was retired from general availability within months.

    • Apr 14, 2025 GPT-4.1 (with mini and nano)

      OpenAI's April 2025 family of three API models — GPT-4.1, GPT-4.1 mini and GPT-4.1 nano — offering a context window of over a million tokens, low prices per token and stronger coding scores. It was succeeded by GPT-5.

    • Apr 16, 2025 OpenAI o3

      OpenAI's second-generation reasoning model, announced in December 2024 and released in April 2025, which posted large gains over o1 on science, software-engineering and competitive-programming benchmarks before being succeeded by GPT-5.

    • Aug 7, 2025 GPT-5

      GPT-5 is OpenAI's fifth GPT foundation model, released on 7 August 2025. It pairs a fast model with a deeper reasoning model and a router that chooses between them for each request.

    • Nov 12, 2025 GPT-5.1

      GPT-5.1 is an update to GPT-5 released by OpenAI on 12 November 2025. It added a warmer default personality with selectable styles, and its API version has been scheduled for shutdown in 2027.

    • Dec 11, 2025 GPT-5.2

      GPT-5.2 is a model family OpenAI released on 11 December 2025, with Instant, Thinking and Pro versions and a coding variant. It was aimed at professional work such as spreadsheets and presentations.

  8. 2026
    • Mar 5, 2026 GPT-5.4

      GPT-5.4 is a model OpenAI released on 5 March 2026 in Thinking and Pro versions. It added built-in computer use and improved deep research, and it was the model that succeeded GPT-5.2.

    • Apr 23, 2026 GPT-5.5

      GPT-5.5 is an OpenAI model released on 23 April 2026 as GPT-5.5 Thinking and Pro, with an API version the next day. It succeeded GPT-5.4 and had a cybersecurity variant in limited preview.

    • Jul 8, 2026 GPT-Live-1 · This page

      GPT-Live-1 is OpenAI's full-duplex voice model family, launched 8 July 2026, which lets ChatGPT listen and speak at the same time and replaced the earlier chained speech pipeline in ChatGPT Voice.

    • Jul 9, 2026 GPT-5.6 (Sol, Terra and Luna)

      OpenAI's three-model family released on 9 July 2026 — Luna, Terra and Sol, ordered from least to most capable — with Sol pitched as the company's strongest coding and agent model.

    • Sep 3, 2026 GPT-6 (Astra, Sol, Luna, Instant)

      GPT-6 is OpenAI's sixth-generation model family, launched from 3 September 2026 with GPT-6 Astra, followed by Sol, Luna and Instant. Astra was the first OpenAI model to reach its internal critical cybersecurity threshold.

    • Sep 29, 2026 GPT-6.1 (Sol and Terra)

      OpenAI's late-2026 model family: Sol, released at DevDay on 29 September 2026, and the faster, cheaper Terra on 26 October 2026. A planned Astra version was withheld over safety concerns.

20261

  1. ReleaseOpenAI launches GPT-Live full-duplex voice in ChatGPT

    On 8 July 2026 OpenAI launched GPT-Live, a generation of full-duplex voice models for ChatGPT that can listen and speak at the same time; the smaller model became ChatGPT's default voice model.

Developed by1

OpenAI

Successor of1

GPT-4o

Powers1

ChatGPT

Notes and sources

  1. OpenAI launches GPT-Live, a full-duplex voice upgrade that lets ChatGPT talk more like a personhttps://venturebeat.com/technology/openai-launches-gpt-live-a-full-duplex-voice-upgrade-that-lets-chatgpt-talk-more-like-a-person
  2. ChatGPT can now listen and talk at the same time, making AI conversations seem more humanhttps://the-decoder.com/chatgpt-can-now-listen-and-talk-at-the-same-time-making-ai-conversations-seem-more-human/
  3. GPT-Live 1 Model | OpenAI APIhttps://developers.openai.com/api/docs/models/gpt-live-1
  4. OpenAI GPT Model Release Timelinehttps://hidekazu-konishi.com/entry/openai_gpt_model_release_timeline.html
  5. Deprecationshttps://developers.openai.com/api/docs/deprecations
  6. Introducing GPT-Livehttps://openai.com/index/introducing-gpt-live/

Cite this page: GPT-Live-1. TellWorld, https://www.tellworld.net/models/gpt-live-1. Updated 2026-11-08