我们正在 API 中推出 GPT‑Live‑1，为开发者提供一个强大、自然的语音模型，用于构建支持语音的应用和业务工作流。最初在 ChatGPT 中推出，GPT‑Live‑1 能够同时听和说，并且，正如在 Codex 和 ChatGPT Work 中所见（在新窗口中打开），它可以将更深层的推理和操作委托给它所搭配的模型和工具。
对于 GPT‑Live‑1 的 API 发布，我们专注于新能力，让开发者能够围绕其用户、工作流和目标来引导和定制语音体验。GPT‑Live‑1 的一项核心优势——流畅的中断处理——已经在产生业务影响：在早期评估中，Speak 发现 GPT‑Live‑1 让学习者在语言导师回应前有更多时间思考，与之前基于轮次的系统相比，中断减少了近 80%。
GPT‑Live‑1 在 API 中的关键优势：
- **中断处理：**通过一个单一模型同时推理传入和传出的音频，改进了中断处理，避免了链式 STT–LLM–TTS 架构的延迟和脆弱交接。
- **推理与工具调用委托：**GPT‑Live‑1 可以将推理和工具调用委托给后端文本模型，如 GPT‑6 Astra 或第三方模型。
- **语气、节奏和风格：**让开发者可以通过系统提示来塑造智能体的语气、节奏和对话风格。
- **静默上下文管理与背景噪音：**更好地处理背景噪音和静默，而不会打断对话或大声叙述每一步。
- **长会话可靠性：**在长时间交互中改进上下文保留和对话质量。
- **电话支持：**支持为电话通话部署全双工语音智能体，从餐厅预订到客户支持。
试用 GPT-Live-1
开始一个会话并自然说话。打断、笑、改变主意——在家里或在咖啡店、城市街道等嘈杂空间中试用。
看看它能做什么
- **自然地打断它。**寻求帮助，然后在回复中途打断以更改问题或添加细节。
- **随身携带。**在户外散步时或日常背景噪音中尝试对话，看看它如何跟上你。
- **让它更有趣。**笑、犹豫、使用简短回应，或短暂与附近的人交谈——然后继续对话。
此演示有时间限制。使用它即表示你同意 OpenAI 的条款并确认我们的隐私政策。
简化你的语音智能体架构并降低语音延迟
传统语音智能体将语音转文本、推理模型和文本转语音拼接在一起。每次交接都会增加延迟，并创造更多丢失时机、上下文或对话自然节奏的机会。开发者往往需要协调这些阶段，包括当有人打断、暂停或改变方向时会发生什么。
GPT‑Live‑1 在单一模型中处理听和说，简化了语音层。它可以对实时发生的中断和回应作出反应，同时将更深层的推理委托给后端。这让对话可以在后台工作发生时继续进行。
开发者选择对话背后的模型、工具和智能体框架。例如，他们可以将 GPT‑Live‑1 与 Luna 这样的模型搭配，用于调度或订单更新等高容量任务，并使用 Astra 这样的模型处理需要推理的复杂客户问题。这种灵活性让开发者能够为每项任务匹配推理深度、速度和成本。
GPT‑Live‑1 原生提供 ASR 转录和响应文本。它还具备强大的字母数字理解能力，并支持关键词偏置。尽管 GPT‑Live‑1 不是基于轮次的模型，但它原生支持轮次检测，因此开发者可以继续围绕明确的轮次边界进行构建。
衡量全双工优势
在我们的评估中，GPT‑Live‑1 将 Full Duplex Bench 性能比 GPT‑Realtime‑2.1 提高了 30 个百分点，在轮次转换延迟和交互行为方面有大幅提升。与中等推理工作量的 GPT‑6 Astra 搭配使用时，它还在 Tau3 上排名第 1，该基准衡量端到端任务中的前沿语音智能体智能。
评估航空、零售和电信领域的口语客户服务任务。Pass@1 衡量任务成功；标题为每个领域赋予相同权重。
- GPT Live 后端：Astra（中等）。
评估带知识检索和账户工具的口语银行支持。Pass@1 是 97 个 banking_knowledge 任务成功完成的比例。
- GPT Live 后端：Astra（中等）。
评估暂停处理、对话轮次转换、中断和背景回应。
测试对背景语音、与他人交谈、听者背景回应和中断的反应。
衡量智能体在用户完成一轮后开始回复的速度。
测试从包含自然停顿、犹豫和自我纠正的口语请求中进行工具使用。Pass@1 对工具调用序列评分。
- GPT Live 后端：Terra（低）。
评估对包含停顿、犹豫和自我纠正的工具使用请求的口语回答。评分回答与参考意图的匹配程度。
- GPT Live 后端：Terra（低）。
客户评价
1 / 4
新的语音选项
开发者需要适合其产品、并且对使用者来说听起来自然的语音。借助 GPT‑Live‑1，我们正在从少量实时语音扩展到更广泛的选择，涵盖口音、方言和语言，让开发者在助手的声音方面有更多选择。
聆听新语音
我们将在未来几个月继续扩展语音选项和语言可用性。
定价与可用性
GPT‑Live‑1 今天已在 API 中提供（在新窗口中打开），前端语音层每分钟 $0.05。将其与适合你产品的后端模型和智能体框架搭配，然后构建一个能够随其需要完成的工作而扩展的语音体验。
将 GPT-Live-1 连接到 Codex。此摘录展示了一个应用如何将对话上下文传递给 Codex，并将其答案返回给 GPT-Live-1。连接设置和委托处理已省略。
如需自定义语音访问，联系销售以了解有关资格和请求流程的更多信息。
在 GPT‑Live‑1 之上构建语音工作流的另一种方式是使用 OpenAI Presence，它利用该模型来驱动实时语音交互。Presence 帮助企业部署可信的 AI 代理，这些代理可以回答问题、解决问题、使用公司系统、执行已批准的操作，并在需要时升级给人工处理。如需了解更多信息，请联系您的 OpenAI 客户总监。
We’re launching GPT‑Live‑1 in the API, giving developers a powerful, natural voice model for building voice-enabled apps and business workflows. First introduced in ChatGPT, GPT‑Live‑1 is capable of listening and speaking at the same time, and, as seen with Codex and ChatGPT Work(opens in a new window), can delegate deeper reasoning and actions to the models and tools it is paired with.
For the API release of GPT‑Live‑1, we’ve focused on new capabilities that let developers steer and customize voice experiences around their users, workflows, and goals. A core GPT‑Live‑1 strength, smooth interruption handling, is already delivering business impact: in early evaluations, Speak found that GPT‑Live‑1 gave learners more time to think before the language tutor responded, cutting interruptions by almost 80% versus previous turn-based systems.
Key strengths of GPT‑Live‑1 in the API:
- **Interruption handling:**Improves interruption handling via a single model that reasons over incoming and outgoing audio together, avoiding the latency and brittle handoffs of chained STT–LLM–TTS architectures.
- **Reasoning & tool calling delegation:**GPT‑Live‑1 can delegate reasoning and tool calls to a backend text model like GPT‑6 Astra or a third-party model.
- Tone, pace, and style: Lets developers shape an agent’s tone, pace, and conversational style through the system prompt.
- Silent context management & background noise: Better handles background noise and silence without interrupting the conversation or narrating every step out loud.
- Long-session reliability: Improves context retention and conversational quality across extended interactions.
- Telephony support: Enables deployment of full-duplex voice agents for phone calls, from restaurant reservations to customer support.
Try GPT-Live-1
Start a session and speak naturally. Interrupt, laugh, change your mind - try it at home or in a loud space like a coffee shop or city street.
See what it can do
- Talk over it—naturally. Ask for help, then interrupt mid-response to change the question or add detail.
- Take it with you. Try a conversation while walking outside or with everyday background noise, and see how it stays with you.
- Make it playful. Laugh, hesitate, use short acknowledgments, or briefly talk to someone nearby—then continue the conversation.
This demo is time-limited. By using it, you agree to OpenAI's Terms and acknowledge our Privacy Policy.
Simplify your voice-agent architecture and reduce voice latency
Traditional voice agents stitch together speech-to-text, a reasoning model, and text-to-speech. Each handoff adds latency and creates more opportunities to lose timing, context, or the natural rhythm of a conversation. Developers are often the ones left coordinating those stages, including what happens when someone interrupts, pauses, or changes direction.
GPT‑Live‑1 handles listening and speaking in a single model, simplifying the voice layer. It can respond to interruptions and acknowledgements as they happen, while delegating deeper reasoning to the back end. This lets the conversation continue while work happens in the background.
Developers choose the models, tools, and agent harness behind the conversation. For example, they might pair GPT‑Live‑1 with a model like Luna for high-volume tasks like scheduling or order updates, and use a model like Astra for complex customer issues that require reasoning. That flexibility lets developers match reasoning depth, speed, and cost to each task.
GPT‑Live‑1 natively provides ASR transcripts and response text. It also offers strong alphanumeric understanding and supports keyword biasing. Although GPT‑Live‑1 is not a turn-based model, it natively supports turn detection, so developers can continue to build around explicit turn boundaries.
Measuring the full-duplex advantage
Across our evaluations, GPT‑Live‑1 improves Full Duplex Bench performance by 30 percentage points over GPT‑Realtime‑2.1, with large gains in turn-taking latency and interactive behavior. Paired with GPT‑6 Astra at medium reasoning effort, it also ranks #1 on Tau3, which measures frontier voice-agent intelligence on end-to-end tasks.
Evaluates spoken customer-service tasks in airline, retail, and telecom domains. Pass@1 measures task success; the headline gives each domain equal weight.
- GPT Live backend: Astra (medium).
Evaluates spoken banking support with knowledge retrieval and account tools. Pass@1 is the fraction of 97 banking_knowledge tasks completed successfully.
- GPT Live backend: Astra (medium).
Evaluates pause handling, conversational turn taking, interruptions, and backchannels.
Tests reactions to background speech, speech to another person, listener backchannels, and interruptions.
Measures how quickly the agent starts its reply after the user finishes a turn.
Tests tool use from spoken requests containing natural pauses, hesitations, and self-corrections. Pass@1 scores the tool-call sequence.
- GPT Live backend: Terra (low).
Evaluates the spoken answer to tool-using requests containing pauses, hesitations, and self-corrections. Scores how well the answer matches the reference intent.
- GPT Live backend: Terra (low).
What customers are saying
1 of 4
New voice options
Developers need voices that fit their product and sound natural to the people using it. With GPT‑Live‑1, we’re expanding from a small set of real-time voices to a broader selection across accents, dialects, and languages giving developers more choice in how their assistants sound.
Listen to the new voices
We’ll continue to expand voice options and language availability over the coming months.
Pricing & Availability
GPT‑Live‑1 is available in the API today(opens in a new window) at $0.05 per minute for the front-end voice layer. Pair it with the backend model and agent harness that fit your product, then build a voice experience that can scale with the work it needs to do.
Connecting GPT-Live-1 to Codex. This excerpt shows how an application passes conversation context to Codex and returns its answer to GPT-Live-1. Connection setup and delegation handling are omitted.
For custom voice access, contact sales to learn more about eligibility and the request process.
Another way to build voice workflows on top of GPT‑Live‑1 is with OpenAI Presence, which uses the model to power real-time voice interactions. Presence helps enterprises deploy trusted AI agents that can answer questions, resolve issues, use company systems, take approved actions, and escalate to people when needed. Reach out to your OpenAI account director to learn more.
本文内容采集自官方网站，排版和翻译可能与原页面存在差异。
阅读官方全文