智能体
www.aibase.com ·
OpenAI 将 GPT-Live-1 引入 API：全双工语音、支持打断，可接电话做客服
OpenAI 宣布将 GPT-Live-1 引入 API，支持全双工实时语音交互，可同时听与说，并处理打断、停顿和背景噪声，适用于餐厅预订、客服等电话场景。该模型将语音理解与语音输出整合在同一模型内，减少传统“语音转文字—大模型—文字转语音”的多段连接以降低延迟，复杂推理和工具调用仍由后端文本模型处理；开发者可通过系统提示调整语气、语速和对话风格，并配置后端模型、工具与 Agent 框架。OpenAI 称其支持原生语音识别转写与回复文本，具备字母数字理解、关键词偏置和轮次检测等能力。早期评估方面，语言学习平台 Speak 称使用后学习者思考停顿时的误打断较此前轮次制系统下降近 80%；一家医疗服务平台的联合创始人兼 CTO 称团队代码量减少 80%，移除约 2.3 万行代码。OpenAI 评估显示 GPT-Live-1 在 Full Duplex Bench 测试中领先 GPT-Realtime-2.1 达 30 个百分点，并在搭配 GPT-6 Astra 中等推理强度时于 Tau3 端到端语音 Agent 任务测试中排名第一。定价上，GPT-Live-1 前端语音层为每分钟 0.05 美元（约每小时 3 美元），后端模型与 Agent 工具费用另计；OpenAI 还新增 Quartz、Ripple、Vesper、Willow、Stone、Gleam、Meridian、Bossa、Tempo、Beacon、Delta、Cinder 等 12 种音色，并计划继续增加音色和语言支持。
AI推荐理由
OpenAI 将 GPT-Live-1 引入 API 是语音 Agent 方向的具体产品更新：全双工、可打断、支持电话客服场景，并给出前端语音层每分钟 0.05 美元的定价和新增 12 种音色。文中引用的 Speak 误打断下降近 80%、医疗平台减少约 2.3 万行代码、Full Duplex Bench 领先 30 个百分点等均为 OpenAI 或合作方自述的早期评估，未经独立验证，需保留不确定性；后端模型与工具成本另计，实际落地成本仍取决于调用量。
82
正文
OpenAI Introduces GPT-Live-1 to API: Full-Duplex Voice, Support for Interruption, Can Handle Phone Calls as Customer Service
AIbase基地
Published inAI News · 4 min read · Sep 11, 2026
11
OpenAI announced the introduction of GPT-Live-1 into its API, allowing developers to build applications and business processes that support real-time voice interaction. The model supports full-duplex conversation, able to listen and output voice simultaneously, and can handle interruptions, pauses, and background noise during the conversation.
GPT-Live-1 also supports phone scenarios, such as restaurant reservations and customer service, for full-duplex voice agents. OpenAI stated that developers can connect it with tools like Codex or use OpenAI Presence to develop voice work that can query enterprise systems, perform approved actions, and transfer to human agents when necessary.
Speech understanding and output combined, lower latency
According to the introduction, GPT-Live-1 integrates speech understanding and speech output within the same model, reducing the multiple connections of the traditional "speech-to-text - large language model - text-to-speech" process, thus reducing latency; the model also supports complex reasoning and tool calls being handled by backend text models. Developers can adjust tone, speed, and conversation style through system prompts, and can also configure backend models, tools, and agent frameworks. OpenAI stated that GPT-Live-1 supports native speech recognition transcription and response text, and has capabilities including letter and number understanding, keyword bias, and round detection.
Early evaluations show that after using GPT-Live-1, the number of mis-interruptions during learners' thinking pauses on the language learning platform Speak decreased by nearly 80% compared to the previous round-based system; Tony Stoyanov, co-founder and CTO of a medical service platform, said his team reduced the code volume by 80%, removing about 23,000 lines of code. OpenAI's evaluation results showed that GPT-Live-1 outperformed GPT-Realtime-2.1 by 30 percentage points in the Full Duplex Bench test, and ranked first in the Tau3 end-to-end voice agent task test when paired with GPT-6 Astra at medium reasoning intensity.
Front-end speech layer costs $0.05 per minute, added 12 voices
In terms of pricing, the front-end speech layer of GPT-Live-1 costs $0.05 per minute, which is approximately $3 (about 20.2 RMB) per hour. The cost of the back-end model and agent tools is calculated separately. OpenAI also expanded real-time voice options, adding 12 new voices including Quartz, Ripple, Vesper, Willow, Stone, Gleam, Meridian, Bossa, Tempo, Beacon, Delta, and Cinder, and plans to continue adding more voices and language support in the coming months.
GPT-Live-1OpenAIReal-timeVoiceInteractionVoiceAIAgent
This article is from AIbase Daily
Scan to view
Welcome to the [AI Daily] column! This is your daily guide to exploring the world of artificial intelligence. Every day, we present you with hot topics in the AI field, focusing on developers, helping you understand technical trends, and learning about innovative AI product applications.
—— Created by the AIbase Daily Team
© Copyright AIbase Base 2024, Click to View Source -