Advancing voice intelligence with new models in the API
OpenAI Blog1767 字 (约 8 分钟)
92
OpenAI introduces three real-time audio models to enhance voice applications.
入选理由：GPT-Realtime-2 能处理复杂请求并自然延续对话。
FeaturedArticle#OpenAI#Audio Models#API中文
模型
GPT Realtime Whisper
用于实时语音转录的 GPT 模型。
已跟踪 7 条高相关材料
TraeAI 观察
最近变化
2026-05-27 · Codex 使用 GPT Realtime Whisper 实现会议实时转录。
为什么值得关注
GPT Realtime Whisper 被反复提及时，通常意味着它正在影响产品路线、开发者工作流或 AI 产业判断。这个页面把分散材料合并成一个可持续更新的观察入口。
OpenAI语音模型APIGPT实时API
如果只读 3 篇
1
Advancing voice intelligence with new models in the API
OpenAI Blog · 9.2 分
OpenAI 推出三款实时语音模型，提升语音应用的智能化水平。
2
OpenAI 在 Realtime API 里上线了三款新语音模型：GPT-Realtime-2、GPT-Realtime-Translate 和 GPT-Realtime-Whisper，分别管对话...
宝玉(@dotey) · 8.9 分
OpenAI发布了三款新语音模型：GPT-Realtime-2、GPT-Realtime-Translate和GPT-Realtime-Whisper，显著提升了对话、翻译和实时转录能力。
3
Our new voice models are now available in the Realtime API: 🎙️ GPT-Realtime-2: Build production-re...
OpenAI(@OpenAI) · 7.8 分
OpenAI发布了三款新的语音模型：GPT-Realtime-2、GPT-Realtime-Translate和GPT-Realtime-Whisper，支持超过70种输入语言和13种输出语言的实时翻译。
相关材料
已收录 7 条与 GPT Realtime Whisper 相关的内容，按评分排序。
OpenAI Released Three New Voice Models in Realtime API
宝玉(@dotey)572 字 (约 3 分钟)
89
OpenAI released three new voice models: GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper, significantly enhancing dialogue, translation, and real-time transcription capabilities.
入选理由：GPT-Realtime-2在Big Bench Audio智能测试上从81.4%提升到96.6%，支持更复杂的任务编排。
FeaturedTweet#OpenAI#voice model#API中文
OpenAI on X: "Our new voice models are now available in the Realtime API:
OpenAI(@OpenAI)216 字 (约 1 分钟)
78
OpenAI has released three new voice models: GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper, supporting real-time translation across more than 70 input and 13 output languages.
入选理由：GPT-Realtime-2能够构建生产就绪的语音代理，处理复杂对话并保持流畅。
FeaturedTweet#OpenAI#Voice Models#Realtime API英文
Codex for transcribing and answering questions about a meeting in real time:
Greg Brockman(@gdb)94 字 (约 1 分钟)
72
Codex 现实时间转录会议并实时回答问题，通过更新的 Codex Meeting Recorder 技能实现。
入选理由：Codex 使用 GPT Realtime Whisper 实现会议实时转录。
FeaturedTweet#Codex#GPT#会议转录#实时问答中文
OpenAI Developers on X: "GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper are available in the Realtime API today.
OpenAI Developers(@OpenAIDevs)74 字 (约 1 分钟)
70
OpenAI has released GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper, now available in the Realtime API.
入选理由：GPT-Realtime-2提升了实时处理能力。
FeaturedTweet#OpenAI#GPT#Realtime API英文
GPT-Realtime-Whisper brings low-latency streaming transcription to the Realtime API
OpenAI Developers(@OpenAIDevs)94 字 (约 1 分钟)
65
GPT-Realtime-Whisper brings low-latency streaming transcription to the Realtime API, suitable for applications that need to continuously understand speech during interactions.
入选理由：GPT-Realtime-Whisper实现了低延迟的语音转文字服务。
FeaturedTweet#GPT-Realtime-Whisper#Speech Recognition#OpenAI英文
The Third Model GPT-Realtime-Whisper is a Streaming Speech-to-Text Model
小互(@imxiaohu)311 字 (约 2 分钟)
55
GPT-Realtime-Whisper is a streaming speech-to-text model designed for real-time scenarios, supporting low-latency processing unlike the original Whisper which handles complete audio batches.
入选理由：新版模型支持流式处理，无需等待整段音频完成即可输出结果。
FeaturedTweet#AI#Speech Recognition#Streaming Processing#Whisper#Real-time Communication中文