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
产品
GPT Realtime 2
别名：GPT-Realtime2
OpenAI的实时语音处理API
相关材料
已收录 15 条与 GPT Realtime 2 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
We’re introducing three audio models in the API
OpenAI970 字 (约 4 分钟)
87
OpenAI has introduced two new real-time audio models: GPT Realtime Translate supports live translation across 70 languages, while GPT Realtime 2 enhances voice assistant capabilities with intelligent reasoning.
入选理由：GPT Realtime Translate能够实现实时跨70种语言的翻译。
FeaturedVideo#OpenAI#Speech Recognition#Real-Time Translation#Voice Assistant英文
LWiAI Podcast #245 - TML-Interaction, Claude For Legal, Sam Altman on Stand
Last Week in AI624 字 (约 3 分钟)
85
This episode highlights OpenAI's real-time voice API, Thinking Machines' interactive model architecture, Anthropic's legal product, and market dynamics, revealing advancements in real-time interaction, vertical applications, and security compliance.
入选理由：OpenAI推出GPT Realtime 2 API，强调低延迟与推理的平衡，新增反欺诈防护。
FeaturedArticle#AI API#Real-time Interaction#Legal Tech#Model Security#Platform Competition英文
BestBlogs Weekly | Issue 94: Voice AI Breakthrough
Gino Notes2911 字 (约 12 分钟)
85
Voice AI is moving from the edge to the core of human-AI interaction. OpenAI released multiple real-time voice models, ElevenLabs achieved $400 million in annual revenue, and Anthropic partnered with SpaceX for 300 MW of computing power.
入选理由：OpenAI 发布 GPT-Realtime-2，通话成功率提升至 95%
FeaturedArticle#Voice AI#OpenAI#ElevenLabs#Anthropic#AI Infrastructure中文
Simon Willison on X: "Saw this and thought 'yes! ChatGPT voice mode is going to stop acting like a two-year-old' but that upgrade hasn't shipped just yet"
Simon Willison(@simonw)167 字 (约 1 分钟)
85
OpenAI launched GPT-Realtime-2 with GPT-5-level reasoning, enabling real-time voice agents, but the update isn't live in ChatGPT yet.
入选理由：GPT-Realtime-2 支持 GPT-5 级推理，提升语音交互智能水平
FeaturedTweet#OpenAI#GPT-Realtime-2#voice model#API英文
🚀 GPT-Realtime-2 just landed in Genspark.
Genspark(@genspark_ai)202 字 (约 1 分钟)
78
GPT-Realtime-2 has enhanced the reasoning and instruction-following capabilities of voice agents, increasing effective conversation rates by 26%.
入选理由：GPT-Realtime-2使Call for Me Agent的对话效率提升26%。
FeaturedTweet#GPT-Realtime-2#Voice Agents#OpenAI英文
Greg Brockman on X: "GPT-5-class reasoning for voice agents, now in the API:" / X
Greg Brockman(@gdb)118 字 (约 1 分钟)
78
OpenAI introduced GPT-Realtime-2 in the API, their most intelligent voice model yet, supporting real-time collaboration and complex problem solving.
入选理由：GPT-Realtime-2是目前OpenAI最智能的语音模型。
FeaturedTweet#OpenAI#GPT-Realtime-2#voice recognition英文
Greg Brockman on X: "You can now just build amazing voice agents, with the GPT-Realtime-2 reasoning model in our API:" / X
Greg Brockman(@gdb)151 字 (约 1 分钟)
78
OpenAI introduces GPT-Realtime-2 model, significantly enhancing real-time reasoning capabilities for voice assistants, suitable for complex problem-solving.
入选理由：GPT-Realtime-2在API中提供，性能接近GPT-5级别。
FeaturedTweet#OpenAI#GPT-Realtime-2#Voice Assistants英文
OpenAI Developers on X: Building voice applications with GPT-Realtime-2? Our new prompting guide covers how to tune reasoning effort, use preambles, design tool behavior, handle unclear audio, capture exact entities, and maintain state in longer sessions.
OpenAI Developers(@OpenAIDevs)112 字 (约 1 分钟)
78
OpenAI's newly released guide introduces how to build voice applications using GPT-Realtime-2, covering aspects such as tuning reasoning efforts, preamble design, and tool behavior.
入选理由：GPT-Realtime-2能有效处理模糊音频输入，提高语音识别准确性。
FeaturedTweet#GPT-Realtime-2#Voice Applications#OpenAI英文
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
Sam Altman on X: "people are really starting to use voice to interact with AI, especially when they have a lot of context to dump."
Sam Altman(@sama)176 字 (约 1 分钟)
72
Voice interaction is becoming an important way for AI applications, and the release of GPT-Realtime-2 API marks a significant progress.
入选理由：语音交互在复杂场景中表现更佳，用户反馈积极。
FeaturedTweet#AI#Voice Interaction#GPT英文
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
What if your team gave standup updates, and GPT-Realtime-2 moved the tickets?
OpenAI Developers(@OpenAIDevs)56 字 (约 1 分钟)
50
GPT-Realtime-2 might enable automatic ticket updates from team standup audio, but this remains a conceptual idea with no technical validation yet.
入选理由：GPT-Realtime-2 尚未发布，功能仅基于推测。
FeaturedTweet#GPT-Realtime-2#AI Automation#OpenAI英文
GPT-Realtime-2, Directionally Bad and Agent Memory
Matthew Berman630 字 (约 3 分钟)
20
The provided YouTube video link does not offer specific technical content, only showing the playback interface and related recommended videos.
入选理由：无法获取具体技术信息
FeaturedVideo#AI#GPT英文