OpenAI新语音模型GPT-Live，对话超流畅，还能同时翻译，比老版本自然多了。
OpenAI发布GPT-Live，采用全双工架构，能连续处理输入而非前代的轮次模型。演示显示对话流畅无中断，支持在后台调用其他模型协作。还展示了实时翻译能力，能同时听、处理、输出。ChatGPT的语音对话因此获得重大升级。
OpenAI just rolled out GPT-Live, its next-gen voice model that makes talking to AI "feel much more l...
OpenAI just rolled out GPT-Live, its next-gen voice model that makes talking to AI "feel much more like having a real conversation". The demo showed off a fast, super smooth back-and-forth without the awkward interruptions or pauses of older voice models. GPT-Live is a "full-duplex" architecture, which processes inputs continuously instead of predecessors that strung together models and used turn-based conversation. GPT-Live is also able to delegate work to other models, allowing it to leverage top systems in the background during conversations. Another demo showed off real-time translation capabilities, with GPT-Live able to listen, process, and output at the same time. Voice conversations in ChatGPT just got a big upgrade. Your browser does not support the video tag. 🔗 View on Twitter 💬 2 🔄 0 ❤️ 9 👀 2561 📊 3 ⚡