Google 发布 Gemini 3.8 Live 语音模型，附浏览器试用 UI
原标题：Gemini Live audio
AI 摘要
Google 发布 Gemini 3.8 Live 和 3.8 Live Extended Thinking 两款语音到语音模型，形态类似 OpenAI 的 GPT-Live 系列。作者用 GPT-6 Astra Extra High 参考文档构建了一个网页 UI，可选择模型和语音预设、输入系统提示词，并通过浏览器进行可打断的语音对话。该实现不依赖任何库，直接连接 Google 的 WebSocket 端点，并用 Web Audio API 处理音频采集与播放。
正文节选
15th September 2026 Google released Gemini 3.8 Live and 3.8 Live Extended Thinking today - two new speech-to-speech models that are a similar shape to OpenAI's GPT-Live family. I pointed GPT-6 Astra Extra High at the documentation and had it build me this web UI for trying out the new models. You can select a model and voice preset, enter an optional system prompt and then start a voice conversation through your browser, including the ability to interrupt the model while it is talking. The imple