---
id: 20260916-T0-15
title: "Google发布Gemini 3.8 Live语音模型，支持实时对话"
title_en: "Google Releases Gemini 3.8 Live Speech-to-Speech Models"
url: https://ai.daily.yangsir.net/daily/20260916-T0-15
issue_date: 2026-09-16
publish_date: 2026-09-15T22:47:07.000Z
category: release
source_name: "Simon Willison"
source_url: https://simonwillison.net/2026/Sep/15/gemini-live/
---

# Google发布Gemini 3.8 Live语音模型，支持实时对话

Google 发布 Gemini 3.8 Live 和 3.8 Live Extended Thinking 两款语音到语音模型，形态与 OpenAI 的 GPT-Live 系列类似。Simon Willison 用 GPT-6 Astra Extra High 阅读文档后，搭建了一个网页 UI 用于试用新模型。这两款模型支持实时语音交互，Extended Thinking 版本可能在复杂推理场景下提供更强的响应能力。开发者现在可以通过该 UI 直接体验新模型的对话效果。

## English Version

**Google Releases Gemini 3.8 Live Speech-to-Speech Models**

Google released Gemini 3.8 Live and 3.8 Live Extended Thinking, two new speech-to-speech models similar in shape to OpenAI's GPT-Live family. Simon Willison pointed GPT-6 Astra Extra High at the documentation and had it build a web UI for trying out the new models. These models support real-time voice interaction, and the Extended Thinking variant likely offers stronger responses for complex reasoning tasks. Developers can now use the UI to directly test the new models' conversational capabilities.

---

**来源**：[Simon Willison](https://simonwillison.net/2026/Sep/15/gemini-live/)

**详情页**：https://ai.daily.yangsir.net/daily/20260916-T0-15

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*