Google 发布 Gemini 3.8 Live 与 3.8 Live Extended Thinking
Gemini 3.8 Live and 3.8 Live Extended Thinking are here. Following 3.5 Transcribe last month, this continues our focus on real-time voice agents. 🐸🐸
Google 发布 Gemini 3.8 Live 和 Gemini 3.8 Live Extended Thinking,延续上月 3.5 Transcribe 之后对实时语音智能体的投入。官方给出的数据包括 Artificial Analysis Quality Index 82.6 排名第一、输入 $0.005/min 与输出 $0.018/min,以及 τ-banking 智能体任务完成率 35.1 排名第一。3.8 Live Extended Thinking 可在后台思考并异步执行工具调用,同时保持对话不中断,用于协调多步工具使用。该模型已在 Google AI Studio 的 Gemini API、Google Search 和 Gemini App 上线,也可通过 LiveKit、Pipecat、LangChain、Vercel 的合作伙伴插件使用。
推荐理由
AI 评分 80
Gemini 3.8 Live 系列把实时语音与后台思考、异步工具调用结合,并给出价格和榜单排名,可据此判断语音智能体的落地成本。
主题
正文
当前显示原文,中文全文译文尚未就绪。
Gemini 3.8 Live and 3.8 Live Extended Thinking are here. Following 3.5 Transcribe last month, this continues our focus on real-time voice agents. 🐸🐸
- 82.6 (#1) on Artificial Analysis Quality Index - $0.005/min input and $0.018/min output. - 35.1 (#1) Agentic task completion (τ-banking)
3.8 Live Extended Thinking can think in the background and run asynchronously tool calls while keep talking to you. It uses background thinking to coordinate multi-step tool use without losing conversational flow.
Available in @GoogleAIStudio Gemini API, Google Search, and @GeminiApp or as partner plugins in @LiveKit, @Pipecat_ai, @LangChainAI, and @vercel