LangChain发了个教程，教你用Gemini Live做语音代理，把复杂任务丢给deepagents子代理，既能低延迟对话又能跑长时间任务，挺实用的。
本教程展示如何结合Gemini Live和deepagents子代理构建语音研究代理。Gemini Live提供低延迟、自然流畅的语音对话能力，而deepagents负责执行长时间运行的复杂任务。通过LangSmith实现全链路追踪与可观测性。该方法解决了语音代理中对话质量与可靠性的权衡问题。
Tutorial on using Gemini live to build a voice agent Uses deepagents as a tool: offload complex wor...
Tutorial on using Gemini live to build a voice agent Uses deepagents as a tool: offload complex work to this subagent, use Gemini live for the naturalness/latency LangChain @LangChain Building voice agents can come with tradeoffs. 💬 Better convos w/ speech to speech models Vs 🥪 More reliable harnesses w/ sandwich architecture How to build a voice research agent with both: ✅ Gemini Live: low-latency, natural-sounding convos ✅ Deep Agents: long-running research tasks ✅ LangSmith: full tracing & observability Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 1 👀 481 📊 1 ⚡