Event ·Multi-source

LangSmith 为语音代理新增全音频追踪，支持 Pipecat、LiveKit 等框架

LangChain 发布 LangSmith 追踪功能，支持 Pipecat、LiveKit、OpenAI Realtime 和 Gemini Live 四个语音框架。开发者只需几行代码即可捕获完整的音频轨迹、STT/TTS 延迟、中断事件和 VAD 状态。该功能解决了语音代理在生产中的黑盒问题，提供详细的性能洞察。

Current read

做语音代理的兄弟，LangSmith 现在能追踪 Pipecat、LiveKit 这些框架的音频和延迟了，几行代码就能搞定，调试省大事。

11 sources71° AI heatLast updated 2026/7/21 17:11:43

Evidence

11 sources

Primary sourceLangChain

2026/7/21 17:11:43View source

Related source 1Harrison Chase

2026/7/21 17:30:41View source

Related source 2Decoder

2026/7/20 18:08:33View source

Related source 3elvis

2026/7/20 22:09:00View source

Related source 4OpenAI

2026/7/22 13:08:16View source

Related source 5IT之家

2026/7/23 03:43:44View source

Related source 6Greg Brockman

2026/7/19 19:18:34View source

Related source 7Sam Altman

2026/7/20 17:34:35View source

Related source 8@OpenAIDevs

2026/7/20 23:30:18View source

Related source 9berryxia

2026/7/21 15:20:55View source

Related source 10Stanford AI Lab

2026/7/21 19:21:59View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story