Event ·Multi-source

LangSmith 为 4 个语音框架推出生产追踪功能

LangChain 为 LangSmith 新增对 pipecat_ai、livekit、OpenAI Realtime 和 GeminiApp Live（Google ADK）四个语音框架的追踪支持。该功能可捕捉语音智能体在生产中的延迟、音频流和函数调用等指标。开发者通过 LangSmith 面板即可调试语音响应中的延迟问题。LangSmith 已支持超过 10 种框架的追踪，此次扩展针对语音场景。

Current read

做语音智能体怕出问题？LangSmith 直接帮你追踪 pipecat、livekit、OpenAI Realtime 和 Gemini 这四个框架的生产数据，调试延迟和错误就靠它了。

11 sources60° AI heatLast updated 2026/7/21 16:45:09

Evidence

11 sources

Primary sourceLangChain

2026/7/21 16:45:09View 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 4arXiv: Anthropic

2026/7/21 15:45:47View source

Related source 5OpenAI Blog

2026/7/22 05:30:00View source

Related source 6IT之家

2026/7/22 12:16:57View source

Related source 7小互

2026/7/23 12:45:02View source

Related source 8Greg Brockman

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

Related source 9Sam Altman

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

Related source 10@OpenAIDevs

2026/7/20 21:36:41View 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