December 10, 2025
The team at @LangChainAI built voice AI support into their agent debugging and monitoring tool, LangSmith.
LangSmith is built around the concept of "tracing." If you've used OpenTelemetery for application logging, you're already familiar with tracing. If you haven't, think about it like this: a trace is a record of an operation that an application performs.
Here's a very nice video from @_tanushreeeee that walks you through building and debugging a voice agent with full conversation tracing.
Using the LangSmith interface you can find a specific agent session, then dig into what happened during each turn of the conversation. What did the user say and how was that processed by each model you're using in your voice agent? What was the latency for each inference operation? What audio and text was actually sent back to the user?
Today's production voice agents are complex, multi-model, multi-modal, multi-turn systems! Tracing gives you leverage to understand what your agents are doing. This saves time during development. And it's critical in production.
Tanushree shows using a local (on-device) model for transcription, then switching to using the OpenAI speech-to-text model running in the cloud. You can see the difference in accuracy. (Using Pipecat, switching between different models is a single-line code change.)
Also, the video is fun! It's a French tutor. Which is a voice agent I definitely need.
How to debug voice agents with LangSmith:
https://t.co/nRbU4KqbNE
Getting started with LangSmith tracing: https://t.co/bmUToG1wh6
LangSmith Pipecat integration docs page:
https://t.co/ncM2BNGst6
I always like to read the code for nifty Pipecat services like the LangSmith tracing processor. It's here, though I think this nice work will likely make its way into Pipecat core soon: https://t.co/8FNbERnBuk