Skip to main content
Trace your Pipecat voice agents to LangSmith with the LangSmith Pipecat integration. For high-level conventions, see Voice tracing fundamentals.
The Pipecat integration requires langsmith[pipecat]. It is in development, so its API may change.
The integration captures each conversation as a single LangSmith trace, with a span for every pipeline stage (STT, LLM, TTS) grouped by turn. You enable it with one call and do not create any spans yourself.

​
Install

Install the integration along with the Pipecat service extras your pipeline uses:

​
Set environment variables

The integration reads your LangSmith credentials from the environment and exports to LangSmith for you:
.env

​
Set up tracing

Import configure_pipecat and call it once before building your pipeline. Enable tracing on the PipelineTask:
Set enable_tracing=True, enable_turn_tracking=True, and enable_metrics=True. Turn tracking is required for tracing, and metrics drive the latency and token data on each span.
If your LLM stage is an in-process LangGraph or LangChain agent, pass configure_pipecat(llm_span_kind="chain") so its model and tool runs nest correctly inside Pipecat’s llm span.

​
Use your own tracer provider

There are two ways to install the tracing provider. configure_pipecat() is the quick path: it installs an OpenTelemetry TracerProvider and registers the LangSmith span processor on it for you. To send spans through a TracerProvider you already manage (for example, one that also exports to another OpenTelemetry backend), skip configure_pipecat and add the processor to your provider directly:

​
Group a conversation into a thread

To group a conversation’s runs into a LangSmith thread — for thread-level views and token and cost aggregation — call set_thread_id once per conversation, before its spans are emitted:
The integration then stamps the id on every span for you. Because set_thread_id stores the id in a ContextVar, a server handling many conversations concurrently keeps them correctly separated as long as each runs in its own task.

​
Record the conversation audio

Attach the conversation audio to the trace using Pipecat’s AudioBufferProcessor. Place it after transport.output() so it captures what was actually played (after any barge-in truncation), hand it to the integration, and start it once the session is running:
The integration attaches the recording to the conversation root when it ends. For the underlying attachment API, see Upload files with traces.

​
Next steps

Voice fundamentals

Core conventions for tracing voice agents.

Upload files with traces

Attach the conversation audio recording to your trace.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.