Pipecat

​

Setup

pip install braintrust "pipecat-ai[openai]>=1.3.0"

BRAINTRUST_API_KEY=your-api-key
OPENAI_API_KEY=your-openai-api-key

​

Auto-instrumentation

import asyncio

import braintrust

braintrust.auto_instrument()
braintrust.init_logger(project="my-pipecat-project")  # Replace with your project name

from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.worker import PipelineWorker


async def main():
    # Build your pipeline as usual. Tracing is injected automatically.
    pipeline = Pipeline([...])  # Add your pipeline processors
    worker = PipelineWorker(pipeline)

    runner = PipelineRunner()
    await runner.run(worker)


asyncio.run(main())

from braintrust.integrations.pipecat import setup_pipecat

setup_pipecat(project_name="my-pipecat-project")  # Replace with your project name

braintrust.auto_instrument(pipecat=False)

BRAINTRUST_CAPTURE_USER_AUDIO_ATTACHMENTS=true   # Attach user speech to user_speaking spans
BRAINTRUST_CAPTURE_AGENT_AUDIO_ATTACHMENTS=true  # Attach TTS audio to tts_response spans

from braintrust.integrations.pipecat import setup_pipecat

setup_pipecat(
    project_name="my-pipecat-project",
    capture_user_audio_attachments=True,
    capture_agent_audio_attachments=True,
)

​

Manual instrumentation

from braintrust.integrations.pipecat import BraintrustPipecatObserver

observer = BraintrustPipecatObserver()
worker = PipelineWorker(pipeline, observers=[observer])

​

What Braintrust traces

• Pipeline spans (pipecat_pipeline), the root span covering the full pipeline run, with audio sample rate and format metadata.
• LLM response spans (pipecat_llm_response), nested under the pipeline span, with input messages, output text or tool calls, token usage, time to first token, and model name and provider.
• Tool spans (named by the function), with tool arguments and result.
• STT transcription spans (stt_transcription), with transcript text and language.
• TTS response spans (tts_response), with input text and, when enabled, an audio attachment.
• User speaking spans (user_speaking), with optional user audio attachment.

​

Resources

• Pipecat documentation
• Trace LLM calls
• Braintrust Python SDK reference