Quick Start
Production voice AI observability — instrument LiveKit, Pipecat, or LangGraph agents in minutes.
Know if your voice AI agent is actually working. Parlot’s MIT parlotize() instruments
production voice AI agents on LiveKit Agents,
Pipecat, and LangGraph
/ LangChain — and models each call as turns: timeline, multi-agent graph, and goal completion
with an evidence trail to the proving turns and audio.
This walkthrough uses LiveKit (Cloud, self-hosted, or LiveKit on Telnyx). For Pipecat or LangGraph, jump to the framework guides under Next.
Install
# Using pip
pip install parlot-instrumentation-livekit
# Or using uv
uv add parlot-instrumentation-livekit
# Or via the parlot meta-package
pip install "parlot[livekit]"
# also: "parlot[pipecat]" · "parlot[langgraph]" · "parlot[all]"Instrument
Call parlotize("…") before constructing AgentSession, then await ctx.connect() before session.start():
from parlot.instrumentation.livekit import parlotize
parlotize("my-agent")
from livekit.agents import AgentSession, JobContext, WorkerOptions, cli
async def entrypoint(ctx: JobContext):
await ctx.connect()
session = AgentSession(...)
await session.start(agent=..., room=ctx.room)Environment
export PARLOT_ENDPOINT=https://ingest.parlot.ai
export PARLOT_API_KEY=<org-scoped-key>Create the API key in Parlot Settings → API keys. New tenants record session audio by
default (Settings → Recording allowlist *). Turn recording off with an empty allowlist or
parlotize(record=False). On LiveKit, recording uses Room Composite egress; audio is available
when you open the session in Parlot.
Next
License
Instrumentation is MIT. The companion analysis platform is Business Source License 1.1 (BSL 1.1): free production use up to 4,000 turns/month for your own agents and agents you operate for clients; above that, or to offer Parlot as a hosted service, requires a commercial license. Each version converts to Apache 2.0 four years after its first public release. Enterprise governance features require an Enterprise Edition (EE) license key.