Full observability for your LiveKit voice agents
Connect your LiveKit Agents to Tuner in two lines of code. Every session’s transcript, latency, usage, and cost is captured automatically, so you catch hallucinations, broken flows, and missed intents before your callers do.
pip install tuner-livekit-sdk
from tuner import TunerPlugin
async def entrypoint(ctx: JobContext):
session = AgentSession(…)
TunerPlugin(session, ctx) # wires itself automatically
await session.start(…)
Setup
Integrate in under two minutes
No re-architecting your pipeline. Tuner attaches to your existing LiveKit agent and starts capturing production data immediately.
01
Install the SDK
Add tuner-livekit-sdk to your Python or Node.js LiveKit Agents project. Works with livekit-agents v1.4 and later.
02
Set your Credentials
Drop in your Tuner API key, workspace ID, and agent ID — via environment variables or inline in code.
03
Add the plugin
Add TunerPlugin right after creating your AgentSession. It listens to session events and submits call data when the session ends.
04
Monitor calls in Tuner
Transcripts, latency, usage, and cost flow into your dashboard automatically — no manual API calls, ready to analyze and monitor.
Features
Everything you need to run LiveKit agents in production
Turn production from a black box into something you can actually monitor, measure, and improve.
Catch failures early
Automatically flag hallucinations, broken flows, dead air, early hangups, and other failure conditions before they show up in your churn data.
See where latency comes from
Break out STT, TTS, and LLM latency at p50 and p90, so you can see exactly which part of the voice stack is slowing conversations down.
Get alerted when something breaks
Get notified when red flags, failed evals, or other conditions appear in production — while there’s still time to fix them.
Simulate calls before you ship
Stress-test your agent over SIP before launch and after every change, using the same evals that monitor your live traffic.
LangGraph & LangChain capture
Record LangGraph and LangChain node transitions, tool calls, and timing alongside session data, so you can see what your logic layer was doing during the call.
Track cost on every call
Attach a cost calculator and track LLM, TTS, and STT spend on every session — no separate billing pipeline required.
Why Tuner
See what's happening in production
Voice agents fail quietly, and at a scale no team can review by hand. Tuner turns every production call into structured data you can search, debug, evaluate, alert on, and test against.
Comparison
Tuner vs LiveKit Cloud Observability
LiveKit's built-in observability covers agents hosted on LiveKit Cloud — infra metrics, recordings, and traces. Tuner adds the production quality layer, across every stack you build on.
Capability
Tuner
Vendor-independent observability, eliminating the conflict of a platform evaluating its own output
Evals pricing built for scale: tuner price per call, no per minute surcharge
Built-in flags (hallucination, dead air, early hangup)
Root-cause diagnosis with a specific fix, not just metrics
30+ voice quality metrics & red flags out of the box
Drift & regression alerts over time
SIP call simulations with AI agents, using your live evals
Turn-by-turn transcripts & latency traces
FAQ
Frequently asked questions
Common questions about connecting Tuner to your LiveKit agents.
Read the docs
Which LiveKit versions are supported?
How much do I have to change my agent code?
How long does setup take?
Does TunerPlugin add latency to my sessions?
What gets captured?
Can I test my agent before going live?
Does it work with SIP / phone calls?
Does Tuner work if I'm not on LiveKit Cloud?
LiveKit Cloud has observability. What does Tuner add?
Can I define my own evaluations and metrics?
How is Tuner priced?
Is my call data private and secure?