Full Observability for custom voice stacks
Attach observers to the pipeline you already built. Your loop stays untouched, it just becomes measurable.
$ pip install tuner-core "tuner-stt-observer[deepgram]" "tuner-tts-observer[cartesia]" tuner-langchain
session = TunerSession(config=TunerConfig.from_env(), call_id=call_id)
session.attach(DeepgramAdapter(connection=dg_connection))
graph = session.attach(wrap_graph(your_graph))
tts = session.attach(CartesiaAdapter())
await session.flush()
Works with your providers
Deepgram
Cartesia
LangGraph
LangChain
Speechmatics
elevenlabs
You own the best data in voice AI. You're using almost none of it.
Your stack already has richer call data than any platform. Most teams either stop too early, or build an observability layer they have to maintain forever.
Too little signal
The thin path
Logs aren’t enough
You see that something failed. Not which turn, which tool, what the caller heard, or what it cost. The richest data never gets used.
Too much upkeep
The heavy path
Building it yourself never ends
Tap every stage, align every provider clock, chase every SDK bump. Seeing the call becomes a second product your team has to run.
The Tuner path
Attach Tuner once. See everything.
Tuner turns the signals your stack already emits into observability, analytics, and simulation, one timeline, live alerts, and tests you run before every deploy. We keep the capture working. You stay on your agent.
Why teams use Tuner
Voice agents fail quietly, and at a scale no team can review by hand. Tuner turns every production call into signal you can debug, alert on, test against, and improve.
01
Debug in minutes, not days
When a call goes wrong, see exactly what happened and where — the full transcript, every turn, latency at each step, tool calls, and conversation state. No more guessing from sparse logs.
02
Get alerted the moment something breaks
Don’t wait for a customer complaint. Configure your own alerts with multiple triggers and conditions — by red flag, metric threshold, agent, or flow — and get notified the instant quality slips.
03
Test before you ship
Run call simulations and automated checks over SIP before every launch and after every change, scored against the same evals that monitor production — so you catch regressions before your callers do.
04
Diagnose your agent at scale
At thousands of calls a day, manual validation is impossible. Tuner finds the patterns, pinpoints where your agent breaks, and suggests how to fix it — so one engineer can stay on top of production.
05
Analytics that explain production
Understand how your agent actually behaves live: where it breaks, when callers get frustrated, which flows are missing, when it hallucinates, and which tool calls fail the most.
Works with pieces you already chose
Each observer ships separately, install only what you use.
STT
Deepgram
Speechmatics
AssemblyAI
Coming soon
TTS
Cartesia
OpenAI TTS
Coming soon
ElevenLabs
Coming soon
LLM / Orchestration
LangChain
LangGraph
One Platform. Every Stakeholder Covered.
From debugging a failed call to proving ROI to the board, Tuner gives every role on your team exactly what they need, from the same source of truth.
Debug Faster. Ship Changes With Evidence.
- ✓Full call traces: LLM, TTS, STT, tool calls
- ✓Tool call breakdown: status, failure, delay per API call
- ✓Alerts the moment a pattern breaks
- ✓Run hundreds of simulated calls before every deploy
- ✓Hallucinations and silent API errors
- ✓Latency spikes and provider timeouts
- ✓Regressions after every prompt or config change
Frequently asked questions
Does Tuner change how my stack runs?
+
Do I have to be on a framework?
+
Which providers are supported today?
+
What if I use a provider you do not list?
+
Does Tuner support alerts and monitoring?
+
Can I define my own evaluations and metrics?
+
How is Tuner priced?
+
Is my call data private and secure?
+