Full observability for your Vapi voice agents
Connect your Vapi assistant to Tuner with no code, paste your API key and every call's transcript, latency, and outcome flows in automatically. Works with both permanent and transient agents, so even inline per-call assistants stay grouped and analyzable.
Integrate in under two minutes
Paste your Vapi key, point Tuner at your assistant, and Tuner configures the webhook for you.
01
Get your Vapi credentials
Copy your Private API key and Assistant ID from the Vapi dashboard.
02
Add your key in Tuner
Paste your Vapi Private key under Workspace Settings → API Keys & Integrations and save, before you create the agent.
03
Create your agent
Add a new agent in Tuner with Provider: vapi and your Assistant ID as the Agent Remote ID.
04
Tuner wires the webhook
Tuner configures the Vapi webhook automatically. Already using a webhook? The webhook proxy forwards every call to your existing n8n or Zapier flow too.
Read the Vapi guide →
One dashboard
Every Vapi call, scored automatically
Transcripts, latency, usage, and red flags from every call land in one place, so quiet failures surface before they reach your churn data.
Works with both Permanent and Transient agents
However you build on Vapi, Tuner captures every call — including the inline, per-call agents that normally vanish.
Permanent agents
Stored in Vapi, referenced by Assistant
Your assistant lives in the Vapi dashboard and every call points at its Assistant ID. Connect it to Tuner once and all of that agent's calls are captured, scored, and alerted on automatically.
Transient agents
Built inline, per call, and they scatter
You hand Vapi the whole agent inline on every call, so nothing is stored and calls aren't tied to an Assistant ID. Tuner pulls those scattered calls back into one view, grouped by customer, use case, or prompt version — so multi-business and per-caller agents stay fully analyzable.
Read the Vapi Transient guide →
Why you need 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.
Everything you need to run Vapi agents in production
Turn production from a black box into something you can actually monitor, measure, and improve.
Catch failures early
Hallucinations, broken flows, dead air, early hangups, and missed intents are flagged automatically — before they reach your churn data.
Outcome & intent scoring
Score every call against your own outcomes and evals, not just Vapi's call status , so you know whether the agent actually did its job.
Real-time alerts
Get notified the moment red flags or failed evals appear in production, instead of weeks later buried in logs.
Call simulation
Stress-test your agent over SIP before launch and after every change, scored against the same evals that monitor live traffic.
Calls grouped your way
Every call is organized by customer, use case, and prompt version, so even transient, multi-business agents stay easy to track.
Keep your existing webhooks
Tuner's webhook proxy takes Vapi's single webhook slot and forwards the full payload to your original URL, so your automations keep running.
Ship with confidence
Catch regressions the moment a new version ships
Compare agent versions across success rate, red-flag rate, and cost per call, and see exactly which failure types are driving the drop.
Tuner vs Vapi Monitoring
Vapi's monitoring, alerting, and evals are good. The problem is that Vapi is scoring the same agent it built, and it only reports per turn. One turn can hide several nodes, so you get a number without knowing which step broke. Tuner stays independent and goes node by node, pointing to the exact STT, LLM, or TTS step behind a failure or delay. It also tracks quality across versions and runs SIP simulations with AI agents before you ship.
Vendor-independent observability, eliminating the conflict of a platform evaluating its own output
✓
Per-node breakdown ,pinpoint the exact STT, LLM or TTS step at fault (Vapi only totals each turn)
✓
SIP call simulations with AI agents, using your live evals
✓
Root-cause diagnosis with a specific fix, not just metrics
✓
30+ voice quality metrics & red flags out of the box
✓
Version & regression analytics across agent deploys
✓
Regroups transient / inline per-call agents
✓
Production monitoring & real-time alerting
✓
Native call transcripts
✓
Frequently asked questions
Do I need to write code to connect Retell to Tuner?
+
Will connecting Tuner break my existing Retell webhook?
+
What gets captured?
+
Can I test my agent before going live?
+
How long does setup take?
+
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?
+