Skip to main content

​
General Questions

Tuner is an analytics and observability platform for voice AI agents. It helps you understand how your agents are performing in real-time, identify issues, and get the insights you need to improve the user experience.
Tuner is designed for developers, product managers, and business teams who are building and managing voice AI agents. Whether you’re a startup or a large enterprise, Tuner provides the tools to monitor and optimize your voice applications.
Tuner integrates with your voice AI platform to automatically ingest call data.
  • For supported platforms like Retell and Vapi, this is a one-click setup.
  • For custom-built voice agents, you can use our simple API to send call data to Tuner.
Once the data is in Tuner, it’s processed to provide transcripts, sentiment analysis, evaluations, and metrics on the Overview dashboard.
Any of them. Tuner does not run your agent or plug into your platform’s internals. The only thing an integration does is send the call to Tuner, and once Tuner has the call it handles everything else.Which route you take depends only on what you build on:
  • Retell, Vapi, or Dograh: a guided setup in the dashboard, no code.
  • LiveKit or Pipecat: install that framework’s Tuner SDK.
  • Anything else: the custom stack route, using either the custom SDK or the Custom API.
What each route involves is under Technical Questions below.
It depends which side of the product you mean.Observability and evals work in whatever language your agent handles. Tuner analyses the transcript you send it, and the eval judges read that transcript in the language the call actually happened in. An Arabic call is scored by the same evals as an English one, with no per-language configuration and no separate agent for each language. Eval prompts themselves can be written in English or in the language of the call.Call Simulation is a fixed list, because there Tuner has to speak rather than just read. Simulated callers support Arabic, English, French, German, Italian, and Spanish, and for English you can also pick an AU, UK, or US accent. See Languages and accents.So an agent that takes calls in a language outside the simulation list can still be fully monitored and evaluated. Only the generation of test calls is limited.
Tuner provides a comprehensive view of your agent’s performance, including:
  • High-Level Metrics: Total calls, success rate, average call duration.
  • Call Analysis: User intent, call outcomes, and sentiment trends.
  • Issue Detection: Red flags for issues like hallucinations, high latency, and agent loops.
  • Drill-Down Capabilities: Full transcripts and evaluation results for every call.

​
Technical Questions

Yes. Where your agent runs makes no difference, because Tuner never runs your agent and needs no access to your infrastructure.The whole integration is one idea: get the call to Tuner. Once Tuner receives it, everything after that is handled for you, including the transcript, per-turn timing, classification, evals, red flags, and alerts. There is nothing else to wire up.How you send the call depends only on what you build on:
  • Retell, Vapi, or Dograh: a guided setup in the dashboard. Add your platform key and pick your agent, or drop the Tuner node into your Dograh workflow. No code, and Tuner configures the receiving side for you.
  • LiveKit or Pipecat: install that framework’s Tuner SDK, LiveKit or Pipecat, and attach it to your session. It captures the call as it happens and sends it when the call ends.
  • Any other platform, or a stack you built yourself, for example Plivo, Bland, or Twilio: use the custom stack route. On Python, the custom SDK attaches observers to your own STT, LLM, and TTS and does the capture for you. In any other language, build the call payload yourself and POST it to the Custom API. Both arrive in Tuner as the same thing.
Self-hosted or managed changes nothing on any of these routes. Calls travel one way, out from your stack to Tuner over HTTPS, so Tuner needs no route into your network. Call Simulation is the one exception: to place a test call, your agent either has to be reachable at a SIP URI you give Tuner, or able to dial a SIP URI Tuner gives it.
You can find our complete API documentation with code examples in the API Reference section.
  • Workspace ID: A unique identifier for your entire workspace in Tuner. Used in API calls to route data to the correct account.
  • Agent Remote ID: A unique identifier that links a specific agent in Tuner to its counterpart on your voice platform. How this works depends on your provider, see below.
  • Workspace ID: Found in your Tuner dashboard under Workspace Settings > General.
  • Agent Remote ID: Depends on how you’re sending call data to Tuner:
    • Retell, Vapi, or other webhook-based providers: Copy the agent ID from your provider’s dashboard and paste it when creating an agent in Tuner. This lets Tuner match incoming calls to the right agent.
    • Custom API (LiveKit, Pipecat, etc.): Tuner auto-generates this ID for you when you create an agent. Use it in your API requests to attribute calls to the correct agent.

​
Security & Privacy

This is a different question from where your agent runs, and the two get mixed up often.
  • Your voice agent can run anywhere, including entirely on your own infrastructure. See the question above on connecting a self-hosted voice agent.
  • Tuner runs as a hosted cloud service on the Pay as You Go, Builder, and Growth plans. On-premise deployment is available on Enterprise, alongside SOC 2 and HIPAA compliance, custom integrations, and a DPA on request. It is scoped with the Tuner team rather than switched on from the dashboard, so contact hi@usetuner.ai to talk through it.
If the underlying concern is what Tuner stores rather than where it runs, PII redaction keeps sensitive details out of stored transcripts and data retention sets how long call data is kept before it is erased.
On the Growth plan, workspace admins can turn on PII redaction. Tuner then automatically detects sensitive details in each call transcript (names, phone numbers, email and physical addresses, SSN / national ID, card numbers, and spoken PINs or passwords) and replaces them with labels like [NAME] before the transcript is stored. The original, unredacted transcript is never kept, and all analysis runs on the clean version.The setting is workspace-wide, so it applies to every agent in the workspace. See Data Redaction (PII) for the full walkthrough.

​
Billing and Credits

Tuner charges in credits. Each analysis a call goes through consumes credits, so you only pay for what you actually run. Your plan sets how many credits are included each month and which features you have access to. Pay as You Go starts free with 300 credits and no commitment, while Builder, Growth, and Enterprise include a monthly credit allowance. The plan and credit tables are in the next question, and usetuner.ai/pricing has the live version.
Two things decide what you pay: the plan you are on, and the credits your calls consume.PlansCredit packs can be topped up at any time on any plan, with no commitment on Pay as You Go.CreditsCredits are spent per analysis, so a call costs whatever you have switched on for it.One credit is $0.008, and a typical monitored call with the standard analyses running costs about 5 credits. The 300 free credits on Pay as You Go therefore cover roughly 60 analyzed calls. The simulation rate only applies from Builder upward, since that is the plan where Call Simulation is included.usetuner.ai/pricing is the source of truth for rates and plan contents.
Credits are consumed each time a call is processed through Tuner. When you send call data via our API or through an integration like Retell, the call is analyzed and credits are deducted from your balance.
You can purchase additional credits at any time from the Settings > Billing page in your Tuner dashboard. Credits are added to your account immediately upon purchase.
When your credit balance reaches zero, new calls will not be processed until you add more credits. You’ll receive notifications as your balance gets low so you can top up before running out.
Yes, you can view your credit balance and usage history in the Settings > Billing section of your dashboard. This includes a breakdown of credits consumed per agent and over time.

​
Next Steps

If you’re having trouble with Tuner, check out our troubleshooting guide.

Troubleshooting Common Issues

A guide to troubleshooting common issues with Tuner.