The health & performance control room for Voice AI

Voice AI that sounds as smart as it thinks.

Benten listens to your Voice AI agents — measuring latency, dead air, interruptions and acoustic quality across ElevenLabs, Vapi and Retell in one open-source dashboard.

Self-host in minutes · MIT licensed · No credit card

benten / agents / live

Health Score

92/100

+3.2 vs 7d

Turn Latency

612ms

-84ms vs 7d

Dead Air

2.4%

-0.6% vs 7d

Barge-ins

1.9%

+0.3% vs 7d

Live turn analysis

support-agent-v4 · call #a91f

Latency 486ms
User0.0s
Silence0.48s
Agent0.49s

Agent health

  • onboarding-bot

    ElevenLabs

    96
  • sales-outbound

    Retell

    88
  • support-agent-v4

    Vapi

    92
  • renewal-followup

    Retell

    71
  • triage-en

    Vapi

    64

Vendor-agnostic. Works with the voice stack you already use.

ElevenLabsVapiRetellDeepgramTwilioLiveKit

The problem

Voice quality can't be measured with a text transcript.

Traditional AI monitoring evaluates strings. Real callers judge you on timing, tone, and pauses.

The Text Fallacy

A voice bot can generate a perfect response — but if it takes 3 seconds to reply, the caller hangs up thinking the line dropped.

Awkward conversational dynamics

Bots that interrupt mid-sentence, freeze in dead air, or speak over users quietly destroy brand reputation.

Multi-provider fragmentation

ElevenLabs, Vapi, Retell — every vendor gives you a different view. Nobody gives you the whole picture of voice quality.

Platform

Everything you need to ship a voice agent you'd actually call.

One control room for every voice agent your team ships — no matter which provider it runs on.

Integrations

Unified multi-provider discovery

Drop in API keys for ElevenLabs, Vapi or Retell. Benten auto-syncs every agent and assistant profile into one dashboard — zero manual setup per agent.

Metrics

Acoustic & conversational metrics

Turn latency, dead air %, barge-ins and a 0–100 health score derived from raw call audio — not just LLM logs.

Alerts

Smart incident flagging

Automatic alerts on latency spikes, barge-in bursts and audio drops — with root-cause drilldown across TTS, webhooks and LLM.

Analytics

360° agent drawers

Historical trends, response-speed distributions, call volume, health scores and raw config — for every agent, in one click.

Security

Multi-tenant enterprise security

Workspace isolation, role-based access and audit-ready logs — built for agencies managing many client portfolios.

Open source

Fully open source

MIT-licensed. Self-host it, extend it, audit it. Own your voice observability stack end-to-end.

The metrics that matter

Measured from the audio. Not the transcript.

Speed

Turn Latency

ms

Exact millisecond delay from when the human stops speaking to when the agent responds.

Silence

Dead Air %

%

Unintended silences during processing, hand-offs, or model warm-up.

Flow

User Interruptions

count

Calls where the user had to talk over the agent, or the agent failed to yield the turn.

Overall

Health Score

0–100

Response speed, conversational flow and acoustic quality synthesized into one benchmark.

How it works

From API key to insight — in under 10 minutes.

01

Connect providers

Paste API keys for ElevenLabs, Vapi or Retell. Encrypted, workspace-scoped, revocable.

02

Auto-discover agents

Benten catalogs every deployed assistant across every provider into a single unified list.

03

Automated call QA

Raw call audio is analyzed for turn timing, dead air, barge-ins and speech dynamics.

04

Inspect & resolve

Drill down into any call. Trace latency to TTS, webhooks or LLM — and fix it.

05

Continuous quality

Track health score trends over time. Ship voice changes with confidence.

Built for

Every team that ships voice.

AI Engineers & PMs

Measure real-world latency, fine-tune voice settings, and debug call bottlenecks across vendors.

CX & QA Teams

Audit voice call quality at scale — without listening to thousands of hours of raw audio.

Support & Ops Leaders

Track SLA compliance, reduce caller drop-offs, and safeguard CSAT.

Voice AI Agencies

Report on agent performance for multiple client organizations from a single dashboard.

MIT Licensed

Own your voice observability stack.

Benten is fully open source. Self-host it on your own infra, extend the evaluators, contribute back — and never lock your voice quality data inside another vendor.

~/benten
$ git clone github.com/benten/benten
$ cd benten && docker compose up

→ syncing agents from ElevenLabs...
→ syncing agents from Vapi...
→ syncing agents from Retell...

✓ 34 agents discovered
✓ dashboard live at localhost:3000

Hear what your Voice AI really sounds like.

Plug in your provider keys, and get a full acoustic QA report on every agent — today.