Skip to main content
Roark gives you full visibility into every voice AI conversation. Calls flow in via integrations or the API, metrics are collected automatically via policies, and you can explore everything in real-time.

​
Key Components

Call History

Browse, search, and analyze every call

Metrics

Define what to measure across calls

Reports

Build analytics from your metric data

Traces

OpenTelemetry tracing and backend correlation

Dashboards

Organize reports into views

​
How Calls Get Into Roark

There are two ways to get calls into Roark:

​
Integrations

Connect a voice platform — Vapi, Retell, LiveKit, or Pipecat — and calls sync automatically. See Integrations for setup guides.

​
API / SDK

Upload call recordings directly via the Node.js or Python SDK, or the REST API. 
const call = await client.call.create({
  recordingUrl: 'https://example.com/recording.mp3',
  startedAt: '2024-01-15T10:00:00Z',
  interfaceType: 'PHONE',
  callDirection: 'INBOUND',
  agent: { name: 'Support Agent' },
  customer: { phoneNumberE164: '+15551234567' },
  properties: { department: 'sales' },
})

​
What Happens When a Call Arrives

1

Transcription & Analysis

The call is transcribed and analyzed — speech patterns, sentiment, and 64+ emotions are detected automatically.
2

Metric Collection

Active metric policies run automatically, collecting the metrics you’ve configured.
3

Available in Call History

The call appears in Call History with full analysis, ready to explore.