Architecture of a voice AI deployment

Every service in the call and the control plane, and the path a call takes through them. Pick a flow to trace it.

Swipe sideways to see the whole map.

Call plane services

Every service a call touches, in the call plane account in Sydney.

Call plane services
ServiceWhat it doesHow it scales
AdmissionTakes the carrier's call events, applies answering hours and caller blocks, claims a worker and answers the call.Two tasks in two zones
Voice services A and BCall workers. A supervisor keeps idle workers ready, and each worker takes one call and exits.On the worker slots calls need, with a daytime minimum
Post-call serviceWrites call records, runs audio metrics and quality checks, renders greetings and serves chat.On queue age
Jobs serviceUsage meters, call analysis, alerts, follow-up and customer webhooks, read from queues.On the oldest message's age
Test serviceSimulated test calls on their own workers, never on the workers that answer customers.From zero when tests are queued
Route controllerGives each task a route on the media load balancer when it starts, and removes it only after the task stops.One function per task event
DatabaseA serverless relational database, encrypted under a customer-managed key.Serverless capacity, with a reader in single-tenant deployments
Object storageRecordings, call records in transit and cached greetings, with public access blocked.Not applicable
Queues and registryQueues for post-call work, each with a dead-letter queue, and a table of workers and call ownership.On demand
Failover handler and canaryAnswers calls in Melbourne when Sydney cannot, and places test calls around the clock.One function per event

Control plane services

The dashboard, sign-in and releases, in our account or in yours.

Control plane services
ServiceWhat it doesHow it scales
Web appDashboard and agent editor, behind a content delivery network and a web application firewall.Two tasks in two zones
Sign-inAccounts and sessions, with SAML 2.0 and OIDC single sign-on.Two tasks in two zones
Data APIThe dashboard's access to the database, with row-level security on every table.Two tasks in two zones
Release pipelineBuilds each image once and promotes it to each environment by digest.Runs per release

Design rules

  • One call per process

    Each call runs in its own operating system process, which exits when the call ends. In our measurements a second call on the same event loop added 37% to median turn latency.

  • Answer first, then place

    Admission acknowledges the carrier at once, then places the call on a named worker before any audio arrives.

  • One owner per call

    Only the handler that answered a call sends it later commands, so a failover never splits control of a call.

  • Calls do only calls

    Analysis, metrics, webhooks and tests run on other services from queues, so post-call work never stalls a live call.

  • Protected while busy

    A task holding a call is protected from scale-in, and a release waits for its calls to end.

  • A second failure domain

    Failover answering, canary calls, paging, backups and the audit trail sit in Melbourne.

Security questionnaires

We answer security questionnaires in writing and take your team through the architecture on a call. Send yours to hello@verticalai.com.au.