Customer Experience / Small Business

VeraVoice — AI Phone Receptionist

A 24/7 AI receptionist that answers every call instantly, books appointments, and screens spam

Reception team serving a visitor while a conceptual voice AI handles an incoming call

Original conceptual visual of the voice-reception workflow; not a product screenshot.

Project evidence

Published project record

Published project evidence from Alector Lab. Alector Lab project record; operational metrics are not independently audited.

Measurement period: Published operating period; exact dates are not publicly stated

Evidence method: Operational metrics are not independently audited.

The problem

Missed calls cost service businesses bookings: without round-the-clock coverage, calls outside business hours go to voicemail or the next business that answers.

The approach

The agent runs on OpenAI's Realtime API for conversation, routed through Twilio for telephony and LiveKit for low-latency audio streaming, backed by a Node.js service that handles appointment booking, spam screening, and call logging.

Implementation

The agent answers every inbound call, determines caller intent, books appointments directly into the calendar, and filters spam and robocalls before they reach staff.

What we learned

  • A phone agent has to handle interruptions and natural speech, not just clean turn-taking, to be usable as a real receptionist.
  • Spam and robocall filtering needs to run before the conversation flow starts, so it doesn't waste the agent's time or clutter the call log.

Have a similar system to build?

Discuss a project