Rabbitt Voice API

Create AI voice agents, have them place and answer phone calls, and run candidate interviews inside your own product — over one REST API.

Place a call

curl -X POST "https://api.rabbitt.ai/api/v1/calls" \
  -H "Authorization: Bearer $RABBITT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agentId": "507f1f77bcf86cd799439011",
    "phoneNumber": "+919876543210",
    "contactName": "Asha Menon"
  }'

New here? The quickstart takes you from an API key to a completed call in about five minutes.

Building a production integration? The complete API reference covers credentials, every supported workflow and endpoint, polling, retries, and the release checklist in one place.

Core concepts

Agents

The reusable definition of who the AI is and what it should accomplish. Everything else references an agent.

Calls

A single phone conversation placed by an agent, inbound or outbound.

Interviews

A browser-based conversation with one candidate — hosted by us, or embedded in your product.

Reports

The structured analysis produced after a call or interview ends: outcomes, captured fields, and scores.

Two ways to run an interview

If you are building a hiring product on top of Rabbitt Voice, you have a choice. Create an interview and send the candidate our hosted link, or mint a short-lived embed token and render the interview inside an iframe in your own app — with your own surrounding UI and full control over when it starts and ends.

The embed guide covers the second path end to end, including the postMessage protocol your page uses to drive the interview and receive live events.

Getting help

Every error carries a machine-readable code and a request_id. Include the request id when you get in touch and we can trace the exact call.