Skip to main content
The Ringg AI API lets your backend do what the dashboard does for day-to-day calling: pick an agent, place calls, run campaigns, read call logs and analytics, and receive results by webhook. Building and editing agents is mostly done in the dashboard; the API covers creating an agent from a prompt and changing selected settings.

Base URL and version

The version (v0) is part of the base URL. Some endpoints have a newer variant with its own path, for example POST /calling/v2/outbound/individual next to POST /calling/outbound/individual.

Resources

Requests

Send the API key in X-API-KEY on every request (see Authentication). Request and response bodies are JSON; set Content-Type: application/json on POST and PATCH requests with a JSON body. Endpoints that take a file (campaign CSVs, knowledge-base documents) use multipart/form-data. Let your HTTP client set that Content-Type so it includes the boundary; setting it by hand breaks the upload.

IDs to store

Errors

Failed requests return a 4xx or 5xx status and a JSON body with the reason in message:
Some endpoints add keys beside message, such as code on Create agent (for example VOICE_LANGUAGE_MISMATCH). A 429 may carry its reason in error instead. Log the status code and the whole body.

Paging

Paging differs by endpoint:

Typical integration order

  1. Check the key with GET /workspace.
  2. Pick an agent with GET /agent/all and a caller number with GET /workspace/numbers.
  3. Place one test call with POST /calling/outbound/individual.
  4. Subscribe the agent to webhook events so results reach your server without polling.
  5. Move to campaigns for lists of people, and to call history and analytics for reporting.

Next steps

Make your first call

From API key to a ringing phone.

Run a campaign by API

Upload a CSV and start calling it.