API Trigger

The API Trigger node lets you initiate outbound calls to your voice agent programmatically. When you add an API Trigger node to your workflow, Voice AiLunaPro generates a unique endpoint URL that external systems can call to start a conversation. This is useful when you want to trigger calls from your own backend, a CRM, or workflow tools like n8n and Zapier.

Prerequisites

A configured telephony provider — outbound calls will fail without one
An API key for authentication

Finding your trigger URL

When you add an API Trigger node to your workflow, AiLunaPro assigns it a unique UUID. The trigger node exposes two URLs that share this UUID:

A production URL for the published workflow
A test URL for the latest draft

You can copy either URL from the trigger node’s settings dialog.

POST https://voice-api.ailunapro.com/api/v1/public/agent/{uuid}        # Production
POST https://voice-api.ailunapro.com/api/v1/public/agent/test/{uuid}   # Test

Test vs production

Mode	URL	Runs
Production	`/api/v1/public/agent/{uuid}`	The published version of the agent.
Test	`/api/v1/public/agent/test/{uuid}`	The latest draft. Falls back to the published version if no draft exists.

Use the test URL while iterating on changes so production traffic continues to hit the published version. The production URL only executes a published workflow. If you update the workflow but do not publish it, the production trigger will continue to run the older published version. Once you publish your draft, both URLs run the same definition.

A common pitfall is editing the workflow, saving the draft, and then calling the production trigger URL expecting the new behavior. That will not work until you publish the workflow. Use the test URL to verify draft changes before publishing.

The request body, headers, and response shape are identical for both URLs.

Making a request

Authenticate by passing your API key in the X-API-Key header. The request body requires a phone_number and accepts optional initial_context, telephony_configuration_id, from_phone_number_id, and model_overrides fields.

curl -X POST https://voice-api.ailunapro.com/api/v1/public/agent/{uuid} \
  -H "Content-Type: application/json" \
  -H "X-API-Key: dg_your_api_key" \
  -d '{
    "phone_number": "+14155550100",
    "initial_context": {
      "customer_name": "Jane",
      "appointment_date": "March 15"
    }
  }'

curl -X POST https://voice-api.ailunapro.com/api/v1/public/agent/test/{uuid} \
  -H "Content-Type: application/json" \
  -H "X-API-Key: dg_your_api_key" \
  -d '{
    "phone_number": "+14155550100",
    "initial_context": {
      "customer_name": "Jane",
      "appointment_date": "March 15"
    }
  }'

Use the test URL when you want to verify draft changes before publishing.

Response

A successful request returns a workflow_run_id that you can use to retrieve run details, recordings, and transcripts.

{
  "status": "initiated",
  "workflow_run_id": 12345,
  "workflow_run_name": "WR-API-7823"
}

Error responses

Status	Cause
`400`	Telephony provider not configured, or call failed to initiate
`401`	Missing or invalid API key
`403`	API key does not have access to this agent
`404`	Trigger not found, inactive, or a referenced model configuration or provider connection is unavailable in your organization
`422`	Invalid or incompatible model overrides

Initial context

initial_context is a JSON object containing any information you want your voice agent to access during the call. You can reference these values in your prompts using template variables — values enclosed in {{ and }}. For example, if your request includes:

{
    "phone_number": "+14155550100",
    "initial_context": {
        "user": {
            "name": "John"
        }
    }
}

You can reference the user’s name in your agent prompt as {{user.name}} — in Agent prompts, initial_context fields are referenced directly by name (not prefixed with initial_context.). See template variables for the exact syntax in prompts versus webhook payloads. See Context & Variables for more on how data flows through a call.

Override the greeting for one call

Pass greeting_override inside initial_context to replace the Start Call node’s saved greeting for one API-triggered call. A valid override takes precedence over the saved greeting. If you omit it, AiLunaPro uses the saved greeting; if neither exists, the Start node follows its normal no-greeting behavior. For a text greeting:

{
  "phone_number": "+14155550100",
  "initial_context": {
    "greeting_override": {
      "type": "text",
      "text": "Hi, please confirm account {{account_id}}."
    }
  }
}

For a pre-recorded greeting, pass the recording’s string ID from the Recordings page:

{
  "phone_number": "+14155550100",
  "initial_context": {
    "greeting_override": {
      "type": "audio",
      "recording_id": "callback-welcome"
    }
  }
}

AiLunaPro renders a text override after Pre-Call Data Fetch completes, so the override can reference variables returned by the fetch. The override follows the same playback restrictions as a saved greeting. In particular, static text greetings are not spoken by realtime speech-to-speech models; use an audio override for those configurations. Pre-Call Data Fetch can also return greeting_override. Because fetched context is applied after trigger context, a valid fetched override replaces one supplied by the trigger.

Choosing models for one call

Create provider connections and named model configurations on the Model Configurations page. Copy their UUIDs to select them in model_overrides. Referenced configurations and connections must be active and belong to the trigger’s organization. This request selects a saved setup and customizes its LLM temperature and TTS voice:

{
  "phone_number": "+14155550100",
  "model_overrides": {
    "model_configuration_uuid": "11111111-1111-4111-8111-111111111111",
    "llm": {
      "settings": {
        "temperature": 0.2
      }
    },
    "tts": {
      "settings": {
        "voice": "default"
      }
    }
  }
}

Replace the example UUID with your configuration UUID and choose a voice supported by its TTS provider. Omit model_configuration_uuid to customize the setup already selected by the workflow. To select another connection for one service, provide that service’s provider_connection_uuid:

{
  "phone_number": "+14155550100",
  "model_overrides": {
    "llm": {
      "provider_connection_uuid": "22222222-2222-4222-8222-222222222222",
      "settings": {
        "model": "gpt-4.1-mini",
        "temperature": 0.2
      }
    }
  }
}

This example assumes the selected LLM connection uses OpenAI. Keep credentials, endpoints, cloud project IDs, and regions in the provider connection; they cannot be supplied through settings. The order of precedence is organization default → workflow override → API override → pre-call data fetch override:

Selecting a named configuration starts from that entire saved setup, replacing earlier model choices and parameter changes. Explicit settings in the same override apply afterward.
Selecting another connection for the same provider preserves that service’s parameters. Selecting a different provider starts that service from the new provider’s defaults and your explicit settings.
Settings-only overrides change individual fields. Omitted fields inherit; temperature: null requests the provider default. embeddings: null disables embeddings only when the workflow does not require indexed-document retrieval.
Overrides affect this run. They do not edit saved configurations or workflows.

For realtime mode, the setup must include a realtime connection and a separate text LLM. Pipeline mode requires LLM, STT, and TTS. Multiple AiLunaPro connections may be saved, but the active AiLunaPro services within one run must share a service key. AiLunaPro resolves the organization, workflow, and API-trigger overrides, validates the setup locally, and checks billing and quota before dialing. Invalid settings or references stop the call; validation does not contact model providers to test credentials. The pre-call data fetch runs once the call connects and may still adjust the agent’s LLM, LLM fallback, and TTS. Each run retains its selected model settings and connection references. Credentials are loaded from those connections when a runtime starts, so rotating credentials can affect a prepared call, a later text-chat turn, or post-call analysis. Keep model_overrides outside initial_context. See Pre-Call Data Fetch for selecting models from your own endpoint.

Choosing a telephony configuration and caller ID

By default, calls are placed through your organization’s default outbound telephony configuration. To route a specific call through a different configuration — for example, to dial out from a regional number — pass telephony_configuration_id in the request body.

{
  "phone_number": "+14155550100",
  "telephony_configuration_id": 42
}

The id is shown on each row in Telephony configurations (https://voice.ailunapro.com/telephony-configurations). The configuration must belong to the same organization as the API Trigger; otherwise the request returns 404. To use a specific caller ID from that configuration, also pass from_phone_number_id:

{
  "phone_number": "+14155550100",
  "telephony_configuration_id": 42,
  "from_phone_number_id": 84
}

from_phone_number_id is the ID of a phone number configured under the selected telephony configuration. The number must be active and belong to that configuration; otherwise the request returns 400. You can retrieve configured numbers with List phone numbers.

For full endpoint details including all parameters and response fields, see the API reference.

Getting started

Build your First Agent

Core Concepts

Configurations

Voice Agent Builder

Telephony

Integrations

Prerequisites

Finding your trigger URL

Test vs production

Making a request

Response

Error responses

Initial context

Override the greeting for one call

Choosing models for one call

Choosing a telephony configuration and caller ID

​Prerequisites

​Finding your trigger URL

​Test vs production

​Making a request

​Response

​Error responses

​Initial context

​Override the greeting for one call

​Choosing models for one call

​Choosing a telephony configuration and caller ID

Prerequisites

Finding your trigger URL

Test vs production

Making a request

Response

Error responses

Initial context

Override the greeting for one call

Choosing models for one call

Choosing a telephony configuration and caller ID