Place a call | Revox API

import requests
url = "https://www.getrevox.com/api/call"
payload = { "phone_number": "string" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())

{
  "call": {
    "id": "string",
    "from_phone_number": "string",
    "to_phone_number": "string",
    "direction": "inbound",
    "is_completed": true,
    "is_cancelled": true,
    "calls_count": 1.1,
    "next_call_at": null,
    "last_call_attempt": {
      "id": "string",
      "phone_number": "string",
      "status": "queued",
      "result": "IVR",
      "recording_url": "string",
      "started_at": null,
      "answered_at": null,
      "ended_at": null,
      "transcript": [
        {
          "role": "user",
          "content": "string",
          "tool_name": "string",
          "tool_arguments": {},
          "tool_is_error": true
        }
      ],
      "structured_output": {}
    },
    "call_retry_config": {
      "calling_windows": [
        {
          "calling_window_start_time": "string",
          "calling_window_end_time": "string",
          "retry_delay_seconds": 7200
        }
      ],
      "max_retry_attempts": 3,
      "timezone": "string"
    },
    "llm_model": {
      "type": "string",
      "name": "gpt-4.1"
    },
    "call_attempts": [
      {
        "id": "string",
        "phone_number": "string",
        "status": "queued",
        "result": "IVR",
        "recording_url": "string",
        "started_at": null,
        "answered_at": null,
        "ended_at": null,
        "transcript": [
          {
            "role": "user",
            "content": "string",
            "tool_name": "string",
            "tool_arguments": {},
            "tool_is_error": true
          }
        ],
        "structured_output": {}
      }
    ],
    "created_at": null,
    "metadata": {},
    "first_sentence_delay_ms": 1,
    "scheduled_at": null
  }
}

Place a new call order. A call order can be resolved over multiple call attempts spanning up to a few days.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

Body

phone_numberstringRequired

The phone number to call in the E.164 format. Example: +1234567890

force_nowbooleanOptional

The prompt to use for the call. This will be given to the LLM (gpt-4.1)

from_phone_numberstringOptional

The phone number to use for making the call (e.g., +1234567890). If not provided, uses the default trunk.

prompt_variablesmap from strings to stringsOptional

Variables to interpolate into the prompt. Wether you use an assistant_id or an assistant object, this will be used to interpolate the variables into the prompt.

metadatamap from strings to stringsOptional

Metadata to store with the call.

assistant_idstringOptional

The ID of the assistant to use for this call.

assistantobjectOptional

You can provide a custom assistant configuration here. If you don’t provide an assistant_id, this assistant object will be used for this call.

concurrencyobjectOptional

Limit the number of concurrent calls for a given concurrency key.

scheduled_atdatetime or anyOptional

Schedule the call to start at a specific date and time (ISO 8601 format). If not provided, the call will start immediately.

Response

200

callobject

This represent a call "order" that was requested by the user. A call order can be resolved over multiple call attempts spanning up to a few days.