Skip to main content
PATCH
/
assistants
/
{id}
cURL
curl --request PATCH \
  --url https://www.getrevox.com/api/assistants/{id} \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>"
}
'
{
  "assistant": {
    "prompt": "<string>",
    "first_sentence": "<string>",
    "first_sentence_mode": "generated",
    "voice": {
      "provider": "cartesia",
      "id": "<string>"
    },
    "webhook_url": "<string>",
    "max_call_duration_secs": 123,
    "structured_output_config": [
      {
        "name": "<string>",
        "type": "string",
        "required": false,
        "description": "<string>",
        "enum_options": [
          "<string>"
        ]
      }
    ],
    "call_retry_config": {
      "calling_window_start_time": "<string>",
      "calling_window_end_time": "<string>",
      "retry_delay_seconds": 7200,
      "max_retry_attempts": 3,
      "timezone": "<string>"
    },
    "background_sound": "audio/office.ogg",
    "id": "<string>",
    "organization_id": "<string>",
    "name": "<string>",
    "created_at": "<unknown>",
    "updated_at": "<unknown>",
    "faq_items": [
      {
        "question": "<string>",
        "answer": "<string>",
        "id": "<string>",
        "needs_human_answer": true,
        "source": "human"
      }
    ],
    "pending_faq_count": 123
  }
}

Headers

​
authorization
string

Bearer auth token. Example: Bearer sk_123...

Path Parameters

​
id
string
required

Body

application/json

Body

​
prompt
string

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

​
first_sentence
string

The first sentence to use for the call. This will be given to the LLM

​
first_sentence_mode
enum<string>

How the first sentence should be handled. "generated" means the LLM will generate a response based on the first_sentence instruction. "static" means the first_sentence will be spoken exactly as provided. "none" means the agent will not speak first and will wait for the user.

Available options:
generated,
static,
none
​
voice
object

The voice to use for the call. You can get the list of voices using the /voices endpoint

​
llm_model
object
​
webhook_url
string

The webhook URL to call when the call is completed.

​
max_call_duration_secs
number

The maximum duration of the call in seconds. This is the maximum time the call will be allowed to run.

​
structured_output_config
object[]

The structured output config to use for the call. This is used to extract the data from the call (like email, name, company name, etc.).

​
call_retry_config
object

Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.

​
background_sound
enum<string> | null

The background sound to play during the call. Useful to give the impression that your AI agent is in an office, in the street, or anywhere else you want.

Available options:
audio/office.ogg
​
faq_items
object[]

FAQ items to associate with this assistant. When provided, replaces all existing FAQ items.

​
name
string

Response

200

​
assistant
object
required