Voice Agent CRUD API Reference & Documentation

Create, update, retrieve, manage, and delete AI voice agents using Voxentis APIs with examples, endpoints, and workflows.

Endpoints

Method	Path	Description
POST	/agents	Create a new voice agent
GET	/agents	List all agents
GET	/agents/{id}	Get agent by ID
PUT	/agents/{id}	Update agent fields
DELETE	/agents/{id}	Delete an agent
POST	/agents/{id}/clone	Clone an agent

Create Agent

Creates a new voice agent under your tenant. The agent starts in draft status and must be deployed before it can handle calls.

Request Body

Name	Type	Required	Description
name	string	âœ“	Display name of the agent (max 128 chars)
language	string	âœ“	Primary language code, e.g. "en-US", "de-DE"
call_type	string	âœ“	"inbound" or "outbound"
description	string		Brief description of the agent purpose
system_prompt	string		System prompt for the language model
greeting	string		Greeting message spoken at call start
llm_model	string		LLM model identifier (default: gpt-4o-mini)
temperature	number		Sampling temperature 0-2 (default: 0.7)
max_tokens	integer		Max response tokens (default: 1024)
tags	string[]		Metadata tags for filtering

Example

curl -X POST https://api.voxentis.com/v1/agents \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Sales Assistant",
    "language": "en-US",
    "call_type": "outbound",
    "system_prompt": "You are a friendly sales assistant...",
    "greeting": "Hi! Thanks for your time today.",
    "llm_model": "gpt-4o",
    "temperature": 0.6,
    "tags": ["sales", "outbound"]
  }'

Response â€” 201 Created

{
  "id": "agt_9f2k4h1a",
  "name": "Sales Assistant",
  "language": "en-US",
  "call_type": "outbound",
  "status": "draft",
  "version": 1,
  "created_at": "2025-01-15T10:30:00Z"
}