Skip to navigation

Introduction

The complete voice AI platform for enterprise telephony

Levrage.AI is a no-code platform that lets you hire, train, and deploy AI voice agents for your business. Our API gives you programmatic access to create agents, make calls, run batch campaigns, and analyze results — all without building voice infrastructure from scratch.

What can you do with this API?

Create Voice Agents

Build AI agents for sales, support, collections, appointment booking, and 200+ specialized roles across 22 industries.

Make Calls

Initiate outbound calls to any phone number with your configured agent. Calls connect in seconds.

Run Campaigns

Launch batch calling campaigns with up to 2,000 contacts, automatic retries, scheduling, and blackout windows.

Analyze Results

Access call history, full transcripts, recordings, AI sentiment analysis, and structured data collection.

Everything in the API

106 endpoints in 17 areas, all on https://api.levrage.ai/v1 with the same API key. Each area opens its section of the API Reference.

AreaWhat you can doEndpoints
AgentsCreate, change and delete voice agents; read and save their instructions7
Prompt VersionsSave, list and restore versions of an agent’s instructions5
VoicesThe voices and languages an agent can speak2
SkillsReady-made skills an agent can use, and a preview of what each adds2
ConfigurationThe industries to start an agent from1
CallsPlace a call, read call history and transcripts, export to CSV4
CampaignsCall a list of contacts — create, follow, pause, resume, cancel6
NumbersYour phone numbers, connecting your own, and which agent answers each7
CRMPush leads in (one or 500 at a time), update them, read their timeline11
KnowledgeKnowledge bases your agents search during calls — notes, web pages, files, Q&A20
ToolsActions an agent can take during a call (your APIs), and attaching them8
MCP serversConnect MCP servers and give agents their tools9
Call flowsStep-by-step call flows5
AutomationsFollow-ups that run after calls and on events8
TestingTest scenarios, chat test runs and simulated calls8
UploadsFiles you uploaded, used by id for campaigns and knowledge2
AccountYour plan, this month’s allowances and the wallet1

Platform at a Glance

Industries22 — Real Estate, Finance, Healthcare, Insurance, E-commerce, Education, Legal, and more
Agent Templates200+ pre-built agent types with industry-specific prompts
Languages9 — English, Hindi, Hinglish, Bengali, Tamil, Telugu, Kannada, Malayalam, Gujarati
AI Modelslai-premium-2 (latest) — optimized for low-latency voice conversations
Batch CampaignsUp to 2,000 contacts per campaign with concurrency control
WebhooksReal-time CALL_ENDED events with transcripts, recordings, and collected data

Base URL

https://api.levrage.ai/v1

Authentication

All API requests require a Bearer token. Include your API key in the Authorization header:

curl -H "Authorization: Bearer lev_YOUR_API_KEY" \
https://api.levrage.ai/v1/agents

Get your API key from Levrage.AI Studio → Settings → Developers → API Keys.

Quick Example

Create a voice agent and make a call in two API requests:

import requests
API_KEY = "lev_YOUR_API_KEY"
BASE = "https://api.levrage.ai/v1"
headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}
# 1. Create an agent
agent = requests.post(f"{BASE}/agents", headers=headers, json={
"name": "My Sales Agent",
"agent_type": "sales",
"language": "English",
"voice": "female",
"start_flow": "Hello! I am calling from Acme Corp. Am I speaking with the right person?",
"end_flow": "Thank you for your time. Have a great day!"
}).json()
agent_id = agent["data"]["id"]
# 2. Make a call
call = requests.post(f"{BASE}/call", headers=headers, json={
"agent_id": agent_id,
"source_number": "+919240018601",
"phone_number": "+919876543210"
}).json()
print(f"Call initiated: {call['data']['id']}")

Response Format

All responses follow a consistent envelope:

{
"success": true,
"data": { ... },
"request_id": "req_abc123",
"timestamp": "2025-01-01T12:00:00Z"
}

Error responses:

{
"success": false,
"error": {
"code": "validation_error",
"message": "Agent name is already in use"
},
"request_id": "req_abc123",
"timestamp": "2025-01-01T12:00:00Z"
}

Next Steps