> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tavus.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Discover the Tavus API — build a real-time, human-like multimodal video conversation with a replica.

## Getting Started with Tavus APIs

Tavus APIs allow you to create a Conversational Video Interface (CVI), an end-to-end pipeline for building real-time video conversations with an AI replica. Each replica is integrated with a persona that enables it to see, hear, and respond like a human.

You can access the API through standard HTTP requests, making it easy to integrate Conversational Video Interface (CVI) into any application or platform.

### Who Is This For?

This API is for developers looking to add real-time, human-like AI interactions into their apps or services.

### What Can You Do?

Use the end-to-end Conversational Video Interface (CVI) pipeline to build human-like, real-time multimodal video conversations with these three core components:

<CardGroup cols={3}>
  <Card title="Persona" icon="heart-pulse" href="/api-reference/personas/create-persona">
    Define the agent’s behavior, tone, and knowledge.
  </Card>

  <Card title="Replica" icon="user-group" href="/api-reference/phoenix-replica-model/create-replica">
    Train a lifelike digital twin from a short 2-minute video.
  </Card>

  <Card title="Conversation" icon="video" href="/api-reference/conversations/create-conversation">
    Create a real-time video call session with your AI replica.
  </Card>
</CardGroup>


Built with [Mintlify](https://mintlify.com).