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

# Overview

Perso Interactive On-Device SDK brings real-time conversational AI and photorealistic human avatars entirely on-device, powered by Apple Neural Engine for private, low-latency experiences.

The Perso Interactive On-Device SDK enables developers to create fully interactive AI conversations with photorealistic human avatars, featuring natural facial expressions and on-device AI Lip Sync.\
The SDK includes a complete conversational pipeline — Speech-to-Text (STT) → Large Language Model (LLM) → Text-to-Speech (TTS) — all running privately on-device with minimal latency using the Apple Neural Engine (ANE).

> ## **Perso Interactive On-Device SDK Documentation**
>
> Learn how to install and fully configure Perso Interactive On-Device SDK.
>
> [<u>Explore Perso Interactive On-Device SDK Documentation→</u>](https://perso-ai.github.io/perso-interactive-ondevice-sdk-swift/)

## **Key Features**

<Card title="Realistic AI Human Avatars" icon="user-tie-hair-mullet">
  Photorealistic avatars with natural facial expressions and real-time AI Lip Sync.
</Card>

<Card title="Conversational AI Pipeline" icon="message-bot">
  A flexible STT → LLM → TTS pipeline that powers fully interactive AI conversations.
</Card>

<Card title="Customizable Architecture" icon="wrench">
  Integrate your own Speech-to-Text, Large Language Model, and Text-to-Speech components.
</Card>

<Card title="Fully On-Device Processing" icon="server">
  Runs entirely on-device using the Apple Neural Engine, ensuring privacy and low latency.
</Card>