Perso Interactive delivers natural expressions, accurate lip sync, and smooth back-and-forth dialogue — all processed directly on-device for privacy and low latency. The system is built around a flexible conversational AI pipeline that combines speech recognition, language understanding, and speech generation, and it can be customized with the models you prefer.

🌟 Key Features

Photorealistic AI Avatars

Lifelike visuals and natural facial expressions with precise AI-driven lip sync.

Full Conversational Flow

Speech-to-Text, language generation, and Text-to-Speech working together for seamless interaction.

Flexible Model Integration

Use your chosen STT, LLM, or TTS models within the conversational pipeline.

On-Device Intelligence

Private, fast inference powered by on-device acceleration such as the Apple Neural Engine.

🔨 Install Perso Interactive SDK

Perso Interactive can be used through multiple SDKs, letting you integrate AI avatars into a variety of platforms with minimal setup.

Available SDKs

You can install and use Perso Interactive through:

Web SDK

Install Perso Interactive with the Web SDK.

On-Device SDK

Install Perso Interactive with the on-Device SDK.

Each SDK provides the tools needed to run real-time, on-device conversational experiences using Perso Interactive.

🛠️ Configure Resources using Perso AI Platform

PERSO AI Platform provides customer-facing features for managing resources and configurations for your AI Human Perso Interactive sessions.

Go to Perso AI Platform Resources→

Background Image

Upload and manage background images for your sessions

Prompt

Create and manage prompts for LLM interactions

Document

Upload and manage documents for Retrieval-Augmented Generation (RAG)