# Human Agent

> Give your AI agent a face — a lifelike visual avatar that speaks, listens, and expresses emotion with ultra-low-latency synchronized animation.

## Overview

The Human Agent is an end-to-end conversational AI application that combines speech-to-speech (STS) with a lifelike animated face powered by Ojin's avatar model [ojin/oris-portrait](/models/oris-portrait.md). Instead of wiring up STT, LLM, TTS, and avatar services yourself, you create an agent in the Ojin dashboard, embed a single widget on your site, and your users get a live, ultra-low-latency conversation with a fully animated avatar.

## Key Features

* **Lifelike visual avatar** — your agent has a face with synchronized lip movements and natural expressions
* **End-to-end conversational AI** — speech in, speech out, no pipeline assembly required
* **Ultra-low latency** — real-time WebRTC transport for audio, video, and signaling
* **No pipeline assembly required** — Ojin manages the full speech-to-speech stack (or bring your own provider)
* **Drop-in widget** — one HTML tag to embed the agent in any web page
* **Dashboard configuration** — create, configure, and monitor agents without writing code

## Agent Modes

### Ojin Agent (managed)

You configure the personality and appearance — system prompt, face, voice, and behaviour. Ojin handles everything else: the conversational pipeline, avatar rendering, and infrastructure. You never see or manage the underlying providers.

### Third-Party Agent

You bring your own speech-to-speech provider — Hume, ElevenLabs Agents, or Ultravox. Ojin adds the visual avatar layer and runs the agent through Ojin infrastructure. You supply your provider API key and config ID in the dashboard; Ojin handles the rest.

## How It Works

1. **Create an agent** in the [Ojin dashboard](https://ojin.ai/dashboard) — pick a mode, configure it, go online
2. **Get your agent ID** from the agent settings page
3. **Embed the widget** on your site or call the Session API from your backend
4. **Your users interact** via WebRTC — audio, video, and real-time avatar in a single connection

## Use Cases

* **Customer Support** — let customers talk to a lifelike agent instead of a chatbot
* **Sales** — greet and qualify leads with a conversational avatar
* **Education** — build interactive tutors with natural speech and expressions
* **Healthcare** — create empathetic virtual health assistants
* **Reception** — deploy a digital receptionist on your website or kiosk

## Pricing

Agent sessions are metered based on usage. Visit [ojin.ai/pricing](https://ojin.ai/pricing) for details on plans and per-session costs.

## Quick Start

1. [**Create an API key**](/getting-started/authentication.md) — set up authentication for the Ojin platform
2. [**Create & configure your agent**](/apps/overview/configure.md) — set up appearance, voice, and behaviour
3. [**Widget Integration**](/apps/overview/widget-integration.md) — drop the agent into your web page
4. [**Session API Reference**](/apps/overview/api-reference.md) — for custom integrations beyond the widget


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.ojin.ai/apps/overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.