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

# Overview

> Build interactive real-time conversational digital humans with WebSocket-based API

<Hero title="Real-time Digital Human API" subtitle="Create engaging real-time conversations with human-like digital avatars. Powered by direct audio-to-audio processing for the fastest response times." />

**NavTalk Real-time Digital Human API** enables you to build interactive conversational experiences with digital avatars that respond in real-time through WebSocket connections. With **sub-500ms latency** and seamless interruption handling, create natural, human-like interactions that feel truly conversational.

## Core Features

<CardGroup cols={3}>
  <Card title="Ultra-Low Latency" icon="bolt">
    Sub-500ms end-to-end response times for real-time conversations
  </Card>

  <Card title="Real-time Rendering" icon="video">
    Frame-accurate lip sync and emotion-driven facial expressions
  </Card>

  <Card title="Natural Conversations" icon="comments">
    Human-like dialogue with emotional intelligence and empathetic responses
  </Card>

  <Card title="Multilingual Support" icon="language">
    Over 50 languages with 95%+ recognition accuracy, seamless language switching
  </Card>

  <Card title="Context Management" icon="database">
    Maintain conversation history and context across sessions
  </Card>

  <Card title="Preset Characters" icon="user">
    Ready-to-use digital avatars for various use cases and industries
  </Card>

  <Card title="Custom Characters" icon="wand-magic-sparkles">
    Create and deploy your own custom digital character avatars
  </Card>

  <Card title="Knowledge Base Integration" icon="book">
    Connect enterprise or personal knowledge bases for expert-level, context-aware responses
  </Card>

  <Card title="Function Calling" icon="code">
    Integrate external APIs and execute custom functions during conversations
  </Card>
</CardGroup>

## Unified WebSocket Architecture

NavTalk uses a **single unified WebSocket connection** that handles all real-time communication, including:

* **Real-time API communication** - Audio input streaming and text/audio responses
* **WebRTC signaling** - Video stream setup and ICE candidate exchange
* **Session management** - Configuration and conversation history

This unified approach provides several key advantages:

<AccordionGroup>
  <Accordion title="Simplified Integration" icon="plug">
    Only one WebSocket connection to manage, reducing complexity and potential connection issues. No need to coordinate multiple connections or handle separate WebRTC signaling channels.
  </Accordion>

  <Accordion title="Better Performance" icon="rocket">
    Reduced connection overhead and improved reliability with a single persistent connection. All communication flows through one optimized channel.
  </Accordion>

  <Accordion title="Easier Debugging" icon="bug">
    All events and messages flow through a single connection, making it easier to monitor, log, and debug issues in your application.
  </Accordion>

  <Accordion title="Automatic Synchronization" icon="sync">
    WebRTC signaling is automatically synchronized with the audio stream, eliminating timing issues and ensuring smooth audio-video synchronization.
  </Accordion>
</AccordionGroup>

## How It Works

The Real-time Digital Human API uses a **direct audio-to-audio processing pipeline** that eliminates traditional text conversion steps (STT and TTS), delivering unprecedented speed and natural conversation flow.

<AccordionGroup>
  <Accordion title="1. Audio Input" icon="microphone">
    Your application captures user audio input and sends audio streams through WebSocket connections. This layer handles real-time audio streaming and ensures continuous bidirectional communication for seamless dialogue.
  </Accordion>

  <Accordion title="2. Direct Processing" icon="bolt">
    GPT-realtime processes audio signals directly without text conversion steps. By eliminating Speech-to-Text (STT) and Text-to-Speech (TTS) transformations, the system achieves sub-500ms latency and enables natural interruption handling.
  </Accordion>

  <Accordion title="3. Audio Output" icon="volume-high">
    The processed audio response is generated in real-time and synchronized with video rendering. This layer delivers high-quality audio output with preserved fidelity, maintaining natural voice tone and emotional nuances.
  </Accordion>

  <Accordion title="4. Visual Rendering" icon="video">
    Frame-accurate lip sync and emotion-driven facial expressions are rendered in real-time, creating a lifelike visual presence synchronized with the audio output.
  </Accordion>
</AccordionGroup>

## Try Our Demo

We provide simple, single-page demos in multiple languages and platforms that you can clone and run with one click. To get started:

1. **Register for an account** and obtain your API key from the [dashboard](https://console.navtalk.ai/#/projects)
2. **Clone the Samples repository**: `git clone https://github.com/navtalk/Samples.git`
3. **Configure your API key** in the demo files
4. **Run the demo** — each demo is a single-page application that works immediately

The [Samples repository](https://github.com/navtalk/Samples.git) includes ready-to-run examples for Web, Python, JavaScript, and other platforms to help you get started quickly.