Skip to main content
AI agents: Start here for a structured overview of all available documentation.

​
Talk with our docs

​
What can you build?

LiveAvatar supports real-world applications including:
  • Real-time product demos or virtual sales assistants
  • AI-powered support or training agents
  • Interactive hosts, tutors, or characters
The core component — the LiveAvatar Session — manages streaming user input, feeding responses through language models, and rendering synchronized speech and video.

​
Quickstart

Get a LiveAvatar running on your page in 2 steps.
1

Get your API key

Sign up at app.liveavatar.com and grab your API key from the developers page.
2

Start your first session

Paste your API key and hit Try now to start your first session.
The demo above uses sandbox mode — no credits consumed. See Sandbox Mode for details.

​
What just happened?

When you clicked Try now, we called POST /v2/embeddings with your API key to generate a short-lived embed URL, then loaded it in an iframe. Here’s the equivalent code: 
curl -X POST https://api.liveavatar.com/v2/embeddings \
  -H "X-API-KEY: <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "avatar_id": "65f9e3c9-d48b-4118-b73a-4ae2e3cbb8f0",
    "context_id": "158f5d55-2d4f-11f1-8d28-066a7fa2e369",
    "is_sandbox": true
  }'
The response returns a url and a ready-to-use script tag: 
{
  "code": 1000,
  "data": {
    "url": "https://embed.liveavatar.com/v1/<id>",
    "script": "<iframe src=\"https://embed.liveavatar.com/v1/<id>\" allow=\"microphone\" title=\"LiveAvatar Embed\" style=\"aspect-ratio: 16/9;\"></iframe>"
  },
  "message": "Embed Avatar created successfully"
}
Drop the script value directly into your HTML — it’s a ready-to-use iframe. Or use our embedded url however you like.

​
Make it your own

The embed above is the fastest way to get started, but if you want to build something more tailored — your own UI, custom conversation logic, or a deeper integration into your product — LiveAvatar gives you full control. You can:
  • Bring your own LLM — connect any OpenAI-compatible model or your own inference endpoint
  • Use your own voice — plug in ElevenLabs, Fish Audio, or other TTS providers
  • Control the conversation — switch between conversational and push-to-talk modes
  • Manage the video layer directly — connect via LiveKit or Agora for custom WebRTC handling
  • Build custom UIs — render the avatar stream in your own frontend with the Web SDK
Choose FULL Mode if you want LiveAvatar to handle the AI pipeline end-to-end, or LITE Mode if you want to bring your own conversational stack.

FULL Mode

LiveAvatar manages ASR, LLM, TTS, and WebRTC. You configure and ship.

LITE Mode

Bring your own AI stack. LiveAvatar handles real-time video streaming.
FULL ModeLITE Mode
WebRTCManaged by LiveAvatarYou manage
ASR / STTManaged by LiveAvatarYou provide
LLMManaged (or bring your own)You provide
TTSManaged (or bring your own)You provide
Best forShip fast, less infraFull control, existing pipelines
Credits2 per minute1 per minute

​
Resources

Sandbox Mode

Test without consuming credits.

Web SDK

Official JavaScript SDK.

Migration Guide

Moving from HeyGen Interactive Avatar.