Skip to main content
FULL Mode handles the complete real-time chat infrastructure, automating the tasks that typically require complex manual setup:
  • Voice Activity Detection (VAD) — detects when the user is speaking
  • Speech-to-Text (STT) — transcribes user audio
  • Large Language Models (LLM) — generates responses
  • Text-to-Speech (TTS) — converts responses to natural speech

​
When to use FULL Mode

FULL Mode is ideal if you want to:
  • Delegate WebRTC orchestration and infrastructure management
  • Avoid building and maintaining a real-time AI pipeline across audio input, inference, and output
  • Ship products faster without managing model coordination, streaming latency, or state management
By delegating the entire real-time stack to LiveAvatar, you can focus on designing your product and user experience.

​
Getting started

1

Create a session token

Configure your avatar, voice, context, and interactivity type in a session token. Set mode to "FULL".
2

Start the session

Call the start session endpoint to initialize the WebRTC room.
3

Connect and interact

Join the LiveKit room from your frontend and begin the conversation.

​
Learn more

Lifecycle

Understand the three phases of a FULL Mode session.

Configuration

Customize avatar, voice, context, and interactivity.

Voice Settings

Fine-tune TTS provider settings.

Events

Command and response events reference.