Skip to main content
FULL Mode provides four customizable layers for your LiveAvatar session.

​
Avatar (Visual Layer)

Defines what the avatar looks like. Choose from a wide selection of avatars, each with unique styles, appearances, and expressions. Each avatar has a unique avatar_id. Browse available avatars through the List Public Avatars or List User Avatars endpoints.

​
Voice (Audio Layer)

Defines what the avatar sounds like. Voices vary by gender, age, tone, and accent. The voice_settings parameter enables fine-grained audio control for speed, style, and stability. See Configuring Voice Settings for provider-specific options.

​
Context (Cognitive Layer)

Defines how the avatar thinks and responds. The context layer controls:
  • Available information and knowledge
  • Response constraints and guardrails
  • Personality traits
  • Opening text (spoken at session start)
  • Instructions for response generation
If no context is supplied, the avatar operates in restricted mode — it will not respond to user input. User transcripts are still emitted, but the avatar can only repeat pre-set phrases.

​
Interactivity Type (Conversational Layer)

Controls how user input is registered and when the avatar responds.

​
Conversational (default)

The system manages conversation flow automatically based on speech pauses and user interruptions.

​
Push-to-Talk

You control exactly when user input is registered by signaling start/stop events. VAD and ASR are disabled until you signal. See Push-to-Talk for details.

​
Video Settings

These settings apply to both FULL and LITE modes.

​
Quality

The quality parameter controls output resolution:
ValueResolution
very_high1080p
high (default)720p
medium480p
low360p
Higher resolution increases streaming latency. Use high or medium for most real-time applications.

​
Encoding

The encoding parameter controls the video codec: VP8 or H264.