Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.liveavatar.com/llms.txt

Use this file to discover all available pages before exploring further.

Voice settings are configured under avatar_persona.voice_settings when creating a session token. LiveAvatar supports two TTS providers.

​
Shared Settings

These apply to all providers:
ParameterTypeRangeDefaultDescription
speednumber0.8–1.21Speaking speed. Below 1 slows down, above 1 speeds up.

​
ElevenLabs

ParameterTypeRangeDefaultDescription
stabilitynumber0–10.75Voice consistency. Higher = more predictable.
similarity_boostnumber0–10.75Likeness to original voice.
stylenumber0–10Style intensity exaggeration.
use_speaker_boostboolean—trueVoice clarity enhancement.
modelstring——eleven_flash_v2_5 (low latency) or eleven_multilingual_v2.

​
Fish Audio

Fish Audio is currently in beta. Supports English, Chinese, and Japanese only.
ParameterOptionsDefaultDescription
latency_modebalanced, normalbalancedSpeed vs. quality tradeoff.
models1, s2s2Speech generation model.

​
Example

{
  "avatar_persona": {
    "voice_id": "<voice_id>",
    "voice_settings": {
      "speed": 1.0,
      "stability": 0.8,
      "similarity_boost": 0.75,
      "model": "eleven_flash_v2_5"
    }
  }
}