Simli

Simli is an avatar plugin. It renders a real-time, lip-synced AI avatar video track from the agent’s speech.

Setup

Set your Simli API key in the worker environment. Generate a key from the Simli dashboard:

export SIMLI_API_KEY=<key>

Usage

Import the plugin and pass it to the pipeline’s avatar slot.

from zrt.plugins import SimliAvatar

avatar = SimliAvatar(
    face_id="<face-id>",   # falls back to SIMLI_FACE_ID / a default
)

# Pipeline(avatar=avatar, ...)

Parameters

Parameter	Type	Default	Description
`api_key`	`str`	`None`	Simli API key. Falls back to the `SIMLI_API_KEY` environment variable when unset.
`face_id`	`str`	`""`	Identifier of the face to render. Falls back to the `SIMLI_FACE_ID` environment variable, then to a built-in default face when empty.
`model`	`str`	`None`	Optional Simli model identifier for the avatar.
`is_trinity`	`bool`	`False`	Set to `True` when the face ID belongs to a Trinity avatar, to keep lip-sync correct.

The avatar renders the TTS output as a lip-synced video track in the room.

Azure Voice Live Anam

Plugins

Inference Gateway

Speech-to-text

LLM

Text-to-speech

Realtime models

Avatars

Turn detection

Voice activity detection

Noise cancellation

Setup

Usage

Parameters

​Setup

​Usage

​Parameters

Setup

Usage

Parameters