LiveKit is a realtime communication platform that allows you to create voice and video chat applications.

​
Build your AI video agent with LiveKit

We recommend using LiveKit to run your Simli agent. below is a guide to set up your environment and dependencies.
  1. Set up a LiveKit account at LiveKit.io.
You’re gonna a “Video conference” Sandbox project and 3 environment variables from your settings page for later. LiveKit Logo
  1. Create a new folder on your computer: 
    python3 -m venv .venv
source .venv/bin/activate
touch livekit-simli.py
  2. Install dependencies: 
    pip install \
"livekit-agents[openai]" \
"livekit-plugins-simli" \
"python-dotenv"
... etc
  3. Set up your .env file: Create a .env file in your project directory and add your api keys for Simli, Livekit, and other services. For example: 
    LIVEKIT_URL=wss://...
LIVEKIT_API_KEY=...
LIVEKIT_API_SECRET=...

OPENAI_API_KEY=...

SIMLI_API_KEY=...
SIMLI_FACE_ID=...
  4. Fill in your LiveKit runner code: Here’s a simple example of a livekit-simli.py file. Ensure your .env file is in the same directory as this file.
livekit-simli.py
import logging
import os

from dotenv import load_dotenv

from livekit.agents import Agent, AgentSession, JobContext, WorkerOptions, WorkerType, cli
from livekit.plugins import openai, simli

# from livekit.plugins import deepgram, elevenlabs, silero

logger = logging.getLogger("simli-avatar-example")
logger.setLevel(logging.INFO)

load_dotenv()


async def entrypoint(ctx: JobContext):
    session = AgentSession(
        llm=openai.realtime.RealtimeModel(voice="alloy"),
    )

    simliAPIKey = os.getenv("SIMLI_API_KEY")
    simliFaceID = os.getenv("SIMLI_FACE_ID")

    simli_avatar = simli.AvatarSession(
        simli_config=simli.SimliConfig(
            api_key=simliAPIKey,
            face_id=simliFaceID,
        ),
    )
    await simli_avatar.start(session, room=ctx.room)

    # start the agent, it will join the room and wait for the avatar to join
    await session.start(
        agent=Agent(instructions="Talk to me!"),
        room=ctx.room,
    )
  1. Run your bot: 
    python3 livekit-simli.py
    and visit your Sandbox in LiveKit.io to talk to your agent in the browser. You can of course build your own clients that plug into the LiveKit pipeline!
  2. Learn more: For detailed documentation, visit LiveKit’s guide to Simli or keep exploring Simli docs for more insights.