python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

pip install livekit-plugins-simplismart 'livekit-agents[silero]' python-dotenv

SIMPLISMART_API_KEY=your-simplismart-api-key-here
LIVEKIT_URL=your-livekit-url-here
LIVEKIT_API_KEY=your-livekit-api-key-here
LIVEKIT_API_SECRET=your-livekit-api-secret-here

import logging
import os
from dotenv import load_dotenv
from livekit import agents, api
from livekit.agents import AgentSession, Agent
from livekit.plugins import openai, silero, simplismart

load_dotenv()

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger("voice-agent")

# Load Simplismart credentials
SIMPLISMART_API_KEY = os.getenv("SIMPLISMART_API_KEY")
SIMPLISMART_BASE_URL = "https://api.simplismart.live"

# Load LiveKit credentials
LIVEKIT_API_KEY = os.getenv("LIVEKIT_API_KEY")
LIVEKIT_API_SECRET = os.getenv("LIVEKIT_API_SECRET")
LIVEKIT_URL = os.getenv("LIVEKIT_URL")

class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(instructions="You are a helpful voice AI assistant.")

# Initialize Simplismart STT (Speech-to-Text) model
stt = simplismart.STT(
    base_url=f"{SIMPLISMART_BASE_URL}/predict",
    api_key=SIMPLISMART_API_KEY,
    model="openai/whisper-large-v3-turbo"
)

# Initialize Simplismart LLM
llm = openai.LLM(
    model="google/gemma-3-4b-it",
    api_key=SIMPLISMART_API_KEY,
    base_url=SIMPLISMART_BASE_URL,
)

# Initialize Simplismart TTS (Text-to-Speech) model
tts = simplismart.TTS(
    base_url=f"{SIMPLISMART_BASE_URL}/tts",
    api_key=SIMPLISMART_API_KEY,
    model="Simplismart/orpheus-3b-0.1-ft"
)

async def entrypoint(ctx: agents.JobContext):
    logger.info(f"Starting agent in room {ctx.room.name}")
    
    session = AgentSession(
        stt=stt,
        llm=llm,
        tts=tts,
        vad=silero.VAD.load(),
    )
    
    await session.start(
        room=ctx.room,
        agent=Assistant(),
    )
    
    await session.generate_reply(
        instructions="Greet the user and offer your assistance."
    )

if __name__ == "__main__":
    # Generate and display token
    if not LIVEKIT_API_KEY or not LIVEKIT_API_SECRET:
        print("Missing LIVEKIT_API_KEY or LIVEKIT_API_SECRET in .env file")
        print("Get these from your LiveKit Cloud dashboard: https://cloud.livekit.io/")
    else:
        token = api.AccessToken(LIVEKIT_API_KEY, LIVEKIT_API_SECRET) \
            .with_identity("test_user") \
            .with_grants(api.VideoGrants(
                room_join=True,
                room="test_room",
            ))
        
        jwt_token = token.to_jwt()
        
        print("\n\nLiveKit Agent Ready to Connect!\033[0m\n\033[94m" + "="*50 + "\033[0m")
        print(f"\033[94mConnect at: https://agents-playground.livekit.io/\033[0m\n\033[94m")
        print(f"\033[94mURL: {LIVEKIT_URL}\033[0m")
        print(f"\033[94mToken: {jwt_token}\033[0m\n" + "="*50 + "\033[0m")
    
    agents.cli.run_app(agents.WorkerOptions(entrypoint_fnc=entrypoint))

python voice_agent.py dev