Build an AI Voice Agent for Restaurants

1python -m venv myenv
2source myenv/bin/activate  # On Windows use `myenv\\Scripts\\activate`
3

1pip install videosdk-agents videosdk-plugins
2

1import asyncio, os
2from videosdk.agents import Agent, AgentSession, CascadingPipeline, JobContext, RoomOptions, WorkerJob, ConversationFlow
3from videosdk.plugins.silero import SileroVAD
4from videosdk.plugins.turn_detector import TurnDetector, pre_download_model
5from videosdk.plugins.deepgram import DeepgramSTT
6from videosdk.plugins.openai import OpenAILLM
7from videosdk.plugins.elevenlabs import ElevenLabsTTS
8from typing import AsyncIterator
9
10# Pre-downloading the Turn Detector model
11pre_download_model()
12
13agent_instructions = "You are a friendly and efficient AI Voice Agent designed specifically for the restaurant industry. Your primary role is to assist customers by providing information about the restaurant's menu, taking reservations, and answering frequently asked questions about the restaurant's services. You can also provide directions to the restaurant and inform customers about special promotions or events.\n\nCapabilities:\n1. Provide detailed information about menu items, including ingredients and dietary restrictions.\n2. Take and manage reservations, including modifications and cancellations.\n3. Answer common questions about restaurant hours, location, and services offered.\n4. Offer directions to the restaurant using integrated mapping services.\n5. Inform customers about current promotions, events, and special offers.\n\nConstraints and Limitations:\n1. You are not a human and should always identify yourself as an AI Voice Agent.\n2. You cannot process payments or handle financial transactions.\n3. You must include a disclaimer that menu items and prices are subject to change and should be confirmed with the restaurant directly.\n4. You are not responsible for any errors in reservation bookings and should advise users to confirm their reservations with the restaurant.\n5. You cannot provide personal opinions or recommendations beyond the information provided by the restaurant."
14
15class MyVoiceAgent(Agent):
16    def __init__(self):
17        super().__init__(instructions=agent_instructions)
18    async def on_enter(self): await self.session.say("Hello! How can I help?")
19    async def on_exit(self): await self.session.say("Goodbye!")
20
21async def start_session(context: JobContext):
22    # Create agent and conversation flow
23    agent = MyVoiceAgent()
24    conversation_flow = ConversationFlow(agent)
25
26    # Create pipeline
27    pipeline = CascadingPipeline(
28        stt=DeepgramSTT(model="nova-2", language="en"),
29        llm=OpenAILLM(model="gpt-4o"),
30        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
31        vad=SileroVAD(threshold=0.35),
32        turn_detector=TurnDetector(threshold=0.8)
33    )
34
35    session = [AI voice Agent Sessions](https://docs.videosdk.live/ai_agents/core-components/agent-session)(
36        agent=agent,
37        pipeline=pipeline,
38        conversation_flow=conversation_flow
39    )
40
41    try:
42        await context.connect()
43        await session.start()
44        # Keep the session running until manually terminated
45        await asyncio.Event().wait()
46    finally:
47        # Clean up resources when done
48        await session.close()
49        await context.shutdown()
50
51def make_context() -> JobContext:
52    room_options = RoomOptions(
53    #  room_id="YOUR_MEETING_ID",  # Set to join a pre-created room; omit to auto-create
54        name="VideoSDK Cascaded Agent",
55        playground=True
56    )
57
58    return JobContext(room_options=room_options)
59
60if __name__ == "__main__":
61    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
62    job.start()
63

1curl -X POST "https://api.videosdk.live/v1/meetings" \
2-H "Authorization: Bearer YOUR_API_KEY" \
3-H "Content-Type: application/json"
4

1python main.py
2