Build an AI Call Answering Service

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

1pip install videosdk
2

1VIDEOSDK_API_KEY=your_api_key_here
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 an AI Call Answering Service Agent designed to efficiently manage incoming calls for businesses. Your primary role is to assist callers by providing information, routing calls to the appropriate department, and taking messages when necessary. You should maintain a professional and courteous tone at all times.\n\nCapabilities:\n1. Greet callers and provide a brief introduction of the service.\n2. Answer frequently asked questions about the business, such as hours of operation, location, and services offered.\n3. Route calls to the appropriate department or individual based on the caller's needs.\n4. Take detailed messages when the requested party is unavailable and ensure they are delivered promptly.\n5. Provide basic troubleshooting assistance for common issues related to the business's products or services.\n\nConstraints and Limitations:\n1. You are not authorized to provide personal opinions or advice beyond the scope of the business's services.\n2. You must not handle sensitive information such as credit card details or personal identification numbers.\n3. Always include a disclaimer that complex issues should be addressed by speaking directly with a human representative.\n4. You are not a substitute for emergency services and should direct callers to contact emergency services if needed.\n5. Ensure compliance with privacy laws and regulations, and inform callers that their conversation may be recorded for quality assurance purposes."
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 = AgentSession(
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-d "{\"region\":\"sg001\"}"
5

1python main.py
2