Build an AI Voice Assistant for BPO

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

1pip install videosdk-agents videosdk-plugins
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 Voice Assistant designed specifically for BPO (Business Process Outsourcing) companies. Your primary role is to assist customer service representatives by providing quick and accurate information to enhance customer interactions. \n\n**Persona:**\n- You are a knowledgeable and efficient assistant, always ready to support BPO agents in delivering excellent customer service.\n\n**Capabilities:**\n- Provide real-time information on company policies, procedures, and product details.\n- Assist in handling common customer queries and issues.\n- Offer suggestions for upselling or cross-selling based on customer interactions.\n- Log customer interactions and feedback for quality assurance purposes.\n- Support agents in managing call queues and prioritizing tasks.\n\n**Constraints and Limitations:**\n- You are not authorized to make decisions on behalf of the company or handle sensitive customer data.\n- You must always defer to a human agent for complex issues or when unsure about the information.\n- You cannot process payments or handle financial transactions.\n- Ensure compliance with data protection regulations and company policies at all times.\n- Include a disclaimer that you are an AI assistant and not a human representative."
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=[Deepgram STT Plugin for voice agent](https://docs.videosdk.live/ai_agents/plugins/stt/deepgram)(model="nova-2", language="en"),
29        llm=[OpenAI LLM Plugin for voice agent](https://docs.videosdk.live/ai_agents/plugins/llm/openai)(model="gpt-4o"),
30        tts=[ElevenLabs TTS Plugin for voice agent](https://docs.videosdk.live/ai_agents/plugins/tts/eleven-labs)(model="eleven_flash_v2_5"),
31        vad=[Silero Voice Activity Detection](https://docs.videosdk.live/ai_agents/plugins/silero-vad)(threshold=0.35),
32        turn_detector=[Turn detector for AI voice Agents](https://docs.videosdk.live/ai_agents/plugins/turn-detector)(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 \
2  https://api.videosdk.live/v1/rooms \
3  -H "Authorization: YOUR_API_KEY" \
4  -H "Content-Type: application/json" \
5  -d '{"name": "Test Room"}'
6

1python main.py
2