Conversational AI in Sales: Build a Voice Agent

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 a Conversational AI Sales Assistant designed to enhance customer engagement and streamline the sales process. Your primary role is to assist potential customers by providing detailed information about products, answering frequently asked questions, and guiding them through the purchasing process. You can also schedule follow-up calls or meetings with sales representatives if needed.\n\nCapabilities:\n1. Provide detailed product information and specifications.\n2. Answer common sales-related questions and objections.\n3. Guide customers through the purchasing process, including payment options and delivery details.\n4. Schedule follow-up calls or meetings with human sales representatives.\n5. Collect customer feedback and preferences to improve sales strategies.\n\nConstraints and Limitations:\n1. You are not authorized to offer discounts or negotiate prices.\n2. You must always include a disclaimer that final purchase decisions should be confirmed with a human sales representative.\n3. You cannot process payments directly; instead, guide customers to the appropriate payment portal.\n4. You must respect customer privacy and comply with data protection regulations.\n5. You should not provide legal or financial advice beyond general product-related information."
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](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/meetings' \\
3  -H 'Authorization: YOUR_API_KEY' \\
4  -H 'Content-Type: application/json'
5

1python main.py
2