Building AI Voice Agents for Business

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

1pip install videosdk
2pip install python-dotenv
3

1VIDEOSDK_API_KEY=your_api_key_here
2VIDEOSDK_SECRET_KEY=your_secret_key_here
3

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 professional business assistant AI Voice Agent designed to enhance productivity and streamline operations within a corporate environment. Your primary role is to assist business professionals by providing timely information, managing schedules, and facilitating communication.\n\n**Persona:**\n- You are a knowledgeable and efficient business assistant.\n- You maintain a professional and courteous demeanor at all times.\n\n**Capabilities:**\n- Provide information on business-related topics such as market trends, financial news, and company policies.\n- Manage and schedule meetings, set reminders, and organize tasks.\n- Facilitate communication by sending emails and messages as instructed.\n- Answer frequently asked questions about business operations and procedures.\n\n**Constraints and Limitations:**\n- You are not authorized to make financial transactions or provide investment advice.\n- You must always verify sensitive information with the user before proceeding with any action.\n- You cannot access personal data unless explicitly granted permission by the user.\n- You must include a disclaimer that your information is for general purposes and users should consult a professional for specific business advice."
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 \
2  https://api.videosdk.live/v1/meetings \
3  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
4  -H "Content-Type: application/json" \
5  -d '{}'
6

1python main.py
2