Build AI Voice Agent for Appointments

1python3 -m venv venv
2source venv/bin/activate  # On Windows use `venv\\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 a helpful appointment booking assistant designed to assist users in scheduling appointments efficiently. Your primary role is to facilitate the booking process by understanding user requests, providing available time slots, and confirming appointments. You can also answer basic questions related to the appointment process, such as cancellation policies or rescheduling options. However, you are not a medical professional and cannot provide medical advice or diagnose conditions. Always include a disclaimer advising users to consult a qualified professional for medical-related inquiries. Your interactions should be polite, concise, and focused on resolving the user\'s request as efficiently as possible. You must ensure user data privacy and adhere to all relevant data protection regulations."
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: YOUR_VIDEOSDK_API_KEY" \\
4  -H "Content-Type: application/json"
5

1class MyVoiceAgent(Agent):
2    def __init__(self):
3        super().__init__(instructions=agent_instructions)
4    async def on_enter(self): await self.session.say("Hello! How can I help?")
5    async def on_exit(self): await self.session.say("Goodbye!")
6

1pipeline = CascadingPipeline(
2    stt=DeepgramSTT(model="nova-2", language="en"),
3    llm=OpenAILLM(model="gpt-4o"),
4    tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
5    vad=SileroVAD(threshold=0.35),
6    turn_detector=TurnDetector(threshold=0.8)
7)
8

1async def start_session(context: JobContext):
2    agent = MyVoiceAgent()
3    conversation_flow = ConversationFlow(agent)
4
5    pipeline = CascadingPipeline(
6        stt=DeepgramSTT(model="nova-2", language="en"),
7        llm=OpenAILLM(model="gpt-4o"),
8        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
9        vad=SileroVAD(threshold=0.35),
10        turn_detector=TurnDetector(threshold=0.8)
11    )
12
13    session = AgentSession(
14        agent=agent,
15        pipeline=pipeline,
16        conversation_flow=conversation_flow
17    )
18
19    try:
20        await context.connect()
21        await session.start()
22        await asyncio.Event().wait()
23    finally:
24        await session.close()
25        await context.shutdown()
26
27def make_context() -> JobContext:
28    room_options = RoomOptions(
29        name="VideoSDK Cascaded Agent",
30        playground=True
31    )
32
33    return JobContext(room_options=room_options)
34
35if __name__ == "__main__":
36    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
37    job.start()
38

1python main.py
2