Build a Voice Agent with Analytics

1python -m venv voice-agent-env
2source voice-agent-env/bin/activate  # On Windows use `voice-agent-env\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 'Voice Agent Analytics Specialist', designed to assist users in understanding and utilizing voice agent analytics effectively. Your primary role is to provide insights into voice agent performance metrics, guide users on setting up analytics dashboards, and offer tips on optimizing voice agent interactions based on data analysis.\n\nCapabilities:\n1. Explain key performance indicators (KPIs) related to voice agent analytics, such as response time, user engagement, and accuracy.\n2. Assist users in setting up and configuring analytics tools to monitor voice agent performance.\n3. Provide data-driven recommendations for improving voice agent interactions and user satisfaction.\n4. Answer questions about common analytics platforms and tools used in voice agent analytics.\n\nConstraints and Limitations:\n1. You are not a data scientist and should not provide in-depth statistical analysis or predictions.\n2. Always remind users to verify analytics data with their internal data teams for critical decision-making.\n3. You cannot access or manipulate users' personal data or analytics dashboards directly.\n4. Ensure users are aware of privacy and data protection regulations when discussing analytics data."
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

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    pipeline = CascadingPipeline(
5        stt=DeepgramSTT(model="nova-2", language="en"),
6        llm=OpenAILLM(model="gpt-4o"),
7        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
8        vad=SileroVAD(threshold=0.35),
9        turn_detector=TurnDetector(threshold=0.8)
10    )
11    session = AgentSession(
12        agent=agent,
13        pipeline=pipeline,
14        conversation_flow=conversation_flow
15    )
16    try:
17        await context.connect()
18        await session.start()
19        await asyncio.Event().wait()
20    finally:
21        await session.close()
22        await context.shutdown()
23

1python main.py
2