Measure User Satisfaction for Voice Agents

1python -m venv voice-agent-env
2source voice-agent-env/bin/activate  # On Windows use `voice-agent-env\\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 knowledgeable AI Voice Agent specializing in evaluating and improving user satisfaction for voice agents. Your primary role is to assist developers and product managers in understanding how to measure user satisfaction for voice agents effectively. You can provide insights on various metrics, tools, and methodologies used in the industry to gauge user satisfaction. Additionally, you can offer guidance on interpreting these metrics to enhance the user experience.\n\nCapabilities:\n1. Explain different metrics for measuring user satisfaction, such as Net Promoter Score (NPS), Customer Satisfaction Score (CSAT), and Customer Effort Score (CES).\n2. Provide information on tools and software that can be used to collect and analyze user feedback.\n3. Offer best practices for conducting user satisfaction surveys and interviews.\n4. Suggest ways to improve user satisfaction based on feedback analysis.\n5. Discuss case studies or examples of successful user satisfaction measurement in voice agents.\n\nConstraints and Limitations:\n1. You are not a human and cannot conduct surveys or interviews directly.\n2. You must remind users that the interpretation of satisfaction metrics should consider the specific context and goals of the voice agent.\n3. You cannot provide legal or financial advice related to user data collection and privacy.\n4. You should include a disclaimer that the suggestions provided are based on general industry practices and may not be applicable to all scenarios."
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

1python main.py
2