AI Voice Agent 401 Error Guide

1python -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 an AI Voice Agent specialized in troubleshooting and resolving '401 Unauthorized' errors for users interacting with web services and APIs. Your persona is that of a knowledgeable and patient technical support assistant. Your primary capabilities include:
14
151. Explaining what a '401 Unauthorized' error means and its common causes.
162. Guiding users through step-by-step troubleshooting processes to resolve '401 Unauthorized' errors.
173. Providing best practices for authentication and authorization in web services.
184. Offering insights into common pitfalls and how to avoid them when dealing with API security.
19
20Constraints and limitations:
21
221. You are not a certified network security professional, and users should consult a qualified expert for complex security issues.
232. You cannot access or modify users' security settings or credentials directly.
243. You must remind users to never share sensitive information, such as passwords or API keys, during interactions.
254. You should always include a disclaimer that the information provided is for educational purposes and users should verify solutions in their specific context."
26
27class MyVoiceAgent(Agent):
28    def __init__(self):
29        super().__init__(instructions=agent_instructions)
30    async def on_enter(self): await self.session.say("Hello! How can I help?")
31    async def on_exit(self): await self.session.say("Goodbye!")
32
33async def start_session(context: JobContext):
34    # Create agent and conversation flow
35    agent = MyVoiceAgent()
36    conversation_flow = ConversationFlow(agent)
37
38    # Create pipeline
39    pipeline = CascadingPipeline(
40        stt=DeepgramSTT(model="nova-2", language="en"),
41        llm=OpenAILLM(model="gpt-4o"),
42        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
43        vad=SileroVAD(threshold=0.35),
44        turn_detector=TurnDetector(threshold=0.8)
45    )
46
47    session = AgentSession(
48        agent=agent,
49        pipeline=pipeline,
50        conversation_flow=conversation_flow
51    )
52
53    try:
54        await context.connect()
55        await session.start()
56        # Keep the session running until manually terminated
57        await asyncio.Event().wait()
58    finally:
59        # Clean up resources when done
60        await session.close()
61        await context.shutdown()
62
63def make_context() -> JobContext:
64    room_options = RoomOptions(
65    #  room_id="YOUR_MEETING_ID",  # Set to join a pre-created room; omit to auto-create
66        name="VideoSDK Cascaded Agent",
67        playground=True
68    )
69
70    return JobContext(room_options=room_options)
71
72if __name__ == "__main__":
73    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
74    job.start()
75

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

1def make_context() -> JobContext:
2    room_options = RoomOptions(
3        name="VideoSDK Cascaded Agent",
4        playground=True
5    )
6    return JobContext(room_options=room_options)
7

1if __name__ == "__main__":
2    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
3    job.start()
4

1python main.py
2