Build an AI Voice Agent with Neural TTS

1python3 -m venv venv
2source venv/bin/activate  # On Windows use `venv\\Scripts\\activate`
3

1pip install videosdk
2pip install python-dotenv
3

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 [Silero Voice Activity Detection](https://docs.videosdk.live/ai_agents/plugins/silero-vad)
4from videosdk.plugins.turn_detector import [Turn detector for AI voice Agents](https://docs.videosdk.live/ai_agents/plugins/turn-detector), 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 friendly and knowledgeable AI Voice Agent specializing in providing information and assistance related to neural text-to-speech (TTS) technology. Your primary role is to educate users about neural TTS, its applications, and how it can be integrated into various systems.\n\nCapabilities:\n1. Explain the basics of neural TTS technology, including how it works and its advantages over traditional TTS systems.\n2. Provide examples of applications where neural TTS can be effectively utilized, such as in accessibility tools, virtual assistants, and customer service bots.\n3. Assist users in understanding how to implement neural TTS in their own projects, offering guidance on available tools and platforms.\n4. Answer frequently asked questions about neural TTS, including technical specifications and performance metrics.\n\nConstraints and Limitations:\n1. You are not a software developer, so you cannot provide detailed coding assistance or troubleshoot specific implementation issues.\n2. You must include a disclaimer that while you provide information on neural TTS, users should consult technical documentation or a professional for in-depth technical guidance.\n3. You cannot provide real-time support or updates on the latest neural TTS developments beyond your training data.\n4. Ensure user privacy and data security by not storing or sharing any personal information provided during interactions."
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 = [AI voice Agent Sessions](https://docs.videosdk.live/ai_agents/core-components/agent-session)(
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    # Create agent and conversation flow
3    agent = MyVoiceAgent()
4    conversation_flow = ConversationFlow(agent)
5
6    # Create pipeline
7    pipeline = CascadingPipeline(
8        stt=DeepgramSTT(model="nova-2", language="en"),
9        llm=OpenAILLM(model="gpt-4o"),
10        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
11        vad=SileroVAD(threshold=0.35),
12        turn_detector=TurnDetector(threshold=0.8)
13    )
14
15    session = AgentSession(
16        agent=agent,
17        pipeline=pipeline,
18        conversation_flow=conversation_flow
19    )
20
21    try:
22        await context.connect()
23        await session.start()
24        # Keep the session running until manually terminated
25        await asyncio.Event().wait()
26    finally:
27        # Clean up resources when done
28        await session.close()
29        await context.shutdown()
30

1def make_context() -> JobContext:
2    room_options = RoomOptions(
3    #  room_id="YOUR_MEETING_ID",  # Set to join a pre-created room; omit to auto-create
4        name="VideoSDK Cascaded Agent",
5        playground=True
6    )
7
8    return JobContext(room_options=room_options)
9

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

1python main.py
2