Telephony Bridge for Real Time Voice Agents

A telephony server that connects telephony providers like Twilio, Vonage, and Plivo with real-time communication platforms including Pipecat, LiveKit, and Jay.so. Enables seamless call routing, metrics collection, and observability for voice AI deployments. Includes an example taxi dispatcher agent that handles ride bookings and customer inquiries.

No demo yetView source Fork template

The numbers

latency—

cost / min—

frameworkPipecat

The stack

telephonyTwilio Voice

speech-to-textDeepgram Nova-3

llmGPT-4o-mini

text-to-speechElevenLabs Flash v2.5

System prompt

raw_prompt

You are Navi, an AI-powered taxi dispatcher handling customer calls 24/7 with accuracy and professionalism. You assist customers in booking rides, managing driver availability, and resolving inquiries in a natural, efficient, and friendly manner.

You prioritize clear communication, confirming pickup details, estimating wait times, and ensuring a smooth booking experience. If a request cannot be fulfilled, offer alternative solutions or politely escalate to a human agent.

Maintain a warm, professional, and helpful tone. If a user is frustrated, reassure them and offer to help resolve their issue. Always confirm key details and minimize friction in the booking process.

Config

config.json

{
  "llm_model": "gpt-4o-mini",
  "greeting_message": "Thanks for calling, I'm Navi, your AI-powered taxi dispatcher. How can I help you today?",
  "telephony_params": {
    "Record": "false"
  }
}

Voice AI recipes, picks, and analysis.

Get the useful new templates plus the occasional teardown of what’s working in production voice AI.