voice-telephony

Route voice calls via Twilio, Telnyx, and Plivo with streaming STT/TTS.

1|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/framerslab/agentos-skills --skill voice-telephony
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: voice-telephony
Source: https://github.com/framerslab/agentos-skills/tree/main/registry/curated/voice-telephony
Command: npx skills add https://github.com/framerslab/agentos-skills --skill voice-telephony

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires twilio, telnyx, plivo, deepgram, whisper, google-cloud, vosk, elevenlabs, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive solution for voice call routing, integrating various telephony providers and streaming STT/TTS services, simplifying the setup and management of voice pipelines.

Core Features & Use Cases

  • Telephony Provider Integration: Seamlessly integrate Twilio, Telnyx, and Plivo for call routing.
  • STT and TTS Streaming: Connect to Deepgram, Whisper, Google Cloud, Vosk, and ElevenLabs for real-time speech-to-text and text-to-speech.
  • IVR Setup: Configure interactive voice response systems for efficient call handling.
  • Use Case: Create a voice assistant that can handle customer inquiries over the phone, using Twilio for call routing and Deepgram for real-time speech-to-text processing.

Quick Start

Set up voice call routing to a Twilio number using the voice-telephony skill with STT from Deepgram and TTS from ElevenLabs.

Frequently Asked Questions about voice-telephony

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up an IVR system with Twilio for real-time voice call routing?

You can set up an IVR system by integrating Twilio for voice call routing and connecting it to streaming STT and TTS services. This Skill handles the telephony provider integration and speech processing pipeline configuration for you.

How does real-time speech-to-text streaming work during a telephony voice call?

Real-time STT streaming works by routing live telephony audio from providers like Telnyx or Plivo to speech processing engines such as Deepgram, Whisper, or Google Cloud, which transcribe the audio stream on the fly for immediate response handling.

Can I use ElevenLabs for text-to-speech streaming in a Plivo voice pipeline?

Yes, you can use ElevenLabs for TTS streaming within a Plivo voice pipeline. The Skill supports connecting multiple telephony providers with various TTS engines to generate real-time spoken audio for callers.

Do I need API credentials for both telephony and speech processing to build a voice assistant?

Yes, you need active telephony API credentials from Twilio, Telnyx, or Plivo, plus speech processing service keys from providers like Deepgram or Vosk to establish live voice call routing and real-time conversation pipelines.

What is the best way to integrate Deepgram STT with Twilio for handling customer phone inquiries?

The best way is using a dedicated voice telephony pipeline that bridges Twilio's call routing audio stream directly to Deepgram's real-time STT API, enabling your voice assistant to process customer inquiries instantly over the phone.

Are there limitations when using open-source STT like Vosk instead of Google Cloud for telephony pipelines?

Using Vosk for STT in telephony pipelines may require self-hosting and managing the speech processing infrastructure, whereas Google Cloud and Deepgram provide managed streaming APIs, affecting latency and maintenance requirements for your voice routing setup.

Related Skills