Skills
.Work. You
Rest

voice-ai

Community

Ultra-low-latency voice agents for real-time calls.

Software Engineering#llm#tts#twilio#telephony#stt#low-latency#voice-ai
AuthorScientiaCapital
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Production-ready voice AI pipelines enable real-time, end-to-end voice conversations in telephony contexts with sub-500ms latency, bridging STT, LLM, and TTS.

Core Features & Use Cases

  • Streaming STT (Deepgram Nova-3) for near real-time transcription
  • Streaming LLM (Groq llama-3.1-8b-instant) for fast responses
  • Streaming TTS (Cartesia Sonic) with emotion controls and bilingual support
  • Twilio Media Streams integration for low-latency audio transport
  • Bilingual English/Spanish support for IVR and call-centers

Quick Start

Run the quick-start to deploy a production voice pipeline with streaming STT, LLM, and TTS.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: voice-ai
Download link: https://github.com/ScientiaCapital/skills/archive/main.zip#voice-ai

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.