⚗ AI & Voice Agents

Complete guide to ai & voice agents for ViciDial and Asterisk. 10 in-depth tutorials covering everything from basics to advanced production setups.

10 Tutorials

Building an AI-Powered VoIP Call Quality Analysis Service Advanced · 40 min

Score call audio quality automatically with a FastAPI service that combines the NISQA neural model, Silero VAD, and Claude for plain-English verdicts.

Building a Real-Time AI Voice Agent for Asterisk Advanced · 44 min

Build a real-time AI voice agent that answers Asterisk calls: AudioSocket streaming into Deepgram STT, a Groq LLM, and Cartesia TTS replies.

ElevenLabs Cloud Voice Agent with Asterisk SIP Integration Advanced · 46 min

Connect ElevenLabs conversational AI agents to real phone calls over SIP, with webhook tools and dynamic call context injection.

Call Recording Transcription with Faster-Whisper Intermediate · 27 min

Batch transcription of ViciDial call recordings using Faster-Whisper (OpenAI Whisper optimized with CTranslate2) for speech-to-text at scale — on CPU, without cloud APIs.

AI Voice Agent Prompt Engineering & Conversation Design Intermediate · 58 min

Design voice-agent personalities, conversation flows, and tool-calling workflows using patterns mined from real call transcriptions.

Voice Agent Tech Stack Comparison: Local vs Cloud with Shared Booking Backend Advanced · 42 min

ElevenLabs cloud vs a local Deepgram, Groq and Cartesia stack for voice agents: architecture, latency, cost per call, and migration path.

QA Pipeline — Call Transcription + AI Quality Scoring Advanced · 71 min

Build an automated quality assurance pipeline that transcribes every inbound call using Faster-Whisper and scores agent performance with AI — running entirely on your existing ViciDial server with zero impact on live calls.

AI Voice Agent — OpenAI Realtime API + Asterisk Advanced · 76 min

Build a production voice agent with OpenAI's native speech-to-speech Realtime API wired into Asterisk through AudioSocket.

Real-Time Call Transcription & Sentiment Dashboard Advanced · 89 min

Build a live dashboard that transcribes active calls and shows per-call sentiment in real time, using faster-whisper and a lightweight web UI.

AI-Powered Answering Machine Detection — Whisper + ML Classifier Advanced · 82 min

Build a self-hosted answering machine detection (AMD) system that replaces Asterisk's built-in `AMD()` application with a Whisper-based speech recognition + machine learning classifier pipeline. Traditional AMD relies on energy detection and cadence analysis, achieving only 60-70% accuracy in real-world conditions — misclassifying live humans as machines (killing revenue-generating calls) and letting voicemail greetings through to agents (wasting expensive seat time). This tutorial's AI approach transcribes the first 3-5 seconds of answered audio using OpenAI's Whisper model, then feeds the transcript and audio features into a trained ML classifier that distinguishes human pickups from answering machines with 95%+ accuracy. The entire system runs on your own hardware with no per-call API costs, processes decisions in under 2 seconds, and continuously improves as you feed it new labeled data from your call center's actual traffic.

Explore Other Topics

◎ Monitoring & Observability ⚙ ViciDial Administration ★ Infrastructure & DevOps ⚛ AI-Powered Operations