← Back to AIO Orchestration

AI Voice Agent Tutorials

7 step-by-step guides to build and deploy your own on-premise AI voice agent with Asterisk, LLM, STT and TTS.

Asterisk AI Voice Agent Setup

Build a self-hosted AI voice agent with Asterisk EAGI + STT + LLM + TTS. 335ms latency, GDPR compliant.

Asterisk PJSIP Configuration

Essential PJSIP setup for AI voice applications. SIP trunks, endpoints, and codec configuration.

GPU CUDA Setup for Voice AI

Configure NVIDIA GPU with CUDA for real-time voice AI inference. Driver installation and optimization.

Ollama Voice Bot

Deploy a local LLM with Ollama for voice bot applications. Model selection, tuning, and integration.

Voice Activity Detection (VAD)

Implement real-time voice activity detection for natural conversation flow and barge-in support.

Whisper STT with Asterisk

Integrate Faster-Whisper speech-to-text with Asterisk. 170ms latency, on-premise deployment.

XTTS v2 TTS Server

Set up XTTS v2 text-to-speech server with streaming. 84ms first-chunk latency, expressive voice cloning.