agentvoiceresponse/avr-infra
The AVR Infrastructure project is designed to launch the Agent Voice Response application, which will start the Core, ASR, LLM, and TTS services integrated with Asterisk Audiosocket.
Supports pluggable Speech-to-Speech (S2S) endpoints alongside modular ASR/LLM/TTS chains, with real-time audio streaming between Asterisk and multiple AI providers (OpenAI, Deepgram, ElevenLabs, Anthropic, Google, etc.). Deploys via Docker Compose with environment-variable configuration of service URLs, optional Voice Activity Detection layer for STT-only providers, and ambient background noise synthesis. Built on AVR Core that manages audio streaming, transcription, inference, and synthesis in a linear pipeline bridging PBX to AI services.
Stars
83
Forks
39
Language
—
License
MIT
Category
Last pushed
Feb 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/agentvoiceresponse/avr-infra"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
deepgram/deepgram-js-sdk
Official JavaScript SDK for Deepgram.
deepgram/deepgram-rust-sdk
Community Rust SDK for Deepgram.
deepgram/deepgram-dotnet-sdk
Official .NET SDK for Deepgram.
deepgram-starters/node-transcription
Get started using Deepgram's Transcription with this Node demo app
deepgram-starters/node-voice-agent
Get started using Deepgram's Voice Agent with this Node demo app