ninjahuttjr/hal-answering-service
I'm sorry, Dave. I'm afraid I can't let that spam call through. — Local AI answering service with voice cloning, call recording, and sub-second latency. Runs entirely on your GPU. No cloud. No per-minute billing. Just HAL.
Combines Faster-Whisper (speech-to-text), a local LLM via LM Studio/Ollama, Chatterbox TTS with voice cloning, and Silero VAD into a single WebSocket pipeline that processes audio bidirectionally with barge-in support. Integrates with SignalWire for phone line connectivity and supports push notifications via ntfy, with full call recording, transcripts, and JSON metadata logged locally—or runs in browser-based demo mode without any phone line infrastructure.
Stars
9
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ninjahuttjr/hal-answering-service"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
rapidaai/voice-ai
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time...
modal-labs/quillman
A voice chat app
ArchishmanSengupta/autovoiceevals
A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.
lixiangyu890601/EasyAICC-Easy-AI-Call-Center
外呼系统，智能外呼，自动外呼系统，人工外呼，呼叫中心
voicetestdev/voicetest
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous...