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.

39
/ 100
Emerging

This service acts as a personal AI phone screener that answers your incoming calls. It processes the caller's speech, determines a response, and speaks back in a cloned voice, all running on your own computer's GPU. You get a push notification with a summary and full transcript of the conversation, allowing you to decide if you want to call back. It's designed for individuals who want to filter unwanted calls without using cloud-based AI services or incurring per-minute charges.

Use this if you want an automated, private, and customizable system to screen incoming calls, block spam, and receive summarized transcripts without relying on external cloud AI providers.

Not ideal if you lack a dedicated GPU (16GB+ VRAM recommended), prefer not to manage local server hardware, or need an answering service with human operator handover.

call-screening spam-blocking personal-assistant privacy-tools telephony-automation
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 11 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Python

License

MIT

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.