m15-ai/Faster-Local-Voice-AI
A real-time, fully local voice AI system optimized for low-resource devices like an 8GB Ubuntu laptop with no GPU, achieving sub-second STT-to-TTS latency using Ollama, Vosk, Piper, and JACK/PipeWire. Open-source and privacy-focused for offline conversational AI.
This project helps you create a fully private, real-time voice assistant that runs entirely on your own computer, even an older laptop without a powerful graphics card. You speak into your microphone, and the AI processes your speech, generates a response, and speaks it back to you, all without sending any data to the cloud. It's designed for anyone who needs immediate, natural spoken interaction with an AI while keeping their conversations completely private.
No commits in the last 6 months.
Use this if you need an instant, conversational AI experience that prioritizes privacy and operates offline on standard computer hardware.
Not ideal if you need an AI that can be interrupted mid-sentence or if you prefer a system managed entirely by a third-party service.
Stars
23
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jul 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/m15-ai/Faster-Local-Voice-AI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
asiff00/On-Device-Speech-to-Speech-Conversational-AI
This is an on-CPU real-time conversational system for two-way speech communication with AI...
VideotronicMaker/LM-Studio-Voice-Conversation
Python app for LM Studio-enhanced voice conversations with local LLMs. Uses Whisper for...
syntithenai/hermod
voice services stack from audio hardware through hotword, ASR, NLU, AI routing and TTS bound by...
bold-ronin/lira
A Voice-First AI Companion
voice-engine/make-a-smart-speaker
A collection of resources to make a smart speaker