sancliffe/ollama-STT-TTS
A simple, hands-free Python voice assistant that runs 100% locally. This script uses openwakeword for wakeword detection, webrtcvad for silence detection, OpenAI's Whisper for transcription, and Ollama for generative AI responses.
This project offers a completely private, hands-free voice assistant that runs entirely on your computer. You speak a wakeword and your query into a microphone, and the system processes your voice, generates a response using a local AI model, and speaks the answer back to you through your speakers. It's designed for anyone who wants a personal voice assistant without sending their data to cloud services.
Use this if you need a local, private voice assistant for general inquiries or simple tasks, controlled entirely by your voice.
Not ideal if you need a voice assistant integrated with cloud services, smart home devices, or complex, real-time data lookups.
Stars
7
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sancliffe/ollama-STT-TTS"
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