Olney1/ChatGPT-OpenAI-Smart-Speaker
This AI Smart Speaker uses speech recognition, TTS (text-to-speech), and STT (speech-to-text) to enable voice and vision-driven conversations, with additional web search capabilities via OpenAI and Langchain agents.
Implements modular wake-word detection via PicoVoice's custom models to reduce computational overhead on resource-constrained devices, with fallback modes for PC/Mac using Google Speech Recognition. Integrates Tavily Search agents alongside OpenAI's API for real-time web-aware responses, while gpiozero and APA102 LED libraries enable hardware feedback on ReSpeaker 4-Mic Arrays. Designed for headless Raspberry Pi 4 deployment with offline-capable wake-word processing, separating always-listening inference from cloud-dependent response generation.
311 stars. No commits in the last 6 months.
Stars
311
Forks
37
Language
Python
License
MIT
Category
Last pushed
Nov 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Olney1/ChatGPT-OpenAI-Smart-Speaker"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jackwuwei/gptspeaker
The ChatGPT/DeepSeek Voice Assistant uses a Raspberry Pi (or desktop) to enable spoken...
bhattbhavesh91/voice-assistant-whisper-chatgpt
This repository will guide you to create your own Smart Virtual Assistant like Google Assistant...
IgnoranceAI/hugh
A voice-powered AI built with Whisper, ChatGPT, and ElevenLabs
mingkuan/voice-assistant-chatgpt
Voice Assistant based on Whisper ASR and ChatGPT API
ivan00105/Voice-Based-AI-Assistant-with-ChatGPT-on-Raspberry-Pi
CENG4480 project that implements a voice assistant with ChatGPT and Bing