Spirit AI Voice Assistant
Print Profile(1)
Description
Project Video:
A full storytelling showcase of the Spirit AI Voice Assistant, including development process, system evolution, and final working demonstration.
Spirit AI Voice Assistant (Raspberry Pi + ChatGPT Integration)
This project is a fully functional AI voice assistant designed and developed by Gabriele Giovinazzo on a Raspberry Pi system, integrating real-time speech recognition, ChatGPT API interaction, hardware control, and a custom 3D-printed enclosure.
The assistant listens for a wake word, processes natural language commands, and responds through AI-generated speech. It supports practical features such as timers, alarms, reminders, weather queries, volume control, and continuous conversational interaction.
The system is designed with a modular architecture including audio processing, AI logic, memory storage, and hardware interaction (LED feedback and audio routing).
The physical structure of the assistant was custom-designed using CAD software (FreeCAD and Blender), then 3D printed and assembled manually. The enclosure was later finished with sanding, fitting adjustments, and spray painting to achieve an industrial-style surface finish.
Required Components (Hardware System)
- Raspberry Pi 4 Model B (8GB) x 1
- Seeed Studio ReSpeaker XMOS XVF3800 Microphone Array x 1
- USB Stereo Speaker x 1
- MicroSD Card (32GB or higher recommended) x 1
- Raspberry Pi Power Supply x 1
- Custom 3D Printed Enclosure (main shell + components)
Software Stack
- Python 3.10+
- OpenAI API (ChatGPT integration)
- spaCy NLP model (en_core_web_sm)
- FFmpeg (audio processing)
- ALSA audio system
- SpeechRecognition library
- PyAudio
- gTTS (text-to-speech)
3D Printed Parts
Custom-designed enclosure for Raspberry Pi, microphone array, and speaker mounting system.
Designed in FreeCAD and Blender and optimized for FDM 3D printing.
Features
- Real-time voice interaction system
- Wake word detection
- AI-powered conversation (ChatGPT API)
- Intent recognition and command execution
- Timers, alarms, and reminders system
- Weather API integration
- LED hardware feedback system
- Conversation memory system
- Modular Python architecture for scalability
Project Notes
The system is designed for local execution on Raspberry Pi and can be adapted to different audio hardware configurations by modifying device indexes in the configuration file.
The 3D model of the enclosure is available on MakerWorld for personal use and 3D printing.
Source Code
All source code, modules, and project structure are available on GitHub.
GitHub repository: https://github.com/SUP3RGABBO/spirit-ai-voice-assistant
GitHub profile: https://github.com/SUP3RGABBO
License
You shall not share, sub-license, sell, rent, host, transfer, or distribute in any way the digital or 3D printed versions of this object, nor any other derivative work of this object in its digital or physical format (including - but not limited to - remixes of this object, and hosting on other digital platforms). The objects may not be used without permission in any way whatsoever in which you charge money, or collect fees.
Comment & Rating (0)