Loading repository data…

Voice-Based-AI-Assistant-with-ChatGPT-on-Raspberry-Pi GitHub Details, Stars and Alternatives | OpenRepoFinder

KuchikiRenji / repository

Voice-Based-AI-Assistant-with-ChatGPT-on-Raspberry-Pi

Open-source voice-controlled AI assistant for Raspberry Pi. Say “Hey Ras Pi” for hands-free ChatGPT and Bing Chat with wake word detection, multilingual speech (English, Mandarin, Cantonese) and smart routing for time-sensitive questions.

#aiassistant#bing-chat#chatgpt#handsfree#multilingual-nlp#open-source

View Repository on GitHub ↗

REPOSITORY OVERVIEW

Live repository statistics

★ 4Stars

⑂ 0Forks

◯ 0Open issues

◉ 4Watchers

58/100

OPENREPOHUB HEALTH SIGNAL

Mixed signals

A transparent discovery signal based on current public GitHub metadata.

Recent activity35% weight

Community adoption25% weight

Maintenance state20% weight

100

License clarity10% weight

100

Project information10% weight

This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.

README preview

CENG4480 Final Project - Voice Based AI Assistant with ChatGPT on Raspberry Pi

This project is an implementation of a voice-based AI assistant using OpenAI's ChatGPT and Bing on a Raspberry Pi. The assistant listens for the wake word "Hey Ras Pi" and then processes the user's query, providing an appropriate response. The project demonstrates how to integrate multiple language models and APIs to create a more robust and context-aware AI assistant.

Features

Wake word detection using Porcupine
Speech recognition with Google Speech Recognition
AI-based chat using ChatGPT and unoffical Bing APIs
Multilingual support for English, Mandarin, and Cantonese
Text-to-Speech using Google Text-to-Speech (gTTS)
Context-Aware interactions for both ChatGPT and Bing based on conversation history
Time-sensitive question filtering using custom NLP function

Installation

Clone the repository

git clone https://github.com/yourusername/Voice-Based-AI-Assistant-with-ChatGPT-on-Raspberry-Pi.git
cd Voice-Based-AI-Assistant-with-ChatGPT-on-Raspberry-Pi

Update and install your Raspberry Pi packages:

sudo apt-get update
sudo apt-get upgrade
chmod +x install_dependencies.sh
./install_dependencies.sh

Set up a virtual environment and activate it

python3 -m venv env
#on Pi
source env/bin/activate
#on Windows
./env/bin/activate

Install the required packages

pip install -r requirements.txt
python -m spacy download en_core_web_sm

Configuration

Before running the project, you need to create a config.py file in the src directory with your API keys. Use the provided config_example.py as a template and fill in the necessary information.

Openai API

Refer to https://platform.openai.com/examples

PicoVoice Access Key

Get your PicoVoice access key from the PicoVoice Console. Add the access key to the config.py file.

Bing API

This project uses an unofficial BING API from EdgeGPT. To generate a cookies.json file for use with the BING API, follow the instructions in the EdgeGPT repository. Once you have your config.py and cookies.json files ready, you can proceed with running the project.

python main.py

.
├── ./.gitignore
├── ./README.md
├── ./cookies.json
├── ./env
├── ./install_dependencies.sh
├── ./main.py
├── ./models
│   ├── ./models/Hey-Ras-Pi_en_raspberry-pi_v2_1_0.ppn
│   ├── ./models/Hey-Ras-Pi_en_raspberry-pi_v2_1_0.zip
│   └── ./models/alexa_windows.ppn
├── ./output.mp3
├── ./requirements.txt
└── ./src
    ├── ./src/bing.py
    ├── ./src/config.py
    ├── ./src/config_example.py
    ├── ./src/gpt.py
    ├── ./src/nlp.py
    ├── ./src/speech_to_text.py
    ├── ./src/text_to_speech.py
    ├── ./src/translator.py
    └── ./src/wake_up_detect.py
└── ./wake_up_sound.wav