can-01-chatbot 0.1.0

A chatbot project that uses OpenAI, Google Cloud Speech-to-Text, and Text-to-Speech APIs.

CAN.01 Chatbot

This is a chatbot project developed in Python. The chatbot, named Ming, is a 40-year-old pilot from Hong Kong who speaks Cantonese fluently. Ming loves sharing travel experiences and stories, and is passionate about different cultures and foods.

Features

• Real-time speech recognition using Google Cloud Speech-to-Text
• Generates responses using OpenAI's GPT-3.5 model
• Converts text responses to Cantonese speech using Google Cloud Text-to-Speech
• Continuous listening and response capabilities

Requirements

• Python 3.6 or higher
• Google Cloud service account with Speech-to-Text and Text-to-Speech APIs enabled
• OpenAI API key

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/can_01_chatbot.git
   cd can_01_chatbot
   

2. Create and activate a virtual environment:

   python3 -m venv venv
   source venv/bin/activate
   

3. Install the dependencies:

   pip install -r requirements.txt
   

4. Set up environment variables:

   • Set your OpenAI API key:

     openai.api_key = 'your_openai_api_key'
     

   • Set the path to your Google Cloud service account key JSON file:

     export GOOGLE_APPLICATION_CREDENTIALS="path/to/SA_Carefirst.json"
     

Usage

1. Run the chatbot:

   python can_01_chatbot/can01.py
   

2. Interaction:

   • The program will start listening for your speech input.
   • Once it recognizes your speech, it will generate a response using the OpenAI GPT-3.5 model.
   • The response will be converted to Cantonese speech and played back.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Authors

• Michelle - Initial work - YourGitHubProfile

Acknowledgements

• Special thanks to Contributor1 for their help.

Additional Information

• Google Cloud Speech-to-Text: Documentation
• Google Cloud Text-to-Speech: Documentation
• OpenAI GPT-3: Documentation