GPT-in-Terminal is a Python-based command-line application that allows users to interact with OpenAI's GPT models. It provides functionalities for text input, speech recognition, text processing, and text-to-speech conversion.
- Text Input: Users can type in their queries.
- Voice Input: Users can speak their queries, and the program will transcribe them.
- Text Processing: The program preprocesses the input to remove stopwords.
- Text-to-Speech: The program converts the generated text into speech and plays it back to the user.
Before running the program, ensure you have the following dependencies installed:
- Python 3
- NLTK
- SpeechRecognition
- gTTS
- playsound
- pygame
You can install the required libraries using pip:
pip install nltk SpeechRecognition gTTS playsound pygame
- Clone the repository to your local machine.
- Navigate to the cloned directory.
- Run the
GPT-in-Terminal.py
script:
python GPT-in-Terminal.py
- Follow the prompts to input text or use voice commands.
Set your OpenAI API key in the GPT-in-Terminal.py
file:
openai_api_key = "YOUR_OPENAI_API_KEY"
Contributions are welcome! Please feel free to submit pull requests or create issues for bugs and feature requests.