This project is an interactive application that utilizes the OpenAI GPT-4 API to converse with users and respond vocally. It leverages the latest OpenAI text-to-speech features to synthesize and stream audio responses in real-time, providing an engaging user experience.
- Text-based interaction with OpenAI's GPT-4 model.
- Real-time audio feedback using OpenAI's text-to-speech synthesis.
- Streamlined audio playback in Python without the need to download files.
To get started with this project:
- Clone the repository:
git clone https://github.com/nikdanilov/openai-assistant-with-audio
- Navigate to the project directory:
cd openai-assistant-with-audio
- Install the required dependencies:
pip install -r requirements.txt
- Set up your OpenAI API key in your environment variables:
export OPENAI_API_KEY='your-api-key'
- Run the application:
python main.py
Simply type your questions or commands, and the assistant will respond both textually and audibly.
Enjoy interacting with your OpenAI-powered vocal assistant! 🎉