AI Storyteller is a web application that uses OpenAI's GPT-3.5-turbo-instruct engine to generate stories based on user prompts and selected emotions. The application also integrates HumeStreamClient for capturing facial emotions using a webcam and DALL·E for generating images related to the generated story.
- Capture Emotion: Utilizes HumeStreamClient to capture facial emotion through a webcam.
- Generate Story: Takes user input prompts, modifies them based on selected emotions, and generates stories using OpenAI's GPT-3.5-turbo-instruct engine.
- Generate Images: Uses DALL·E to generate images corresponding to different sections of the generated story.
- Text-to-Speech: Utilizes OpenAI TTS to convert the generated story into audio for playback.
-
Clone the repository:
git clone https://github.com/your-username/ai-storyteller.git
-
Install the required dependencies: pip install -r requirements.txt
-
Obtain API keys: OpenAI API key: OpenAI API HumeStream API key: Obtain from HumeStream (replace the placeholder in face.py)
Run the application: streamlit run storyteller.py
Streamlit OpenAI Hume OpenCV asyncio numpy
Update API keys in storyteller.py and face.py. Customize the list of emotions in emotion_options in storyteller.py.