Story Teller
Captions an image, writes a short story from it, and narrates the story.
At a glance
- Type
- Multimodal AI
- Key tools
- Transformers, LangChain, Hugging Face API
- Try it
- Source ↗
Overview
An image-to-story pipeline that combines image captioning, language generation, and text-to-speech. Hugging Face Transformers and LangChain turn visual input into short stories that can also be heard.
How it works
- 01Generate a caption from an input image.
- 02Expand the caption into a short story.
- 03Convert the generated story into audio.
Stack
- Transformers
- LangChain
- Hugging Face API
- gTTS
- NLTK
- Keras
- Streamlit
- Python