Skip to content

An AI-powered Streamlit app that converts images into short stories and reads them aloud. It uses Hugging Face for image captioning and text-to-speech, and OpenAI (via LangChain) for creative story generation.

Notifications You must be signed in to change notification settings

rsadhamhussain/Image_to_Story-Generator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Image-to-Story Generator

An AI-powered Streamlit app that converts images into short stories and reads them aloud. It uses Hugging Face for image captioning and text-to-speech, and OpenAI (via LangChain) for creative story generation.

🧠 Image to Caption to Story (with Text-to-Speech)

This is a simple AI-powered Streamlit app that:

📸 → Converts an image into a caption
📝 → Turns the caption into a short story (via OpenAI LLM)
🔊 → Converts the story into speech (via HuggingFace TTS)


💡 Features

  • Image Captioning: Uses BLIP (Salesforce/blip-image-captioning-base) to describe uploaded images.
  • Story Generation: Uses OpenAI's gpt-3.5-turbo to write a creative story (limited to 20 words).
  • Text-to-Speech: Uses HuggingFace’s ESPnet TTS model to convert story to audio.

🛠️ Requirements

Install dependencies with:

pip install -r requirements.txt

About

An AI-powered Streamlit app that converts images into short stories and reads them aloud. It uses Hugging Face for image captioning and text-to-speech, and OpenAI (via LangChain) for creative story generation.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages