Harsha-Reddy21/Story-Lens

0

stars

2

commits

Python

primary language

Jun 2, 2025

updated

README

AI Creative Story & Audio Narration App

This Streamlit app lets users upload a photo (vacation, birthday, random snapshot) and generates a creative short story or poem inspired by the image using microsoft/kosmos-2 (multimodal AI model). The app then creates an audio narration of the generated text with an AI voice using coqui/xtts-v2 text-to-speech model. Users can listen to the narration and download both the story and audio.


Features

  • Upload an image and get a creative short story or poem inspired by it
  • AI-generated audio narration of the story/poem
  • Play audio directly in the app
  • Download text story and audio narration for sharing

Models Used

Model NameDescriptionSource
microsoft/kosmos-2Multimodal (image + text) model to generate creative text from imagesHugging Face Transformers
coqui/xtts-v2AI text-to-speech (TTS) model with natural voiceCoqui TTS

Requirements

  • Python 3.8+
  • streamlit
  • transformers
  • Pillow
  • soundfile
  • numpy
  • TTS (Coqui TTS Python package)

Setup Instructions

  1. Clone the repository
git clone https://github.com/Harsha-Reddy21/Story-Lens.git
cd Story-Lens

python3 -m venv venv
source venv/bin/activate   # On Windows: venv\Scripts\activate

pip install -r requirements.txt

streamlit run app.py


Contributors

Harsha-Reddy21/Story-Lens

0

stars

2

commits

Python

primary language

Jun 2, 2025

updated

README

AI Creative Story & Audio Narration App

This Streamlit app lets users upload a photo (vacation, birthday, random snapshot) and generates a creative short story or poem inspired by the image using microsoft/kosmos-2 (multimodal AI model). The app then creates an audio narration of the generated text with an AI voice using coqui/xtts-v2 text-to-speech model. Users can listen to the narration and download both the story and audio.


Features

  • Upload an image and get a creative short story or poem inspired by it
  • AI-generated audio narration of the story/poem
  • Play audio directly in the app
  • Download text story and audio narration for sharing

Models Used

Model NameDescriptionSource
microsoft/kosmos-2Multimodal (image + text) model to generate creative text from imagesHugging Face Transformers
coqui/xtts-v2AI text-to-speech (TTS) model with natural voiceCoqui TTS

Requirements

  • Python 3.8+
  • streamlit
  • transformers
  • Pillow
  • soundfile
  • numpy
  • TTS (Coqui TTS Python package)

Setup Instructions

  1. Clone the repository
git clone https://github.com/Harsha-Reddy21/Story-Lens.git
cd Story-Lens

python3 -m venv venv
source venv/bin/activate   # On Windows: venv\Scripts\activate

pip install -r requirements.txt

streamlit run app.py


Contributors

Languages

Python

100.0%