Speech-to-Image is a unique application that converts spoken input into AI-generated images. Utilizing speech recognition to capture user prompts, the project processes the recognized text and generates corresponding images through text-to-image modeling. Built using Streamlit for a user-friendly interface, this project highlights voice-driven creativity and AI interaction.
- Voice Recognition: Capture prompts through speech.
- AI-Powered Image Generation: Translates text into visuals.
- Interactive UI: Simple interface for speech-to-image experience.
SI_streamlit.py
: Main script for the Streamlit app, integrating speech recognition and image generation functionalities.
- Clone the Repository:
git clone https://github.com/jaidh01/Speech-to-Image.git
- Run the Application:
streamlit run SI_streamlit.py
- Python 3.8+
- Streamlit
- Speech Recognition libraries
Contributions are welcome! Fork the repository, enhance it, and submit a pull request.