Vocal Edge is a web-based application designed to help you master the art of speaking. Built using Streamlit and powered by LangChain, Whisper, and Ollama, this app provides a seamless and interactive experience for improving your speaking skills.
- Interactive Speaking Exercises: Engage in various speaking exercises to enhance your fluency and confidence.
- Real-time Feedback: Receive instant feedback on your pronunciation, tone, and pace.
- Personalized Learning: Tailor your practice sessions based on your skill level and progress.
- User-friendly Interface: Enjoy a clean and intuitive interface powered by Streamlit.
- Streamlit: For creating the web-based interface.
- LangChain: For natural language processing and understanding.
- Whisper: For speech recognition and analysis.
- Ollama: For advanced language modeling and feedback. (option)
- OpenAI: For leveraging advanced language models to enhance speaking exercises and feedback. (option)
To get started with Vocal Edge, follow these steps:
- Clone the repository:
git clone https://github.com/SurajAiri/VocalEdge.git
- Install the required dependencies:
pip poetry poetry install
- Run the Streamlit app:
streamlit run app.py
Here are some preview images of Vocal Edge in action:
The home page of Vocal Edge, providing an overview of the features and navigation.
An interactive speaking exercise where users can practice.
Detailed feedback on pronunciation, tone, and pace to help users improve their speaking skills.
We welcome contributions to Vocal Edge! If you have any ideas or improvements, feel free to open an issue or submit a pull request.
For any questions or feedback, please contact us at surajairi.ml@gmail.com.