The Speech-to-Text project is a Python-based application that leverages the SpeechRecognition library to convert speech input into text. It allows users to provide pre-recorded audio files for transcription.

1. Run the provided Jupyter Notebook or execute the Python script to launch the application.
2. Follow the on-screen instructions to select the input source (microphone or file) and the desired speech recognition engine.
3. Provide the file path(s) and let the application convert the speech to text.
4. The recognized text will be displayed as the output, allowing you to process or store it as needed.

• You can further modify this project to take input from the user. However, that will require this code to be written outside the Jupyter notebook environment
• Additional modifications can be made allowing the system to do certain actions based on the speech recieved from the user Input(eg: Alexa)