Text-to-Speech (Python GUI for Whisper)

This is a simple Python-based GUI application that allows users to generate speech from text using the OpenAI API. The application provides a user-friendly interface for inputting text and selecting from different voices to create personalized audio output.

Audio Demo

The demo audio is available in the demo_speech folder.

Features

• Text Input: Enter any text you wish to convert to speech.
• Voice Selection: Choose from multiple voices like Alloy, Echo, Fable, Onyx, Nova, and Shimmer.
• Generate Speech: Convert the text into speech and save it as an MP3 file.

Requirements

• Python 3.x
• tkinter for the GUI
• requests library for making API calls

Installation

1. Clone the repository:

   git clone https://github.com/VolkanSah/Text-to-Speech-PyGUI-for-Whisper.git
   cd Text-to-Speech-PyGUI-for-Whisper

2. Install the required Python packages:

   pip install requests

3. Run the application:

   python run.py

Usage

1. Enter the text you want to convert to speech.
2. Select the voice from the dropdown menu.
3. Click "Generate Speech" to create the speech. Once finished, you can save the speech file wherever you want.

License

This project is open source and available under the MIT License.

Disclaimer

This application uses the OpenAI API. Ensure you have a valid API key and are aware of OpenAI's usage policies and pricing.

Credits

S. Volkan Kücükbudak