KokoroGUI v1.0.0

KokoroGUI v1.0.0

We are excited to announce the 1.0.0 release of the KokoroGUI! This application provides a user-friendly interface for converting text into speech using the kokoro library. Built with tkinter, it offers a seamless experience for generating audio files from text input.

Key Features in v1.0.0:

• Text Input: Easily enter the text you want to convert to speech via the intuitive text input field.
• Voice Selection: Choose from a variety of voices using the dropdown menu. Voices include:
  • af_alloy
  • af_aoede
  • af_bella
  • af_jessica
  • af_kore
  • af_nicole
  • af_nova
  • af_river
  • af_sarah
  • af_sky
  • am_adam
  • am_echo
  • am_eric
  • am_fenrir
  • am_liam
  • am_michael
  • am_onyx
  • am_puck
  • am_santa
  • af_heart
• Filename and Output Directory Customization: Specify the desired filename and output directory for your generated audio files.
• Separate Audio Files: Opt to save each segment of the generated speech as a separate .wav file, providing flexibility for post-processing.
• Timecode Formatting: Customize the timecode format appended to the filenames, allowing for easy organization and identification of audio files.
• Combine Post-Processing: Choose to automatically combine all generated audio segments into a single .wav file after generation, streamlining your workflow.
• Error Handling: Robust error handling to catch common issues such as missing text or pipeline initialization failures, with informative error messages displayed to the user.
• Status Updates: Real-time status updates during the conversion process, keeping you informed about the application's progress.

How to Get Started:

1. Installation: Follow the installation instructions in the README to set up the application and its dependencies.
2. Text Input: Enter the text you want to convert into the text input field.
3. Voice Selection: Select your preferred voice from the dropdown menu.
4. Configuration: Customize the filename, output directory, timecode format, and file combination options as desired.
5. Conversion: Click the "Convert to Speech" button to generate your audio file(s).

Known Issues:

• Initial pipeline initialization may take some time depending on your system.
• Voice quality may vary depending on the selected voice and input text.

Contributing:

We welcome contributions to improve the application! If you encounter any issues or have suggestions for new features, please open an issue or submit a pull request on GitHub.

My First GitHub Project!

This is my first time making a GitHub project and this release is kinda scuffed because PyCharm wouldn't push so I just brought over the main.py file.

License:

This project is licensed under the Apache-2.0 license.

Thank you for using the Text-to-Speech Application! We hope you find it useful.