Skip to content

Latest commit

 

History

History
66 lines (42 loc) · 3.06 KB

README.md

File metadata and controls

66 lines (42 loc) · 3.06 KB
Raw

NADOO_VOICE

NADOO Voice

Overview

NADOO Voice is a cutting-edge text-to-speech application built around the OpenAI TTS API. It is designed to transform written text into high-quality audio, offering a seamless and intuitive experience for users who need to convert text into spoken word.

Features

  • Chapters Editor: Directly input and manage text for audiobook creation.
  • Book Mode: Special feature for books, allowing the AI to identify and create separate audio files for chapters and subchapters, enhancing the audiobook experience.
  • Chapter-wise Playback: Navigate through audio chapters easily, ideal for audiobook listeners and learners.

Installation

git clone [repository-link]
cd NADOO-Voice
# Follow further installation instructions here

Usage

  1. Start the application.
  2. Input text directly or use the Chapters Editor.
  3. For books, select 'Book Mode' to enable chapter-wise conversion.
  4. Press 'Convert' to start the text-to-speech process.
  5. Access and manage your audio files directly within the application.

NADOO_VOICE_UPDATE_LOGO_00_01_01

Update 0.1.1 Announcement

We're excited to announce the release of NADOO Voice version 0.1.1! This update brings several key enhancements and sets the foundation for some much-anticipated features in the future.

What's New

  • Text Input via Chapters Editor: Directly input and manage text for audiobook creation through our newly introduced chapters editor.
  • Enhanced Book Mode: Improved AI-driven chapter segmentation for creating distinct audio files for each chapter in your book.
  • Version Management: Streamline your editing process with our new version management system, allowing for iterative improvements and re-creation of audiobooks.
  • Chapter-wise Playback: Navigate and manage audio chapters easily within the application, enhancing the listening experience.

Coming Soon

  • Voice and Model Selection Dropdown: A future update will introduce a dropdown menu for selecting various voices and models to cater to diverse audio preferences.
  • PDF Upload Feature: We're working on a feature that will enable users to upload PDFs directly and convert them into high-quality audio.
  • Multi-Lingual Translation Support: Plans are underway to support multiple languages, allowing for translation and audio generation in various languages.

Stay tuned for these exciting updates and more!

Thank you for being part of the NADOO Voice journey.

For more details and updates, visit our GitHub repository.

Contributing

Contributions are welcome! Please read our Contributing Guide for more information.

License

This project is licensed under the AGPL License.

Contact

For any inquiries or suggestions, please contact [your-email] or raise an issue in the repository.