Skip to content

Releases: vancoder1/NarrateAI-webui

v1.0

02 Jun 21:55
@vancoder1 vancoder1
1.0
491d095
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0 Latest
Latest

🎉 NarrateAI - Major Update: Kokoro TTS, Expanded Format Support & UI Enhancements! 🎉

NarrateAI Web UI Screenshot

This is a significant update for NarrateAI-webui! We've revamped core components to bring you a more powerful, versatile, and user-friendly audiobook generation experience.

✨ Highlights of this Release:

  • 🚀 New TTS Engine: Kokoro TTS!
    • We've transitioned from Silero TTS to Kokoro TTS (hexgrad/Kokoro-82M). This powerful engine offers a diverse range of languages and voices, aiming for high-quality audio output. Explore the new voice options in the settings!
  • 📄 Wider Document Support:
    • Your literary world just got bigger! NarrateAI can now convert:
      • Plain Text (.txt)
      • PDF (.pdf)
      • EPUB (.epub)
      • Microsoft Word (.docx) - Requires python-docx to be installed (handled by install.bat)
      • HTML (.html, .htm)
  • ⚙️ Interactive Settings Tab in UI:
    • Take full control! A new "Settings" tab allows you to:
      • Select Language Code and see available Voices dynamically update.
      • Adjust speaking Speed (from 0.1x to 2.0x).
      • Choose your processing Device (cpu or cuda if available).
  • 💾 Persistent Configuration:
    • Your preferred settings (language, voice, speed, device) are now saved in config/config.json and automatically loaded. The UI makes managing these a breeze.
  • 💅 Enhanced User Experience:
    • Clearer progress reporting during audiobook generation.
    • More robust error handling and informative messages.
  • 📝 Improved Logging:
    • Logs are now more structured and saved to a dedicated logs/ directory, making troubleshooting easier.

⚠️ Important Notes:

  • TTS Engine Change: Due to the switch to Kokoro TTS, previously available Silero voices are no longer applicable. You'll find a new set of voices based on Kokoro's capabilities. Please explore the "Settings" tab to configure your new preferred voice.
  • Configuration File: The config/config.json structure has been updated for Kokoro TTS. If you had a previous version, your settings will be adapted or reset to new defaults.
  • Dependencies: The requirements.txt has been updated. Ensure you run install.bat for a fresh setup or if you encounter issues after updating. The installer now also guides PyTorch (CPU/CUDA) installation.

🚀 Getting Started:

  • New Users:
    1. Clone the repository.
    2. Run install.bat to set up the Conda environment and install all dependencies, including your choice of PyTorch (CPU/CUDA).
    3. Run start.bat to launch the application.
  • Existing Users (Updating):
    1. Ensure your local repository is clean (commit or stash changes).
    2. Run update.bat to fetch the latest changes and update dependencies.
    3. (Recommended) If you encounter any issues after updating, consider running install.bat again to ensure your environment is fully aligned with the new requirements.
    4. Run start.bat.

🐛 Bug Fixes & Minor Improvements:

  • Improved handling of empty or invalid input files.
  • More resilient audio chunk processing and combining.
  • UI elements are now more responsive to configuration changes.
  • Codebase refactoring for better maintainability and stability.

We're incredibly excited for you to try out this new version of NarrateAI-webui! Your feedback is invaluable to us. Please report any bugs, suggest features, or share your experience by opening an issue on GitHub.

Happy Narrating! 🎙️📚

Assets 2
Loading