ad
ad
Topview AI logo

Updated AI Audiobook Maker Installation and Bug Fixes

Science & Technology


Introduction

In this article, we'll guide you through the updated installation process for the AI Audiobook Maker, ensuring compatibility with the latest version of Tortoise. This update includes necessary prerequisites and straightforward steps to get everything set up properly.

Prerequisites for Installation

Before diving into the installation process of the Audiobook Maker, let's cover the prerequisites you'll need:

  1. NVIDIA Graphics Card: The Audiobook Maker requires an NVidia graphics card, as it isn't compatible with other accelerators.
  2. AI Voice Cloning Repository Version 3: Make sure to have this installed on your computer. For instructions on getting it set up, refer to the linked video in the description.

Installation Process

  1. Download the Audiobook Maker:

    • Navigate to the releases page where the latest version of the Audiobook Maker can be downloaded. The file size is approximately 3.7 GB, so ensure sufficient storage space.
    • Once downloaded, extract the files. The extracted folder will take up about 6 GB as it contains all necessary modules, eliminating the need for additional installations.
  2. Launching the Audiobook Maker:

    • After extraction, locate the V3 folder and open it. You can either double-click or use the shortcut keys to navigate to the folder.
    • In the folder, locate and click on the start_package.bat file to launch the Audiobook Maker application.
  3. Configuring Tortoise:

    • Open Tortoise by launching start.bat.
    • Navigate to settings within Tortoise and make sure to change the "results folder" to an absolute path.
    • Adjust additional settings for speed if desired—using Deep Speed is recommended for better performance.
    • Enable your autoregressive models, which are essential for generating text-to-speech.
  4. Editing the Configuration File:

    • Open the tor.yaml file using Notepad. Update the voice name by inputting the name of the trained model. Set samples to 2 for faster processing and iterations to 50.
    • Make sure RVC is disabled, as the Audiobook Maker has this feature integrated.
  5. Generating an Audiobook:

    • To create an audiobook, prepare a text file with the desired content.
    • In the Audiobook Maker, select the text file and specify voice and model settings. Then click on "Start Audiobook Generation."
    • Monitor the terminal to ensure audio is being generated without errors.

Features and Additional Functionality

The updated Audiobook Maker provides various features such as:

  • Option to regenerate audio for specific sentences.
  • Ability to update audiobook sentences by loading modified text files.
  • Export functionality to consolidate all audio into a single file.

Once you're done, you can play audio directly within the Audiobook Maker and control playback options.

Conclusion

This comprehensive guide should help you smoothly install and utilize the updated AI Audiobook Maker. Future updates and enhancements are anticipated to further improve its usability. Thank you for your continued support, and we hope you enjoy creating audiobooks!


Keywords

  • Audiobook Maker
  • Tortoise
  • NVIDIA Graphics Card
  • AI Voice Cloning
  • Installation
  • Configuration
  • Text to Speech

FAQ

What are the system requirements for installing the AI Audiobook Maker?
You need an NVIDIA graphics card and the AI Voice Cloning Repository version 3 installed on your computer.

How do I update the results folder settings in Tortoise?
Navigate to the settings in Tortoise and ensure to provide an absolute path for the results folder.

Can I regenerate audio for specific sentences?
Yes, you can select sentences and choose the regenerate audio option to update them.

Is it possible to export the entire audiobook into one file?
Absolutely! You can use the export functionality to compile all audio into a single file.

What should I do if I want to update audiobook sentences?
Load your modified text file into the Audiobook Maker and use the update option. This will delete previous audio for modified sentences and regenerate them.

ad

Share

linkedin icon
twitter icon
facebook icon
email icon
ad