OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Voxnovel

Voxnovel is a Python audiobook-generation application that uses BookNLP to analyze literature and attribute quotations to characters, then Coqui TTS to synthesize those characters’ lines with distinct voices.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Voxnovel — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Voxnovel when you want to turn literature into a multi-voice audiobook and can review character assignments as part of the workflow.

Who it is for

  • Readers and audiobook creators seeking multi-speaker narration from literary text.
  • Technically comfortable users who want to review and correct character attribution before generating audio.

Documented uses

  • Convert literary text into an audiobook with different synthesized voices assigned to characters.
  • Inspect and manually correct quotation-to-character assignments before speech synthesis.
  • Create an M4B audiobook with metadata and chapters, or separate chapter audio files.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. The README documents Docker, WSL, and a headless Google Colab route.

  • BookNLP handles character and quotation attribution; the README warns that attribution does not correctly identify quotations for languages other than English.
  • The README describes M4B output with metadata and chapters, plus separate chapter audio files.
  • The README documents voice cloning from reference audio and adding fine-tuned XTTS models.
  • The GUI Docker instructions state that sound is not working in that setup.
  • Repository topics and metadata indicate Linux and macOS, while the README also gives Windows WSL setup instructions.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Voxnovel in Windows Subsystem for Linux

Install the documented WSL environment, activate Voxnovel’s Conda environment, and launch its GUI or headless program.

Before you start

  • Windows PowerShell and WSL, with virtualization enabled if prompted.
  • Internet access for the documented installation command.
  • An NVIDIA graphics card and CUDA toolkit are only required for the optional GPU acceleration path.

Steps

  1. In PowerShell, run wsl --install, then open WSL after the installation and account setup.

  2. In WSL, run yes | wget -O - https://raw.githubusercontent.com/DrewThomasson/VoxNovel/main/shell_install_scripts/Ubuntu-install.sh | bash.

  3. If using an NVIDIA GPU for acceleration, install the NVIDIA CUDA toolkit with sudo apt install nvidia-cuda-toolkit.

  4. Activate the environment with conda activate VoxNovel, then navigate to the project directory with cd ~ && cd VoxNovel.

  5. Launch the GUI with the command below or the headless program with the command below.

    Documented command
    python gui_run.py
    Documented command
    python headless_voxnovel.py

Expected outcome

The documented WSL setup provides a route to launch Voxnovel’s GUI or headless program; the README says generated audiobook files are under `VoxNovel\output_audiobooks` in the WSL environment.

Guide limitations

  • The README describes GPU acceleration as optional and specific to NVIDIA graphics cards.
  • The setup instructions say that if conda is not found, closing and reopening the PowerShell window and relaunching Ubuntu WSL may help.
  • These are published setup steps, not a verified installation or compatibility guarantee.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
DrewThomasson/VoxNovel · Official homepage title · retained in its source language
How we review sourcesSuggest a correction