Important
VoxKit is currently in active development. Versions below 1.0.0 are considered early preview releases and should be treated as experimental. Your feedback during this development phase is invaluable! Please report issues, suggest improvements, and share your use cases. Thanks.
- ARCHITECTURE - System layers and terminology
- RESEARCH - Papers and research background
- CONTRIBUTING - Contribution guidelines
src/voxkit/
├── gui/ # PyQt6 interface (pages, components, workers)
├── engines/ # Speech toolkit backends
├── analyzers/ # Dataset metadata extraction
├── storage/ # Data persistence (datasets, models, alignments)
└── config/ # Application configuration
Prerequisites:
- git – Version control
- uv – Python package manager
- invoke – Task runner (installed via
uv tool install invoke)
Getting-started:
# Clone repository
git clone https://github.com/BrainBehaviorAnalyticsLab/voxkit-desktop.git
cd voxkit-desktop
# As easy as...
# (1) Browse developer commands
invoke --list
# (2) Install precommit and initialize environment
invoke setup
# (3) Start app (developer mode)
invoke devIf you use VoxKit in your research, please cite:
<TODO>APA Format:
<TODO>
See LICENSE for details...
For questions or collaboration inquiries, please open an issue on GitHub.