ENUNU
github.com
- Free plan
- Windows
What ENUNU is
ENUNU is a free, open-source Windows plugin that lets UTAU users work with NNSVS singing voice models. In UTAU, users choose an ENUNU model or an NNSVS model folder, select notes, and run the plugin to create a WAV file. Installation uses the ENUNU ZIP file dragged into the UTAU window. Extensions can edit UST lyrics, score or timing labels, and acoustic parameters such as f0. Additional extensions map expression suffixes to model flags, feed synthesized pitch back into the UST, and smooth sharp pitch changes. A model folder must contain enuconfig.yaml, with question_path pointing to and including the training file. Lyrics containing multiple hiragana characters in one note are unsupported except for the special handling of small っ. ENUNU works with ordinary NNSVS models, while its Training Kit creates models from UST, LAB, and WAV singing data. The MIT License permits commercial use under its conditions, but provides the software without warranty.
Who it suits
ENUNU suits UTAU users who want to use NNSVS singing models and export WAV vocals. It is intended for Windows environments and model-based vocal workflows.
Good to know, and what to watch
- Free, open-source UTAU plugin
- Uses ordinary NNSVS singing models
- Exports synthesized WAV files
- Extensions provide pitch and expression tools
- MIT License allows commercial use
- Windows-only workflow
- Multiple hiragana characters per note are unsupported
- Models require a correctly configured enuconfig.yaml
- Software is provided without warranty
The verdict
ENUNU connects NNSVS singing models with UTAU and adds extensions for lyrics, expression, and pitch handling. Its model configuration requirements and lyric limitation matter when preparing projects.
What the maker publishes
- Compatibility limit
- Lyrics with multiple hiragana characters in one note are unsupported except for gemination (っ). source
- Download links
- The ENUNU account page links downloads for ENUNU 1.0.0, ENUNU Training Kit 2.0.1, and EnuPitch 0.2.0. source
- Extensions
- Extensions can edit UST lyrics, score or timing labels, and acoustic parameters such as f0. source
- Extensions
- Extensions can edit UST lyrics, timing labels, and acoustic properties such as F0. source
- Input limitation
- The README says lyrics with multiple hiragana characters are unsupported except for the special handling described for small っ. source
- Installation
- The README says to drag the ENUNU ZIP file into the UTAU window to install it. source
- Installation
- The README says to install ENUNU by dragging its ZIP file into the UTAU window. source
- Intended users
- The stated use case is for people who want to use NNSVS singing voice models within UTAU. source
- License
- The software is distributed under the MIT License, which grants free use, copying, modification, distribution, sublicensing, and sale subject to its conditions. source
- License
- The repository identifies its license as MIT. source
- Model requirement
- A model folder needs an enuconfig.yaml, and its question_path must point to the file used in training and include that file. source
- Model support
- The README says ENUNU can use ordinary NNSVS models and recommends the ENUNU Training Kit for somewhat more stable results. source
- Pitch tools
- The f0_feedbacker extension feeds synthesized pitch back into the UST, and f0_smoother smooths steep pitch changes. source
- Platform
- The repository lists Windows 10 as its development environment. source
- Purpose
- ENUNU is a UTAU plugin that lets users use NNSVS singing voice models like UTAU voicebanks. source
- Purpose
- ENUNU is a UTAU plugin that lets users use NNSVS singing voice models in UTAU. source
- Support
- The README links to an installation and usage article on note.com. source
- Support
- The project repository provides a GitHub Issues section for reporting issues. source
- Training kit
- The linked Training Kit creates NNSVS or ENUNU models from UST, LAB, and WAV singing data and lists Windows 10 and 11 as its operating environments. source
- Voice colors
- The voicecolor_applier extension maps expression suffixes such as あ強 to model flags such as Power. source
- Warranty
- The MIT license states that the software is provided as is without warranty. source
- Workflow
- Users select an ENUNU model or a folder containing an NNSVS model in UTAU, then run the plugin on selected notes to generate a WAV file. source
- Workflow
- Users select notes in a UST and run ENUNU from UTAU’s plugin list to generate a WAV file. source
Checked against the maker's pages on 9 Oct 2026.