ENUNU
What it is
ENUNU is a free, open-source Windows plugin that lets UTAU users work with NNSVS singing voice models as voicebanks. In UTAU, select an ENUNU model or an NNSVS model folder, choose notes, and run the plugin to produce a WAV file. Installation uses the ENUNU ZIP dragged into the UTAU window. Extensions can edit UST lyrics, score or timing labels, and acoustic parameters such as f0. The voicecolor_applier extension maps expression suffixes such as あ強 to model flags such as Power. f0_feedbacker sends synthesized pitch back into the UST, while f0_smoother reduces steep pitch changes. Model folders require enuconfig.yaml, with question_path pointing to and including the training file. Multiple hiragana characters in one note are unsupported except for gemination (っ). The MIT License permits commercial use under its conditions and provides no warranty.
For and against
For
- Free and open source under MIT License
- Uses NNSVS models inside UTAU
- Extensions edit lyrics and acoustic parameters
- Pitch feedback and smoothing tools
- Commercial use allowed under license conditions
Against
- Windows platform only
- Multiple hiragana characters per note unsupported
- Models require a correctly configured enuconfig.yaml
- Software is provided without warranty
The verdict
ENUNU connects UTAU projects with NNSVS models and offers extensions for expression and pitch handling. Confirm model configuration and lyric constraints before building a voice workflow.
Who it suits
ENUNU suits UTAU users who want to use ordinary NNSVS singing models. It is for Windows workflows involving UST note editing and WAV output.
On the record
- Compatibility limit
- Lyrics with multiple hiragana characters in one note are unsupported except for gemination (っ).github.com · read 4 Oct 2026
- Download links
- The ENUNU account page links downloads for ENUNU 1.0.0, ENUNU Training Kit 2.0.1, and EnuPitch 0.2.0.linktr.ee · read 9 Oct 2026
- Extensions
- Extensions can edit UST lyrics, timing labels, and acoustic properties such as F0.github.com · read 9 Oct 2026
- Input limitation
- The README says lyrics with multiple hiragana characters are unsupported except for the special handling described for small っ.github.com · read 9 Oct 2026
- Installation
- The README says to install ENUNU by dragging its ZIP file into the UTAU window.github.com · read 9 Oct 2026
- Intended users
- The stated use case is for people who want to use NNSVS singing voice models within UTAU.github.com · read 4 Oct 2026
- License
- The repository identifies its license as MIT.github.com · read 9 Oct 2026
- 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.github.com · read 4 Oct 2026
- Model support
- The README says ENUNU can use ordinary NNSVS models and recommends the ENUNU Training Kit for somewhat more stable results.github.com · read 9 Oct 2026
- Pitch tools
- The f0_feedbacker extension feeds synthesized pitch back into the UST, and f0_smoother smooths steep pitch changes.github.com · read 4 Oct 2026
- Platform
- The repository lists Windows 10 as its development environment.github.com · read 9 Oct 2026
- Purpose
- ENUNU is a UTAU plugin that lets users use NNSVS singing voice models in UTAU.github.com · read 9 Oct 2026
- Support
- The project repository provides a GitHub Issues section for reporting issues.github.com · read 9 Oct 2026
- 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.github.com · read 9 Oct 2026
- Voice colors
- The voicecolor_applier extension maps expression suffixes such as あ強 to model flags such as Power.github.com · read 4 Oct 2026
- Warranty
- The MIT license states that the software is provided as is without warranty.github.com · read 4 Oct 2026
- Workflow
- Users select notes in a UST and run ENUNU from UTAU’s plugin list to generate a WAV file.github.com · read 9 Oct 2026
