NNSVS

Spec sheet

Purpose

NNSVS is a neural network based singing voice synthesis library designed for research.Read 8 Oct 2026 · nnsvs.github.io

Intended users

The project says it was originally designed for research and recommends other tools for users who are neither researchers nor software developers.Read 8 Oct 2026 · nnsvs.github.io

Integrations

NNSVS integrates Optuna for hyperparameter optimization and uses MLflow to visualize and track search results.Read 7 Oct 2026 · nnsvs.github.io

Compute

GPU/CUDA is strongly recommended for performance, while Google Colab is listed as an option for users without GPUs.Read 8 Oct 2026 · nnsvs.github.io

Customization

Users can implement custom PyTorch models by inheriting NNSVS's BaseModel interface.Read 8 Oct 2026 · nnsvs.github.io

Input formats

Packed models can generate singing voice from MusicXML or UST files.Read 7 Oct 2026 · nnsvs.github.io

Inputs and outputs

With a packed model, users can generate singing voice by inputting MusicXML or UST files.Read 8 Oct 2026 · nnsvs.github.io

Languages

NNSVS has been used to create singing voice synthesis systems for multiple languages, with the documentation saying 8 or more as far as its author knows.Read 8 Oct 2026 · nnsvs.github.io

Licensing

The project’s GitHub repository lists the MIT license.Read 7 Oct 2026 · github.com

Notable limitation

The documentation says the post-filter is currently not recommended and neural-vocoder support is limited.Read 8 Oct 2026 · nnsvs.github.io

Open source

NNSVS is fully open-source, and users can create their own voicebanks with their dataset.Read 8 Oct 2026 · nnsvs.github.io

Optional compute

Users without a GPU can run NNSVS on Google Colab, though the documentation does not recommend Colab for hyperparameter optimization.Read 7 Oct 2026 · nnsvs.github.io

Requirements

The guide specifies Python 3.7 or later and says a C/C++ compiler must be installed in advance.Read 8 Oct 2026 · nnsvs.github.io

Research recipes

It includes reproducible Kaldi and ESPnet style recipes for creating baseline systems in research.Read 7 Oct 2026 · nnsvs.github.io

Research workflows

NNSVS includes reproducible recipes modeled on Kaldi and ESPnet approaches for building baseline systems in research.Read 8 Oct 2026 · nnsvs.github.io

Support information

The opened project pages provide installation guides, tutorials, and API reference documentation; they do not state a dedicated support service.Read 7 Oct 2026 · nnsvs.github.io

Supported operating systems

The installation guide lists Linux, Mac OS X, and Windows as supported platforms and says Linux is recommended for development.Read 7 Oct 2026 · nnsvs.github.io

Supported platforms

The installation guide lists Linux, Mac OS X, and Windows as supported and says NNSVS is tested on them with GitHub Actions.Read 8 Oct 2026 · nnsvs.github.io

Synthesis pipeline

Its documented system includes time-lag, duration, acoustic, post-filter, and vocoder modules.Read 8 Oct 2026 · nnsvs.github.io

Training limitation

The documentation says acoustic model training can take several hours or a whole day depending on configuration.Read 7 Oct 2026 · nnsvs.github.io

Workflow

Recipes cover data preprocessing, training, and synthesis, and can be customized with users’ own data and models.Read 7 Oct 2026 · nnsvs.github.io

Where Specifiction places it

• AI Singing Voice Generators#20 of 257.3