UtaiSynthesizer

Spec sheet

Purpose

UtaiSynthesizer is a singing-voice synthesis DAW that turns scores into vocals using voice-conversion models.Read 5 Oct 2026 · utaisynthesizer.net

Support

The project directs bug reports and feature requests to GitHub Issues and links to QQ and Discord community groups.Read 5 Oct 2026 · github.com

License

The project repository is licensed under AGPL-3.0.Read 5 Oct 2026 · github.com

DAW features

Features include a piano roll, multi-track timeline, node workflow, vocal separation, training monitor, and vocal-range tools.Read 5 Oct 2026 · github.com

Download integrity

The security policy says downloads are SHA-256 verified and updates are minisign verified.Read 5 Oct 2026 · github.com

Downloads

The official site links to a Windows download, and the repository specifies Windows 10 or 11 x64.Read 4 Oct 2026 · utaisynthesizer.net

Import and export

It exports audio, UST, USTX, and MIDI, and imports USTX, UST, MIDI, audio, and voice-model packages.Read 5 Oct 2026 · github.com

Integrity

The repository says downloads are SHA-256 verified and auto-updates are minisign signed.Read 4 Oct 2026 · github.com

Languages

The app has a trilingual Chinese, English, and Japanese interface and supports lyric pronunciation in seven languages.Read 5 Oct 2026 · github.com

Limitations

The README says AMD runtime coverage is limited to gfx1103-class integrated GPUs and Intel XPU support is experimental and unverified on real hardware.Read 5 Oct 2026 · github.com

Local processing

The maker describes voice-model training as on-device and says inference runs without requiring Python.Read 4 Oct 2026 · github.com

Models

The repository and official installer do not include singer voice models; users import or train their own.Read 4 Oct 2026 · github.com

Offline operation

The app runs locally and says it connects only for update checks, model and asset downloads, and an optional mirror connectivity test.Read 5 Oct 2026 · github.com

Platform

The official site offers a Windows download, and the project README specifies Windows 10 or 11 x64.Read 5 Oct 2026 · utaisynthesizer.net

Recording and training

The maker says a dozen minutes of dry vocals and about an hour or two of training can create a voice model.Read 4 Oct 2026 · utaisynthesizer.net

Score-to-singing

Its Score2ConVec model converts notation into features that let an SVC voice model sing without an intermediate human vocal recording.Read 4 Oct 2026 · github.com

Security reporting

The project asks users to report vulnerabilities through GitHub's private vulnerability reporting rather than public issues.Read 5 Oct 2026 · github.com

Singing workflow

Its Score2ConVec model maps a score into ContentVec features so an SVC model can sing from notation without a human guide vocal.Read 5 Oct 2026 · github.com

SVC backends

It supports RVC and SoVITS backends, with shallow diffusion and multi-speaker voice blending.Read 4 Oct 2026 · utaisynthesizer.net

Training

Users can train voice models on-device using downloadable embedded runtime packs, with no Python required at inference time.Read 5 Oct 2026 · github.com

Voice models

The app supports RVC and So-VITS-SVC backends, with shallow diffusion and multi-speaker voice blending.Read 5 Oct 2026 · github.com

Where Specifiction places it

• AI Singing Voice Generators#23 of 256.8
• AI song cover generators#52 of 556.8