UtaiSynthesizer
UtaiSynthesizer is a free, open-source Windows DAW that turns written scores into singing vocals through voice-conversion models.
What UtaiSynthesizer is
UtaiSynthesizer is a free, open-source Windows DAW that turns written scores into singing vocals through voice-conversion models. Its Score2ConVec model maps notation to features an SVC voice model can sing, without an intermediate human guide recording. The app supports RVC and So-VITS-SVC backends, shallow diffusion, and multi-speaker voice blending. A piano roll, multi-track timeline, per-clip node workflow, vocal separation, training monitor, and vocal-range extension support song creation. Dictionary-backed lyrics are available in Chinese, English, Japanese, German, French, Spanish, and Italian. It imports UST, USTX, MIDI, audio, and voice-model packages, and exports audio plus UST, USTX, and MIDI; audio formats include WAV, FLAC, MP3, OGG, OPUS, and M4A. Training runs on-device, while inference does not require Python. Singer models are not bundled, so users import or train their own. The project uses AGPL-3.0 and supports Windows 10 or 11 x64.
Good
- Free and open source under AGPL-3.0
- Supports seven dictionary-backed lyric languages
- Imports and exports common notation formats
- Trains voice models on-device
- Includes RVC and So-VITS-SVC backends
Watch out
- Singer voice models are not included
- Commercial use is restricted
- Windows 10 or 11 x64 is required
- AMD and Intel hardware support has stated limits
Who it suits
UtaiSynthesizer suits Windows music creators who want score-driven vocal synthesis and custom voice models. It is aimed at users comfortable importing or training singer models locally.
Verdict
UtaiSynthesizer combines score-based singing, voice-model training, and DAW-style editing in a local Windows application. You will need your own models and should check the stated hardware limitations before setup.
The facts
Each one read from UtaiSynthesizer's own pages, with the date it was checked.
What it does
- DAW features
- Features include a piano roll, multi-track timeline, node workflow, vocal separation, training monitor, and vocal-range tools.checked 5 Oct 2026
- Download integrity
- The security policy says downloads are SHA-256 verified and updates are minisign verified.checked 5 Oct 2026
- Downloads
- The official site links to a Windows download, and the repository specifies Windows 10 or 11 x64.checked 4 Oct 2026
- Import and export
- It exports audio, UST, USTX, and MIDI, and imports USTX, UST, MIDI, audio, and voice-model packages.checked 5 Oct 2026
- Integrity
- The repository says downloads are SHA-256 verified and auto-updates are minisign signed.checked 4 Oct 2026
- Languages
- The app has a trilingual Chinese, English, and Japanese interface and supports lyric pronunciation in seven languages.checked 5 Oct 2026
- License
- The project repository is licensed under AGPL-3.0.checked 5 Oct 2026
- 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.checked 5 Oct 2026
- Local processing
- The maker describes voice-model training as on-device and says inference runs without requiring Python.checked 4 Oct 2026
- Models
- The repository and official installer do not include singer voice models; users import or train their own.checked 4 Oct 2026
- Offline operation
- The app runs locally and says it connects only for update checks, model and asset downloads, and an optional mirror connectivity test.checked 5 Oct 2026
- Purpose
- UtaiSynthesizer is a singing-voice synthesis DAW that turns scores into vocals using voice-conversion models.checked 5 Oct 2026
- 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.checked 4 Oct 2026
- Score-to-singing
- Its Score2ConVec model converts notation into features that let an SVC voice model sing without an intermediate human vocal recording.checked 4 Oct 2026
- Security reporting
- The project asks users to report vulnerabilities through GitHub's private vulnerability reporting rather than public issues.checked 5 Oct 2026
- Singing workflow
- Its Score2ConVec model maps a score into ContentVec features so an SVC model can sing from notation without a human guide vocal.checked 5 Oct 2026
- Support
- The project directs bug reports and feature requests to GitHub Issues and links to QQ and Discord community groups.checked 5 Oct 2026
- SVC backends
- It supports RVC and SoVITS backends, with shallow diffusion and multi-speaker voice blending.checked 4 Oct 2026
- Training
- Users can train voice models on-device using downloadable embedded runtime packs, with no Python required at inference time.checked 5 Oct 2026
- Voice models
- The app supports RVC and So-VITS-SVC backends, with shallow diffusion and multi-speaker voice blending.checked 5 Oct 2026
Where it runs
- Platform
- The official site offers a Windows download, and the project README specifies Windows 10 or 11 x64.checked 5 Oct 2026
Alternatives to UtaiSynthesizer
- 1
Revocalize AI
Free planAndroidiOSWebAPI8.1From $9 a month - 2
SightSinger
Free planAndroidiOSWebmacOS8.0Free plan - 3
Kits AI
Free planWebAPIWindows7.7From $10 a month - 4
VoiSona Song
Free planiOSmacOSWindows7.6From ¥6,600 a year - 5
Audimee
Free planWebAPI7.5From $9 a month - 6
Tunela
Free planWeb7.4From $10.99 a month