Sinsy
Nagoya, Aichi, Japan
What it is
Sinsy is a free web and Linux service that turns musical scores into synthesized singing vocals. Upload a MusicXML score, choose a vocal, and use settings labeled ALP, VIB, and PIT; Japanese appears as a language option. The system uses DNN- and HMM-based singing-voice synthesis to model characteristics such as pitch and timbre, rather than accepting vocal input. Sinsy was developed by the Tokuda, Nankaku, and Hashimoto Laboratory. Its version history lists version 5.1 on 2026/05/01, which addressed parameter-panel and smartphone or tablet behavior. Earlier updates added compressed MusicXML uploads in version 4.4 and Japanese DNN vocal f01027j_dnn_beta5 in version 4.5. The Free online synthesis plan costs nothing. The synthesis page states that generating vocals implies agreement to the site’s terms of use. The about page is available in Japanese and presents the project’s research background and history.
For and against
For
- Free online synthesis
- Accepts MusicXML score files
- Adjustable ALP, VIB, and PIT settings
- DNN- and HMM-based synthesis
- Japanese language option
Against
- No vocal input
- MusicXML is the required input format
- Terms apply when synthesizing vocals
- About page is available in Japanese
The verdict
Sinsy offers a focused, free route from MusicXML scores to synthesized singing. Its controls and vocal choices are designed around score-driven generation rather than recording or importing a singer.
Who it suits
Sinsy fits musicians or developers who want score-based singing synthesis through a browser or Linux environment. It is intended for users working with MusicXML rather than recorded vocal input.
Plans and prices
Free online synthesis
Uploads a MusicXML score to generate singing vocals
Read 8 Oct 2026 · sinsy.sp.nitech.ac.jp
On the record
- About page language
- The opened about page is available in Japanese and describes Sinsy's research background and version history.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Compressed files
- The version history says compressed MusicXML upload support was added in version 4.4 on 2023/12/25.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Current version history
- The about page lists version 5.1 on 2026/05/01 and says it fixed parameter-panel and smartphone/tablet behavior.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Development
- The about page says Sinsy was developed by the Tokuda, Nankaku, and Hashimoto Laboratory.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Input format
- The web page accepts a score file in MusicXML format.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Languages
- The synthesis settings on the current web page show Japanese as a language option.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Purpose
- Sinsy generates singing vocals from musical scores using DNN- and HMM-based synthesis.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Recent vocal addition
- The version history says Japanese DNN vocal f01027j_dnn_beta5 was added in version 4.5 on 2024/12/25.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Site terms
- The synthesis page says that synthesizing vocals implies agreement to the site's terms of use.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Synthesis method
- The about page says the system uses DNN- and HMM-based singing voice synthesis to model characteristics such as pitch and timbre.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
- Vocal control
- The page provides settings labeled ALP, VIB, and PIT alongside vocal selection.sinsy.sp.nitech.ac.jp · read 8 Oct 2026
