Sinsy vs Tunela

Sinsy is a free web service that generates singing vocals from musical scores. You upload a MusicXML score, choose a vocal, and adjust settings labeled ALP, VIB, and PIT; Japanese appears as a language option. The system uses DNN- and HMM-based 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, with fixes for parameter-panel and smartphone/tablet behavior. Earlier entries record compressed MusicXML upload support in version 4.4 on 2023/12/25 and the addition of Japanese DNN vocal f01027j_dnn_beta5 in version 4.5 on 2024/12/25. The service is listed for web and Linux. Its Free online synthesis plan costs nothing. The synthesis page says using the service implies agreement to its terms of use. The about page is available in Japanese and describes the research background and version history.

Tunela has no write-up on Specifiction yet; its figures are above.