Sinsy vs SoulX-Singer

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.

SoulX-Singer is a singing voice synthesis model that generates voices for singers it has not been tuned on. Pitch, rhythm, and expression can be guided by melody-conditioned F0 contours or score-conditioned MIDI notes. Its voice-conversion system changes raw singing audio to a target singer’s voice while retaining melody, rhythm, and lyrics, without requiring lyric or MIDI transcriptions. It supports Mandarin Chinese, English, and Cantonese, plus singer-timbre cloning, cross-lingual synthesis, and lyric editing while retaining natural prosody. Preprocessing tools handle vocal separation, dereverberation, F0 extraction, voice activity detection, and lyric and note transcription. Users can edit MIDI metadata, including lyrics, phoneme alignment, pitches, and durations, before synthesis. Soul-AILab provides generation and conversion demos and a separate MIDI editor through Hugging Face Spaces; the repository also supports local inference. Code and model weights use the Apache 2.0 license. Maintainers caution that automatic preprocessing may misalign singing with lyrics and notes, so manual correction may be needed.