UTAU

UTAU is a free vocal synthesis program for Windows that enables users to create singing by composing notes on a piano roll and attaching phoneme data to each syllable. It operates using voice banks—collections of recorded audio samples from a real singer or voice actor, along with timing and pitch information. Voice banks can be created by users or downloaded from online communities, and they are shared and remixed widely.

The software uses a concatenative synthesis approach, stitching together audio samples corresponding to phonemes according to the musical score. A voice bank typically includes samples for multiple phonemes, a pitch map, and sometimes additional data such as vibrato. Songs are authored by inputting notes and lyrics, with phoneme mapping defined for each syllable or mora. Output is usually rendered as WAV audio files, suitable for further mixing and mastering.

UTAU has a strong community focus, with a large repository of user-created voice banks in Japanese, English, and other languages. Because voice banks are user-generated, timbres and vocal qualities vary widely and can range from conventional to highly stylized. The ecosystem has evolved with extensions, scripts, and tools that enhance workflow and automation, as well as various forks and alternative interfaces developed by contributors.

While UTAU is not a commercial product like some proprietary vocal synthesizers, it remains popular among hobbyists and independent musicians for its flexibility, openness, and the ability to produce unique vocal tones through community-sourced voice banks.