Hey~! This page is informative~!
The content of this page may be of interest to readers, contributors and visitors.

Hello, and welcome to the world of UTAU! This is a tutorial to get you acquainted with the basics and terms used in UTAU. This tutorial will explain where to get UTAU, terms, and default voices in addition to answering one of the big questions: what is UTAU?

What is UTAU?

UTAU or Vocal Synthesis Tool UTAU is a voice-synthesis software developed by Ameya/Ayame and made for the Windows, and Apple operating systems. Like Vocaloid, you are in control of a vocalist to sing your songs for you. Though UTAU doesn't have as many features as Vocaloid, UTAU does give the option to import your own voices or others' voices into it to be used for singing. This will be covered in later tutorials. UTAU is a shareware (yet your payment is optional). Everything is practically free, so if you paid for anything concerning UTAU or its voices, you've been cheated!

UTAU is in no way affiliated with Vocaloid. Its engine was developed by a group of users, not YAMAHA (the creators of the Vocaloid engine), or CRYPTON FUTURE MEDIA (the creators of Vocaloid voicebanks Hatsune Miku and others).

The creators of UTAU have said all voices can be used in commercial work with no charge. However, a person can sue if their voice was recorded without permission, so please don't record any famous singer's voice.

For a detailed description of the history of UTAU, see this link. To download the UTAU engine, see this link. Have fun!

Default Voice

The default voice that comes with a fresh install of UTAU is Uta Utane/Defoko. More voices can be obtained by searching UTAU download pages located here, YouTube, Nico Nico Douga, or Google. You need to download and install those optional voices such as Teto or Ruko manually when using voices other than Defoko. Also see the UTAU library page.


MIDI - A .midi file is another export-audio file that can be imported into other applications. It has a small file size because it does not store any actual sound data - instead, it is made up of a list of instructions that tell the program how to play a piece of music. Think of a MIDI file as sheet music and the program you export it into as an instrument. A MIDI will play your voicebank in UTAU, but importing MIDIs into other applications will cause the voice to be replaced with that program's sound bank. This is the same as trying to get a clarinet from a piano by playing a piece of clarinet sheet music on a piano.

MP3 - Yet another audio export file. This is a popular file format for sharing because of its small size and high compatibility with music players, but it's less flexible than MIDI and doesn't have the quality of WAV. A good idea is to export a WAV as a 'master', and then make an MP3 from that as a 'single' which you can send to others.

RAR - A .rar file is a compressed folder that can carry many files at once. To open a .rar, you will need a file extractor, like Winrar.

Vibrato - Vibrato isn't actually a UTAU-used term, but an instrument-related term. It's the wavy sound heard at the end of a note on an instrument, or at the end of a note sung by a person.

Voicebank - Refers to the voices used in UTAU. A voicebank is a series, or bank of files used to make a UTAU sing.

WAV - A .wav file is an audio file that UTAU uses to make a voicebank sing. All voicebank files are made in .wav format, and anything exported from UTAU is also a WAV.


Western computers without eastern-hemisphere language support cannot run UTAU correctly if the voicebanks are in kana. Kana must be converted into romaji to run correctly.