Using UTAU is like collaborating with a real singer!

First, you prepare your "studio."
The "studio" here would be the UTAU program!

Then... you prepare your sheet music!In UTAU, this sheet music is called a UST (UTAU Sequence Text).

After you've gotten the sheet music down, you can now bring in your singer!

In UTAU, singers are granted the power to read and sing USTs thanks to a "voicebank."

By refining the UST and the voicebank, you can make your singer sing any song in any way!

And after you're done, you can begin to "record!"By telling the program that it's time to record, the computer renders the singing of the entire UST!

Now you can finally have vocals that you can mix into a music track!And there you have it! That's how UTAU works!

A voicebank contains 2 very important parts.These parts are the audio files and the configuration files.

Audio files are the data a voicebank uses in UTAU to sing.Here are examples of audio files in a voicebank:
"a_ba_bi_bu_be_bo_bo.wav"
"みみむまめみめ.wav"
"a_tsu.wav"
"ご.wav"

Configuration files, or more officially oto.ini files, split, time, and name audio files for use in UTAU.

Some configurations tell the program where to begin and end the sample......and others tell the program the "perfect" timing to match the recording with a note!

Additionally, there are aliases: names for cut samples that allow a UST to 'command' a singer to summon that sample.

Frequency Files (.frq) serves as pitch information from a recording. This helps UTAU 'flatten' the pitch so the singer can sing on-tune!

There are other parts of a voicebank, like folders, readme.txt, and character.yaml!But this is more important for managing and releasing voicebanks for different programs.

USTs are the sheet music for singers in UTAU.These USTs contain information like BPMs, notes, aliases, pitchbends, and vibratos.(USTs can hold other properties as well, but for now the above things are very important.)

BPM (Beats per minute) represents the tempo of a given song......while the notes are the length and pitches of certain syllables.

Speaking of syllables, aliases represent the names of a syllable.These aliases uses the information from a singer's oto.ini to help them sing correctly!

Lastly, pitchbends and vibratos serve as singing instructions to make the singer sing notes in a specific way.We refer to this as tuning.

USTs need to summon a specific singer. Only one singer can sing one UST (or track) at a time.

After that, USTs uses all the information stored inside it to give the singer instructions.Oftentimes, you may need to finetune a UST to make it compatible with a singer.