VOCALOID2 – Hatsune Miku

Yeah, I know this is old news by now and everyone knows about it. But a recent post in a MySpace group (Anime In Progress) opted me to give what I think about Vocaloid and Miku Hatsune. But first a little bit of information for whoever doesn’t know what I’m talking about:

Vocaloid is a singing synthesizer application software developed by the Yamaha Corporation that enables users to synthesize singing by just typing in lyrics and melody. Yamaha announced its development in 2003 and in January 2004 the first application software product was launched. It was not released as a Yamaha product, but a software package of Vocaloid Singer Libraries was developed by third party licensees which included Yamaha’s Vocaloid software. Leon, Lola, and Miriam have been released from Zero-G Limited, UK, while Meiko and Kaito have been released from Crypton Future Media, Japan.

In January 2007, Yamaha announced a new version of the software engine, Vocaloid2, with various major improvements in usability and synthesis quality. Zero-G and others have announced plans to release products powered by the new software engine in 2007. PowerFX have released the first English package that is powered by Vocaloid2 named Sweet Ann. Crypton has followed and announced a series of character Vocaloid2 packages to be released, the first being Miku Hatsune. The second package Rin Kagamine is slated to be released in December 2007, while a third will be sometime in 2008.

Miku Hatsune is the first character in the Vocaloid Character Voice Series released on August 31, 2007. The name of the title and character of the software was chosen by combining Miku (未来), Hatsu (初), and Ne (音). The data for the voice was created by actually sampling the voice of Saki Fujita, a Japanese voice actress. Unlike general purpose speech synthesizers, the software is tuned to create JPop songs commonly heard in anime, but it is possible to create songs from other genres.



Slightly Edited Image from Official Website

The technology behind Vocaloid is amazing itself. The idea of making a song just by typing the lyrics and indicating the notes is mind-blowing! The only drawback is that you have to have a ‘vocal library’ to take the words from. In English, this can be a problem because even similar words can have multiple readings. The example I used was the difference between read and read. (The second one is past tense…) I don’t know about other languages, but Japanese is easier to make a song with. Every sound in the Katakana/Hiragana table, no matter what it’s used for, is consistent. The same TSU in TSUdzuku, HaTSUgo, and chiTSU {LOL!!} sounds the same no matter where in the word it’s at.

It won’t be long before Vocaloid perfects the technology and is able to correctly make a song in other languages. It also won’t be long before Vocaloid is used in place of real actors. Like CGI took over actors in movies like Toy Story, A Bug’s Life, or even Final Fantasy VII: Advent Children!! Soon enough Vocaloid will have a mind of it’s own and will take over the world!!! You have been warned!! >_<


There’s only a few things I can say about Hatsune Miku.

  • 1. MOE~!
  • 2. I love the character design
  • 3. I don’t really like her singing.

I’ve listened to her first album, “初音ミク – 1st song album” {I don’t know if it’s official or if it’s a fan-made album… -_-‘ }, I thought it would change what I think about her singing…but it didn’t. I still find her voice too ‘fake’ and artificial. There are things that a computer made synthesized voice cannot do, and one of them is being able to project energy or feelings correctly.

I just listened to Hatsune Miku’s version of “Tori no Uta” {AIR OP}, and the lyrics were there, the rhythm was there, but the hybrid feeling of melancholy and happiness I get from the song was not there. Granted, she is the first {and probably experimental} release by Crypton, so she’s just an example of what this technology can do. Maybe soon they’ll figure out how they can make certain words have some sense of energy/feeling.

Also, I think it will be a matter of time before this technology is implemented in video games. Games like “THE IDOLM@STER“. Wouldn’t that be awesome!? Not only will you manage your idol, but you’ll be able to make her sing to your liking!! High pitch this, long pause here, slow here, low pitch here, etc etc.!!! And you’ll be able to make her sing whatever you want!! MAKE IT HAPPEN NAMCO/BANDAI, MAKE IT HAPPEN!!! >_< I wonder if THE IDOLM@STER will be localized here in the U.S…but I highly doubt it. Whatever, I’ll continue studying Japanese so that I won’t have to rely on licensors!! ^_^’

I digressed…back to topic. Um….there isn’t anything more to say. -_-‘ Laters!!

2 thoughts on “VOCALOID2 – Hatsune Miku

  1. Are you stupid? You make it apparent you dont like the vocaloids singing, and claim that its too “artificial.” do you have ANY idea how the app was made? They took real people and made vocal lybraries, so whats fake about that, since its a real voice. ^-^

    • The library may have been made from a real person, but that doesn’t mean it will sound good. It’s still a computer, so the synthesized voice won’t sound as good as a singer’s voice, it still lacks the energy/feeling…well, at least to me. Other people love this.

      This was written about two years ago, and since then, I’ve tried listening to Hatsune Miku more and more, so far, the only songs I’ve like are the ones produced/composed by ryo. The album “supercell” is a pretty good example on how to use Hatsune Miku’s synthesized singing voice. And yes, it gives it a sense of energy/feeling to Hatsune’s voice and songs.

      Thanks to that album, I’m changing the way I see VOCALOIDs.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s