Quite a long time ago now I saw a mini video documentary about Vocaloid, and specifically Hatsune Miku, a virtual singer popular enough in Japan to have real-life concerts. This absolutely blew my mind, I mean think about it: technology was able to create a singer out of thin air, and people liked it so much that they figured out how to do a concert where the singer wasn't a real person.

Ok, perhaps I should back up a little bit and explain better, Vocaloid is a piece of software created by Yamaha (the only instrument and motorcycle company) released in 2004 (hey look that's when I was born) designed to produce text-to-speech in music. Then in 2007 they released Volaloid 2 including new "singers", one of which was Hatsune Miku, a character who's voice comes from samples of Saki Fujita's voice. Hatsune Miku was popular enough to have multiple concerts for which they used a special reverse-projection screen to look like she's actually on the stage (i.e. the screen is transparent).

With the history out of the way on to my thoughts, as well as the impressive and absolutely neat technology involved. Like I said when I first heard of this I was absolutely amazed, though I didn't look into it further because I was quite young at the time and didn't think to try look up songs on youtube. Partially my enthusiasm was due to my desire at the time to live in Tokyo, or even just Japan in general, which was in turn due to my watching this youtube series as it came out (wow that was 7 years ago). But there was also a piece of me that just thought it was absolutely insane that given the state of text-to-speech (remember early Siri?) at the time, there was any way to produce music out of it, combined with the fact that they made a virtual character come to life and I was sold. But even now I still find it absolutely amazing, and I absolutely intend on attending one of those concerts at some point, but now I can have even more of an appreciation for the technology involved.

I know this was a bit of a short post and originally I was planning on talking more specifically on the technology but I didn't end up implementing a text-to-speech of my own yet like I planned due to losing interest in the project so for now that's really all I have to say unfortunately. I was also going to say more about my personal fascination with it but I legitimately can't pin that down, so for now this is all I have for you. Keep an eye out for a part 2 though.