Fire your singers folks, Vocaloid 5 is here!

[GearNostalgia]

Well I red about it in some UTAU forum that it was not possible for regular users. You had to have a special license from Yamaha and some special software too.

That's correct. But even if you could get a license and software for free, the process is not for the feint of heart. For one thing, you have to find a vocalist and record all the necessary phonemes, whatever they are. There are tons of them. Then you have to go through the conversion process and "fix" all the problem ones.

A typical voice bank takes a good year to do.

Do you REALLY want to go through all that? If you're that dedicated, a license and some software isn't going to stop you. So that part of it is a non issue.

This isn't something a casual user is going to do. Hell, I wouldn't even want to do it even if I could get Celine Dionne down here to record all the parts.

People do this for the purpose of selling the libraries and making money.

Well. I would have to quote Kennedy on this one cause sometimes some of us just want to do thing not because it is easy but because it is hard. I am purely into music for my own pleasure, I don't expect to ever earn a buck on it. I have turned other hobbies into work and with it comes preassure and deadlines that I don't need more in my life.

It doesn't seems to be so easy to make voices for UTAU, but there is some people enjoying doing it, I guess that Vocaloid cant be much harder than UTAU so I guess some would do it. I have a five year old that love to sing so I could see myself spending a lot of time on it just cause it would be cool to have my kid as a Vocaloid. But from I have digged up about it in forums it seems that you have to have some "corporate license" for it. So it may not only be a matter of blood sweat and tears, but also a big wad of cash to pay Yamaha.

[Pelicanomicon]

It doesn't seems to be so easy to make voices for UTAU, but there is some people enjoying doing it, I guess that Vocaloid cant be much harder than UTAU so I guess some would do it. I have a five year old that love to sing so I could see myself spending a lot of time on it just cause it would be cool to have my kid as a Vocaloid. But from I have digged up about it in forums it seems that you have to have some "corporate license" for it. So it may not only be a matter of blood sweat and tears, but also a big wad of cash to pay Yamaha.

The company behind crowdfunded Vocaloid Tohoku Zunko asked for (and got) abt $50,000.

Other charas in the same mascot series as her were released as free UTAU banks
zunko.jp/con_voice.html (warning: anime!)

you can listen to the wav files inside the zips to get an idea of how singing robot sausage is made

[rezoneight]

For the most part, I confine my music postings to Music Cafe. And so I don't dominate the whole forum, I put all my tracks in one thread, unlike some people who have 50 different threads floating around that forum, not that I personally have a problem with it. But some people do when they go there and they see 10 threads by one person. Believe me, I try to subject people to my "crap" as little as possible without giving up my right to post my music just like anybody else in this forum.

Anyway, I apologize. I didn't mean to rip your head off. I still can't believe you think I sing well or even passable. But I guess everybody hears things differently. Some people have told me to never sing again and I can't even argue with them because I myself hate my voice. I sure as hell don't expect them to like it.

Sitting here at 3am wide awake and one of the reasons is this thread. Listen, I have no right to say a thing about anyone's creative outlet. I want musicians to excel at their craft and unfortunately I chose to be a bit of a loudmouth instead of being encouraging, which was the real intent. If Vocaloid gets you where you want to be that is all that matters, not the ramblings of anyone in a thread on a music forum website. So my apologies. I refuse to add more ugliness to a world that is already full to the brim with it.

At this point I'll remove myself and let everyone discuss the topic at hand.

[GearNostalgia]

It doesn't seems to be so easy to make voices for UTAU, but there is some people enjoying doing it, I guess that Vocaloid cant be much harder than UTAU so I guess some would do it. I have a five year old that love to sing so I could see myself spending a lot of time on it just cause it would be cool to have my kid as a Vocaloid. But from I have digged up about it in forums it seems that you have to have some "corporate license" for it. So it may not only be a matter of blood sweat and tears, but also a big wad of cash to pay Yamaha.

The company behind crowdfunded Vocaloid Tohoku Zunko asked for (and got) abt $50,000.

Other charas in the same mascot series as her were released as free UTAU banks
zunko.jp/con_voice.html (warning: anime!)

you can listen to the wav files inside the zips to get an idea of how singing robot sausage is made

The Japanese translations may be a bit off, but if I understand it this is just one voice bank for Vocaloid3, right?

[wagtunes]

Finished my first Vocaloid 5 track. Kept it simple for a first try. Not easy to work with but tolerable. The lack of sync between DAW and Editor is a real PITA.

Anyway, this is Amy on lead vocal. She doesn't sound all that bad.

(Nothing But) Seasons

Sounds okey to me. She sounds more airy and breathy than the other Vocas I have heard and that is a good thing. So it seems to me that you have been harsh on the new Vocas. Good demo. Just wondering, do you have Melodyne? I wonder if it would be possible to change the tone of Vocas using Melodynes "synth to chance the harmonics".

I don't have Melodyne. I guess you could use it on Vocaloid but I have no idea what effect it would have or if it would sound any better or worse.

[wagtunes]

People telling me my voice sounds good makes me think they're either tone deaf or crazy. I hear my voice and I cringe. It used to be passable when I was younger. In fact, there were times when it was decent. But now? Forget it. I'd rather walk on broken glass than ever make another recording of me singing.

So can we PLEASE drop this already?

I perfectly understand you. I don't like to hear my own voice either. There is always people that will just keep poking you with the same point over and over. They may have good intentions about it, but if it gets repeated a lot it gets annoying in the end. Music and sounds is a sensual and emotional experience. We all like different things, lets just leave it with that.

I am very glad you share your honest opinions about Vocaloids cause I have recently learned not to trust salesmens demos. The Yamaha demo gave me the impression that Cubase would load the full new interface and that the new phrases would improove the experience a lot, but it seems like it is not all that great in terms of workflow. Did they respond to your request for a refund BTW?

Actually, I didn't ask for a refund. I just expressed my displeasure with the software. Now that I at least got it "working" and got a decent sound out of Amy, I'm content enough to keep it.

Oh to answer your other question, all I did with Amy is use the "To The Stars" preset which seems to be a decent one. Didn't do anything else other than what I normally do.

[wagtunes]

For the most part, I confine my music postings to Music Cafe. And so I don't dominate the whole forum, I put all my tracks in one thread, unlike some people who have 50 different threads floating around that forum, not that I personally have a problem with it. But some people do when they go there and they see 10 threads by one person. Believe me, I try to subject people to my "crap" as little as possible without giving up my right to post my music just like anybody else in this forum.

Anyway, I apologize. I didn't mean to rip your head off. I still can't believe you think I sing well or even passable. But I guess everybody hears things differently. Some people have told me to never sing again and I can't even argue with them because I myself hate my voice. I sure as hell don't expect them to like it.

Sitting here at 3am wide awake and one of the reasons is this thread. Listen, I have no right to say a thing about anyone's creative outlet. I want musicians to excel at their craft and unfortunately I chose to be a bit of a loudmouth instead of being encouraging, which was the real intent. If Vocaloid gets you where you want to be that is all that matters, not the ramblings of anyone in a thread on a music forum website. So my apologies. I refuse to add more ugliness to a world that is already full to the brim with it.

At this point I'll remove myself and let everyone discuss the topic at hand.

Don't worry about it. It's all good.

[GearNostalgia]

I don't have Melodyne. I guess you could use it on Vocaloid but I have no idea what effect it would have or if it would sound any better or worse.

It is not really about making the voice better or worse. You can raise and lower some partials of a sound and get a different tone. I think you would like to use it on some of your Vocaloids, look at this example.

https://www.youtube.com/watch?v=Ol0OZ3xzsjs

[Scotty]

With melodyne you could extract the timing of the notes and the subtle pitch change data and use that data with Vocaloid. You would have to manually enter your lyrics and do a lot of fussing to get the lyric line to fit in and would likely modify the midi data accordingly.

The biggest challenge with Vocaloid isn't the midi timing data, it is coaxing convincing sounds out of each voice which are all different and then depending upon what you want to achieve adding performance elements to it to have more musical/human qualities.

I've not read all the posts, I just have a query.

I don't sing, can't sing and won't sing. I don't like hearing my voice.
Anyway, in theory, could someone record their vocals, then, apply Melodyne to convert it to midi data. Then use Vocaloid with the midi data.
If the Vocaloid software does this, anyway. please forgive my ignorance.

Singing and midi are not among my strong points.

[Aloysius]

Have you considered rapping instead of singing?

[wagtunes]

I don't have Melodyne. I guess you could use it on Vocaloid but I have no idea what effect it would have or if it would sound any better or worse.

It is not really about making the voice better or worse. You can raise and lower some partials of a sound and get a different tone. I think you would like to use it on some of your Vocaloids, look at this example.

https://www.youtube.com/watch?v=Ol0OZ3xzsjs

Okay, I watched the whole video.

Here are my impressions.

From a tech standpoint, the software is cool. And maybe 2 years ago I would have gotten it just to be able to fool around and see what kind of weird sounds I can get.

But, and this is the only thing that matters, there is nothing in this video that I heard that impressed me. None of the sound modifications sounded good to me and the vocals were the worst. I would never use this on vocals unless I purposely wanted to make them sound even more synthetic than they do now.

So no, I have absolutely zero interest in this software. I can see its uses and I'm sure there are those who use it extensively on everything.

It's just not for me.

[Scotty]

My comment isn't intended for Wagtunes as he has been clear that he isn't interested ... but I think it shows a viable use for Vocaloid.

If you are a new producer and adding vocaloid to your productions it can be a fantastic learning tool. First off learning how to write vocal phrases and developing rhyming schemes is possible using synthetic voices. Once you have polished the melodic line and lyric, developing interesting vocal production techniques using effect processors like compressors, doublers, spot delay effects, vocal shops etc is the next step.

If you come up with something that you like you could hire a singer (or sing yourself if you are up to it) and give them the "mock-up" and then they could use that as a guide and take the track further. You could then tweak those production elements to fit with the human voice and have something that sounds very polished.

Not every track that you come up would warrant hiring a singer but those that do are going to better due to the advanced preparation that you already put into it.

I use this approach for some of my own material where I develop the mock ups first and then sing the part myself. The process of developing the melodic line using vocaloids often takes the melody into different places and the song can be better for the experimentation.

[wagtunes]

My comment isn't intended for Wagtunes as he has been clear that he isn't interested ... but I think it shows a viable use for Vocaloid.

If you are a new producer and adding vocaloid to your productions it can be a fantastic learning tool. First off learning how to write vocal phrases and developing rhyming schemes is possible using synthetic voices. Once you have polished the melodic line and lyric, developing interesting vocal production techniques using effect processors like compressors, doublers, spot delay effects, vocal shops etc is the next step.

If you come up with something that you like you could hire a singer (or sing yourself if you are up to it) and give them the "mock-up" and then they could use that as a guide and take the track further. You could then tweak those production elements to fit with the human voice and have something that sounds very polished.

Not every track that you come up would warrant hiring a singer but those that do are going to better due to the advanced preparation that you already put into it.

I use this approach for some of my own material where I develop the mock ups first and then sing the part myself. The process of developing the melodic line using vocaloids often takes the melody into different places and the song can be better for the experimentation as I did in this song.

https://www.youtube.com/watch?time_cont ... XOOQZkW3uM

I agree with you 100%. If you want a finished "professional" product, the above outline will help get you there. It makes the process a lot easier than it was years ago when you had no other options other than to hire a singer or sing yourself right from the start. Vocaloid is a great sketch tool.

[baggagelizard]

The original use for vocaloid in 2003 when it launched was to be used for temp tracks and experimental work and the like.

The things vocaloid has going for it is having a selection of virtual singers with different attributes and tones that vary from your own voice, the temp track options, and use as backup singers. If you combine a real voice with vocaloid the real voice will hide a lot of the flaws of the synthetic voices. Also don't need to bother with recording.

Don't think we're trying to replace a human singer, despite the thread title. There is a market both for the production and consumption of Vocaloid content, and that market is growing.

[GearNostalgia]

The original use for vocaloid in 2003 when it launched was to be used for temp tracks and experimental work and the like.

The things vocaloid has going for it is having a selection of virtual singers with different attributes and tones that vary from your own voice, the temp track options, and use as backup singers. If you combine a real voice with vocaloid the real voice will hide a lot of the flaws of the synthetic voices. Also don't need to bother with recording.

Don't think we're trying to replace a human singer, despite the thread title. There is a market both for the production and consumption of Vocaloid content, and that market is growing.

Well, the technology is not quite there yet, but I don't think we are far away from it. I hope it happens soon. We have digital simulations of Moog synths, Abbey Road plate reverbs and a lot of other great gear that very few of us would have a chance to play with some years ago. The advantages of getting really good voice technology could get us even further than real singers. Imagine beeing able to revive digital voices from the past like Elvis, George Michael, Jenny Lind or Edith Piaf and have it at your disposal to sing any tune in any style you like? Wouldn't that be cool? Listening to Google Duplex makes me think it might not be so far away.