Hacker News Reader

Comment by moth-fuzz | Hacker News Reader

The new V6 vocaloids even with the AI expressiveness still sound very much like vocaloids. There's a specific timbre to the way they pronounce certain vowels or do odd formant shifts that always comes through that I'm unsure of if it's intentional or not - on one hand it's very signature, on the other hand it doesn't sound quite as 'realistic'.

As far as the iconic characters go, they're moving to an entirely different engine (Piapro NT) anyways, so I wonder how future works created using them will sound.

View on HN

Agreed. I wonder how much of it is intentional; one of the common complaints I see from Synth V users is that none of the voice banks, except maybe Eleanor Forte, have that synthetic, "vocaloid-y" sound. Maybe they know they can't compete on realism, so they're leaning into the signature sound?

Solaria sounds like a well tuned Vocaloid.

Solaria can be very good. There's a song, Dawn by Circus-P, that I've used on a few occasions to startle people with its apparent authenticity. It exhibits an unnatural range, but there are only a couple of moments (unfortunately, near the start) where the pronunciation sounds clearly artificial if you know what you're listening for.

Gumi is definitely an iconic character, and the new Gumi release is probably as big as the Vocaloid 6 news itself. (Not only are there a lot of "vocaloid classics" that were made with Gumi, but some of the biggest hits in the past few years, such as KING by Kanaria or Getcha by Giga and Kira, have used Gumi.)

I kind of suspect Piapro NT is going to end up being a bust, with a pivot back to Yamaha's platform. We're a few years in and they've still only released Miku, none of the other Crypton Future Media characters, and a lot of people are sticking to the Vocaloid 4 release because they're not fans of how NT sounds. Now V6 is out and the technological gulf is widening.

The Vocaloid sound is basically part of the brand now. I can't imagine them ever changing it, and if they did, the existing producers would most likely shun it in favour of the sound that they've gotten used to.

Agreed. I think a proper solution for them to this would just be to create a separate spin-off product that is focused on realistic voice synthesis, while continuing the development of the typical-vocaloid-sounding product line as they currently are.

The audience wanting more vocaloid-like sound and the one wanting more realistic sound aren't really the same, and the overlap between them, I suspect, is not large. So it makes way more sense to capture the latter group by creating that more-realistic-voice spin-off product line, as opposed to being forced to choose between the realistic and vocaloid-like target demographics.

We already know the size of vocaloid-sound target audience, but I bet the audience for realistic-sound synthesis is going to be magnitudes larger (mostly because of versatility of where that tech could be useful, while with vocaloid it is mostly constrained to music production and vocaloid-related visual arts accompanied by a typical vocaloid voice).

There's nothing stopping them from making new "characters" that sound more realistic.

Check out Synthesizer V with Eleanor Forte.

Synth V is extremely fast and the output is shockingly good with some tweaking - good enough to be indistinguishable for many people.

Huh, even really good tuning has that quality. [1]

[1] https://www.youtube.com/watch?v=GcxIuAWX7Ws

Reply on news.ycombinator.com