• We're currently having issues with our e-mail system. Anything requiring e-mail validation (2FA, forgotten passwords, etc.) requires to be changed manually at the moment. Please reach out via the Contact Us form if you require any assistance.

SynthV CeVIO AI / Synthesizer V Tsurumaki Maki

pico

robot enjoyer
Sep 10, 2020
528
In regards to her English talk bank, if I remember correctly, doesn't Cevio talk allow you to adjust the pitch/timing/etc of the different parts of the sentence? Because to me, those are the only things about these demonstrations that sounded like they could use some work. her pronunciation of the phonemes themselves didn't seem too terribly accented. If the software works the way I think it does, it may not make a good plug-and-play TTS, but it will be great for generating female character voices for animations and talkloid type things.
My thoughts pretty much line up with this. She's not incomprehensible, but the pacing/construction of the sentences definitely sounds like a Japanese speaker learning English's expectation for a sentence rather than a native English speaker's expectation of the same sentence. We'll see what the clarity's like once the product is in the hands of proficient English-speaking users. Might be the same. Might not be.

I'm more excited to see the English SynthV bank now.
 

Rylitah

kiyoteru enthusiast
Staff member
Moderator
Apr 8, 2018
575
A bit late but no one's posted it, so! New art for her English Talk bank and also seems like her Japanese bank's illustration has a lot of bonus facial expressions. She's posted at least one alternate expression for the English one too, so it'll probably be just as varied.


(Also a bit unrelated, but I don't think anyone's mentioned this yet either: the illustrator for Maki's Synth V designs is the same artist who drew the chibi illustrations for AHS characters in the past.)
 

Rylitah

kiyoteru enthusiast
Staff member
Moderator
Apr 8, 2018
575
Release date June 18!

For Synth V, her Standard and AI banks are bundled together, separated by language. (If you're purchasing via download, it's all available separately for 9680 yen each.)

CeVIO AI banks are separated by language but can also be bought together. (Download is 8778 yen each)


She'll come with two MMD models on all packages, though these will be distributed for free later.


Also, new demos:
 

peaches2217

Give me Gackpoid AI or give me DEATH
Sep 11, 2019
1,930
26
Arklahoma
I'm gonna be honest, I was expecting her to be a lot more expensive. She's only about $10 more a pop than Rikka, so I'm happy!

God, her Talk... they're easily the best-quality CeVIO AI talk banks we've gotten so far. Her accent in English is precious, but doesn't skimp on understandability. I'm already working her into my budget as we speak, and I might just have to get CeVIO now too!

EDIT: Listening through her demos, her English AI and Standard song banks sound... I dunno, kinda like appends of each other? God, I love them both so much... I might have to take the plunge and get both English banks! For her Japanese I'll likely stick with Standard, but. Oh my God I stan her so hard.
 
Last edited:

frankensalad

Passionate Fan
Feb 27, 2019
103
I was skeptical with the whole issue of her voice provider changing, but damn, I'm really impressed by all this. Both of her English singing banks sound really nice. I especially love her English AI, but English standard sounds like it would be good for when you need her to sound a bit more forceful and nasally. Like Peaches said, it's like they're "appends" of each other.

And listening to that English talk demo ... I still feel like the recordings and samples are great, we just need to hear what it sounds like when someone who speaks English as their first language and knows a bit about how stress-accent languages work is at the controls tuning her.

And of course all of her Japanese banks sound great, but I wasn't worried about those ones.
 

Silver1063

Aspiring Fan
Apr 19, 2019
52
I'm trying to understand the lyrics for Dancing in binary. Some parts are easier to understand than others and I think its probably because its written by Japanese speakers (I think?) so some of the lyrics are a bit... unconventional.

[Should kind of bid hi do the sky]
I literally have no idea what she supposed to be saying here
Mmm
Like falling down the snow
Raindrop like a tears on cheek
Shade is falling in my heart
Knock knock, hello my best friend
How's it going, Yeah, today
My voice sounded loud and lone
Woah, we will let go

Ah we are living like that world
Can you give you're ????

Let me tell ya
Let me tell ya
people shouting virtually
Nothing crazy
Nothing crazy
Dancing in the binary

Does it ??? you
and despite a way
We we're made to satisfy
When you are melting down and see a fantasy

yesssss​
 
Last edited:

frankensalad

Passionate Fan
Feb 27, 2019
103
That looks about the same as what I could hear. Honestly, I think given the song was very likely tuned by a Japanese person with minimal English skills, she still came out sounding pretty understandable.
 

aru ii

Your Neighborhood Tianyi Enthusiast!
Feb 12, 2021
1,010
VOCALOID4 Editor
I made a clip of the moment they revealed her ENG TTS. (It's a thread that contains my humble opinion on the quality.)



Also, the stream is continuing again (it stopped briefly).
I actually really like her accent. It sounds like her vp is trying really hard on the pronunciation. I was actually not interested in maki SynthV/CeVIO at all and her English demo made me unexpectedly very interested in her (even tho I never was interested in English vbs)
 
  • Like
Reactions: nachodorito

peaches2217

Give me Gackpoid AI or give me DEATH
Sep 11, 2019
1,930
26
Arklahoma
I actually really like her accent. It sounds like her vp is trying really hard on the pronunciation. I was actually not interested in maki SynthV/CeVIO at all and her English demo made me unexpectedly very interested in her (even tho I never was interested in English vbs)
I don't quite know why, but when her English was announced, I immediately had high hopes for it. The one English bank AHS is really associated with is Nana English, who's freaking good, so that might be the reason... but either way, I'm so glad my gut instinct ended up being right. She sounds adorable, and once native/fluent non-native English speakers get their hands on her, she's really gonna shine.

And I don't think it's a matter of her VP "trying really hard", I think they just got someone who was fairly competent in English. English VBs can be great no matter the level of fluency (Meiko's English, for example), but you can really tell when the VP has a good grasp on the language.
 

Blue Of Mind

The world that I do not know...
Apr 8, 2018
699
Her English banks are pretty much what I expected for a VB originally in Japanese - audibly accented, but still understandable with the right tuning. The voice overall is cute, like Nana English. I'm a bit surprised that the AI and Standard banks have different tones though - AI kinda sounds like Maki Soft/Sweet, while Standard sounds like Maki Power or something.
 
  • Like
Reactions: nachodorito and xuu

nachodorito

Aspiring Fan
Apr 21, 2021
58
These banks sound real good! They fixed most of the issues I had in CeVIO's English, and Synthesizer V AI outsold (as usual). I think I'm getting her Eng Complete since Eng Std sounds like a "dark append" of sorts for Eng AI, and in the future I'm planning to get her CeVIO Talk
I just needed to share that the inabakumori demo was played over my school’s loudspeakers this morning. I could not make this up if I tried.
Someone in charge is a SynthV fan....
 
  • Like
Reactions: TheStarPalace

xuu

long suffering synth fan
Apr 8, 2018
671
23
UK
All I have to say is GOOD lord are her SynthV banks good... like far better than I expected based on the original demos. Her Japanese AI bank especially sounds amazing, I love how she sounds in inabakumori's demo. English is really cute while still being understandable, I hope we get a full length demo with it.
 

uncreepy

👵Escaped from the retirement home
Apr 9, 2018
1,618
I just needed to share that the inabakumori demo was played over my school’s loudspeakers this morning. I could not make this up if I tried.
Please give us more context as to who/what/why o_o;;



(I am only going to talk about the product presentation itself and not Maki's voice. Also, I am REALLY CRABBY today so my angry vibes are probably emanating from my text and I'm sorry.)

Let me get the info on both of Maki's products straight, please correct me if I'm missing anything.
  • We got a whopping one whole 1 minute demo of her English song bank by a non-native English speaker (Dancing in binary).
  • The English TTS demo lasts about 1 minute and the software isn't even complete because they're going to add intonation by June and part of CeVIO's word registration interface apparently isn't even translated into English yet (it's still in Japanese).
    • *cue Miku NT unfinished software but let us take your money flashbacks*
    • (By the way, wasn't CeVIO having delays/lack of demos with IA and ONE even though they're supposed to come out this month? Techno-Speech falling behind makes me nervous.)
  • The product pages on AHS for both her talk and song English have no English translations about the software itself or to make purchasing easier for non-Japanese customers.
    • (I am getting strong IA English vibes: How it's only sold on Vector in Japanese, which is NOT English customer friendly + seems a little like the product is more aimed at bilingual Japanese and otaku synth fans compared to "normal people")
Unless something changes when it's closer to her release in terms of lack of ease for English customers + "ew Western producers", I can't help but feel disappointment that it seems like AHS is allergic to reaching out to the Western fandom. Like... I'm getting tired of it seeming like many Japanese synth companies want our money but will do anything to avoid actually interacting with producers.
 

Users Who Are Viewing This Thread (Users: 0, Guests: 1)