• 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.

Other StudioVoICE Discussion Thread

nalondollie

the-ghost-of-a-cyber-princess
The new character is really cute! I do have to admit though, the demo for her voice seems almost too powerful and mature for such a young and cutesy looking character design haha. It seems there will be another character coming out in the future as well? judging by the grey silhouette.

The enrollment thing is pretty interesting too (or, as google translate calls it, the "naturalization plan"). I wonder if they will only be creating chinese vbs or if other languages will be permitted to enroll as well?
 

Prism

Enthusiast
Jul 18, 2019
524
Wow I love the sound of the new voice bank she sounds amazing. I don't like that design but that voice is so nice
 

xuu

long suffering synth fan
Apr 8, 2018
671
23
UK
Looks pretty cool. I think for now they're only looking for Chinese voices as they seem to request song titles be in Pinyin, and the example song is also Chinese. I wonder if they'll branch it out in future, though...
 

peaches2217

Give me Gackpoid AI or give me DEATH
Sep 11, 2019
1,930
26
Arklahoma
Does anyone know how phonetics/ lyrics work in it ?
Assuming it hasn’t changed, there’s no way to change the phonemes — you just have to enter hanzu. I haven’t read over all the updates though, much less tried it since then. Am I mistaken? Is there more flexibility now?
 

Prism

Enthusiast
Jul 18, 2019
524
doesn't look like it. Is there a standard phoneme character chart? like katakana
 

xuu

long suffering synth fan
Apr 8, 2018
671
23
UK
All the boys have such good designs... it makes me kinda wanna get back into this software LOL
EDIT: Just redownloaded the software... there's 15 voices now?!?! Zhir Bin has a really nice voice... I'll test them out now.
 
Last edited:
  • Like
Reactions: TheStarPalace

Prism

Enthusiast
Jul 18, 2019
524
This software is great has some of the best chinese male vocal synth imo. I really like the updates to the pitch
 

nalondollie

the-ghost-of-a-cyber-princess
I don't know if this has been shared here before but this article seems to talk a bit about StudioVoICE/X Studio:


my main takeaway of which I was not aware of before was that this program is part of a set of programs called x suite, the other two programs in the suite being x writer and x presenter
 

VocAddict

The Voice Within Us
May 8, 2018
55
24
The Other Side
voxil.net
I don't know if this has been shared here before but this article seems to talk a bit about StudioVoICE/X Studio:


my main takeaway of which I was not aware of before was that this program is part of a set of programs called x suite, the other two programs in the suite being x writer and x presenter
Yeah, X-Writer and X-Presenter is essentially Microsoft Office Word and Excel with AI features built-in. They're slowly expanding their use cases of Xiaoice from being a chatbot TTS and Singer to more and more products. I'm glad they managed to avoid the whole US-China trade war by being spun out and I hope that eventually it'll make it to Western markets.

If only the logo won't look so Microsoft Office-ish. I'm tired of mistaking it for Excel in my taskbar lol
There's a update with new voices, making the total 35 voices. There's some good ones in there.
Okay I saw the update and I knew it would have something nice but I didn't expect 35 voices wow.

It seems that the enrolment process is out in full swing. I would love to make a character for this software but I neither have the equipment or environment to record 24bit 48Hz songs without noice, nor can I sing in Chinese so rip me. I also believe you need to be within the PRC to provide relevant documentation so rip me lol. Quote below is a rough machine translate of the process.
1. The recording environment is quiet and noise-free (a professional recording studio with a signal-to-noise ratio of 40dB is recommended.) Amateur recording venues also have a chance to pass the preliminary examination, but are likely to affect the final AI singer's tone quality)
2. Record a dry sound, do not add any accompaniment, reverb, filters and other contemporaneous or later effects
3. Sing in the singer's most natural and comfortable personal style, without worrying too much about individual tones, while maintaining a natural breath and breath
4. Sing as much as possible to the melody and rhythm of the song, and you can adjust key to your comfort zone as appropriate
5. The tone, tone, and volume are as consistent as possible between all recorded song clear segments, so that the final singer's tone modelling works better
6. Each recorded song is sung and contains at least a complete melody from the beginning to the end of the first song
7. When recording each song, please leave a silence of 1 to 2 seconds before and after the start and end of each song
8. Please save the audio file in wav format with 24bit, 48kHz sample rate
9. Audio files are best named after the pinyin of the song's name for subsequent finishing

10. Mail subject: Sign up for the singer's naturalization program (that translation is pretty rough huh)
11. The applicant's contact information (please provide real and valid information to ensure that the legal process for the future AI singer's ownership goes smoothly.) After the first instance is passed, entering the formal data collection and pre-production legal process will require the applicant's identity information or the applicant's various supporting documents.)
12. (Optional) The AI singer to be applied for based information, such as name, gender, age, etc
13. Sent to: [email protected]
 
Last edited:

VocAddict

The Voice Within Us
May 8, 2018
55
24
The Other Side
voxil.net
Here's a few small set of covers from some of the voices now available. When you install it, one some of the profiles the link sends you their bilibili page where you may find some existing covers with that character. One thing I noticed from a few of them is that they're had existing banks on UTAU or DeepVocal and I find that to be pretty cool.

When it eventually extends to the Japanese market (my hopes aren't that high but I'm still hopeful), it would have a much larger explosion than it currently has in China but then again I'm not sure just how much XiaoIce is promoting this period of self-created banks. I don't have anything to cover in Chinese but I really love how they sound.

蔷芜
1617721547145.png
【蔷芜】 KING 【原pv附】【XStudio COVER】_哔哩哔哩 (゜-゜)つロ 干杯~-bilibili (Cover of KING by Kanaria)

幻神·米丝
1617721742785.png
神代梦华谭(X Studio 幻神·米丝 COVER 泠鸢yousa)_哔哩哔哩 (゜-゜)つロ 干杯~-bilibili (Cover of 神代梦华谭)

荼鸢
1617721857992.png
【XStudio荼鸢】Moonlight【XStudio Cover】_哔哩哔哩 (゜-゜)つロ 干杯~-bilibili
 

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