Sonic CD (1993) Aquatic Abyss - (Past Mix)

One of the more difficult songs that I covered (plainly because English voicebanks suck)

https://youtu.be/XJcWhEqazQs

𝐂𝐫𝐞𝐝𝐢𝐭𝐬
Music & Lyrics: KIRA
Vocals: Amy
VPR: me
Tune & Mix: me
Art Illustrator: jingsauce (twt @jingsauce)

𝐏𝐫𝐨𝐠𝐫𝐚𝐦𝐬 𝐔𝐬𝐞𝐝
FL Studio
Vocaloid 5 Editor

【 Amy 】Ladylike【VOCALOID5カバー】

I felt like putting an acapella of my most recent cover if people were curious how his vocals sound

Cover in question: https://www.youtube.com/watch?v=I-1yenq7oag

Natsume Yuuri || Decode (vocals only)

YT: https://youtu.be/uBRyjveQmG8

- original song by Kikuo
- Cover (VSQx, tuning, mixing) by me (Mckatherine)
- Voicebank: VY1V4 Power (with some little Normal and Soft)
- PV by Otori

- Software: Vocaloid 4, FL Studio

- Download in the "more" box!

光よ

VY1V4 - 光よ (Cover)  (+mp3)

github.com/r9y9/nnsvs

Test on a Neural source filter (NSF) model
NOTE: Training is still in progress (350k steps out of 400k)
NOTE: Haven't done any optimization yet

ust: www.nicovideo.jp/watch/sm39319737

Statistical parametric SVS (sampling rate: 48000)
Time-lag model: {
"_target_": "nnsvs.model.MDN",
"in_dim": 331,
"out_dim": 1,
"hidden_dim": 32,
"num_layers": 3,
"dropout": 0.5,
"num_gaussians": 1
}
Duration model: {
"_target_": "nnsvs.model.MDN",
"in_dim": 331,
"out_dim": 1,
"hidden_dim": 256,
"num_layers": 3,
"dropout": 0.5,
"num_gaussians": 1
}
Acoustic model: {
"_target_": "nnsvs.model.ResSkipF0FFConvLSTM",
"in_dim": 335,
"out_dim": 206,
"ff_hidden_dim": 1024,
"conv_hidden_dim": 512,
"lstm_hidden_dim": 256,
"dropout": 0.0,
"bidirectional": true,
"in_lf0_idx": 286,
"out_lf0_idx": 180,
"in_lf0_min": 5.162578582763672,
"in_lf0_max": 6.491110801696777,
"out_lf0_mean": 5.885598413281433,
"out_lf0_scale": 0.23067350503371858
}
Vocoder model: {
"generator_type": "HnSincNSF",
"generator_params": {
"aux_context_window": 2,
"cin_channels": 67,
"cnn_kernel_s": 5,
"cnn_num_in_block": 10,
"filter_block_num": 5,
"harmonic_num": 7,
"hidden_dim": 64,
"noise_std": 0.003,
"out_channels": 1,
"out_lf0_idx": 60,
"out_lf0_mean": 5.885598413281433,
"out_lf0_scale": 0.23067350503371858,
"out_vuv_idx": 61,
"sample_rate": 48000,
"sinc_order": 31,
"sine_amp": 0.1,
"upsample_net": "ConvInUpsampleNetwork",
"upsample_params": {
"upsample_scales": [
2,
3,
4,
10
],
"aux_channels": 67,
"aux_context_window": 2
},
"upsample_rate": 240
}
}

2022/04/06 Kiritan test SVS w/ NSF 350k steps Roshin Yuukai

i finished playing undertale yesterday

that game destroyed me

update: it's longer now

downloads are maxed out, it'll be up on bandcamp soon

Underhell

This is a story of love, loss, and life. And a legendary fan fiction from ancient times. NSFW or some shit.

A friend made this for me when I asked. They shall remain blameless for this grievous sin.

Cloud Mows The Lawn: A Text to Speech Drama

[DOWNLOAD VB] tansansuisui.jimdo.com/
[Youtube] https://youtu.be/RVMLCrO_NoM

Here's a new UTAU VB "Soda -Night-"s demo.
This VB has a sentimental voice.

The VB is made as "Renko-shiki CVVC(連呼式CVVC)"
If you need to know the VB's details, please read the manual.
Manual(OneDrive) https://1drv.ms/f/s!AvIhun7KOMzVeaNO8WjmX3FhYSA

[Vocal] Soda -Night-
[Original] 夜行便/Night Express - Baika-P/バイカP
http://www.nicovideo.jp/watch/sm24228307
* You can watch this video without your account!

* Baika-P/バイカP, 夜行便/Night Express's composer, allowed us to make this VB using the song's melodies.
We would like to take this opportunity to express our appreciation to him/her.

[Voice Provider] 炭酸水/Tansansui (Twitter tansansuisui)
[Project Creator, Otoing, Tuning, Mixing] まいこ/Maiko (Twitter maiko3tattun)
[Illustration] KITA/北口天神 (twitter Tent_Kita)
[De-noising] 塩釜/Shiogama (twitter shiogama_merry)
[Special Thanks] My friends and my brother

Thank you for listening!

[UTAU Cover+VB] Night Express/夜行便 [Soda -Night-]

ust: anti machine
It's a lot faster than the previous verison and overall using it is much snappier.
This bank doesn't use arpasing, sorry if you were expecting me to try that out just yet...

Moresampler 0.8.0 Test

The video will explain it all https://youtu.be/A-kV_KB-q-M! So happy to be able to release him!

DL Links:
https://bit.ly/decpaulVCCV
https://bit.ly/decpaulVCV

The credits here just in case:
Tools used:
wavtool4vcv
doppeltler009

Daisy Bell (Bicycle Built for Two)
Original - Harry Dacre
Instrumental - JivingGerbil https://www.youtube.com/watch?v=iANFExQtcLE
UST+Tuning+Mixing - Me

星のカケラ/ballade 01
Original - Eiji Hirasawa
Instrumental - Utaureni/Lauren
UST+Tuning+Mixing - Me

DECtalk Paul English VCCV and Japanese VCV Release

yes chris, i'm afraid- i'm afraid that our albert is DEAD!!

VSQX/VPR/Tuning/Mixing: Me
Voicebanks: Kagamine Rin & Len V4 English, Hatsune Miku V3/V4 English, Tonio, Big Al, and Chris
Music by: Walter Murphy

Moresampler 0.8.0 Test

na4a4a

Related tracks