Uploaded July 2024 | Updated September 2026, 13 hours ago
I did not expect Nicky to have that accent!
I recorded myself saying this and imported it into Praat. I labeled the phonemes the same way you label Diffsinger training data. I used my UST export script to export each note with the phoneme in brackets, so one note would be [s] and the next would be [ah]
I ran utalis on the output from Praat in OG utau. Saved that UST then imported it into OpenUtau.
Whatever you call the volume of each note, I didn't think it could be used by the Diffsinger renderer, but I was able to trace them. someone please tell me how to actually use parameters without manually drawing each part of the curve 🥲
outside of like rapping small sections and talkoids / HANASU, this method is extremely pointless. just use the utau at that point 😅
I did not expect Nicky to have that accent!
I recorded myself saying this and imported it into Praat. I labeled the phonemes the same way you label Diffsinger training data. I used my UST export script to export each note with the phoneme in brackets, so one note would be [s] and the next would be [ah]
I ran utalis on the output from Praat in OG utau. Saved that UST then imported it into OpenUtau.
Whatever you call the volume of each note, I didn't think it could be used by the Diffsinger renderer, but I was able to trace them. someone please tell me how to actually use parameters without manually drawing each part of the curve 🥲
outside of like rapping small sections and talkoids / HANASU, this method is extremely pointless. just use the utau at that point 😅
![[UTAUSnR] Wiki Wednesday Icon and Example Roundup #17 (161 - 170)](https://i.ytimg.com/vi/lB16MykFMII/mqdefault.jpg "[UTAUSnR] Wiki Wednesday Icon and Example Roundup #17 (161 - 170)
UTAU Search and Rescue blog: https://utausnr.blogspot.com/
UTAUs used:
#161 - フックスケッキー / Keki Fökkusu
#162 - Dr. Leaf / ドクター・リーフ
#163 - Fukaina Shinpai / 心配 不快な
#164 - Chiki Kami
#165 - Huxley Pittal / ハクスリー ピタル
#166 - Minty Mascgrinn / マスクグリン ・ミンティー
#167 - D.SUE / ディ·ス
#168 - Tsuyuri Mochida / 持田つゆり
#169 - Kai Takahashi / かい たかはし
#170 - YA-01 ARTEMIS
There are some wonky sounding USTs used here and I have no idea how I made them or when I made them. Im pretty sure I have no access to them now, but Im still confused.")
![[new singing synth utan test] え？あぁ、そう。 feat. 桃音モモ](https://i.ytimg.com/vi/mYP6_OxsJGs/mqdefault.jpg "[new singing synth utan test] え？あぁ、そう。 feat. 桃音モモ
I learned a lot today :) !
This can be improved further!
I felt like I was losing hearing in one ear and the tablet has really bad speakers, so the mix isnt great.
Momo has not been fully configured, so she can be improved further!
Hataori taught me a lot today about using Utan, but most important thing was actually how to edit pitch in Praat. did you know that in the previous version of this cover, one part was off key because the pitch ceiling was too low?! just changing the ceiling fixed it!
I edited the flatten and contour script I have always used to use intensity objects. That means that instead of sharing an mp3 for the sole purpose of using the intensity copy, I can just share the half megabyte intensity file!! (note: the audio file would still be required for the method involving utau unless Hataori redoes the script.)
what is utan? Utan is a new singing synth by @hataori301 which currently uses Praat as its GUI! The focus of Utan is voice copying. think Vocalo, but instead of a tuning mode... its the entire synth! There are no midis or notes or anything like that - everything comes from the textgrid for timing and the pitch data for... pitch. The engine has nearly no noise and its so clear and I am very much in love.
Eh, aa? sou by Chouchou-P
tuning copied from sm11088594
textgrid by me")
![[UTAUSnR] Wiki Wednesday Icon and Example Roundup #22 (211 - 220)](https://i.ytimg.com/vi/mie4K6IoZZ0/mqdefault.jpg "[UTAUSnR] Wiki Wednesday Icon and Example Roundup #22 (211 - 220)
UTAU Search and Rescue blog: https://utausnr.blogspot.com/
UTAUs Used:
#211 - Amaterasu Kaede / 天照楓
#212 - Amaterasu Miya / 天照宮
#213 - Amaya Heikatsu / 平滑天谷
#214 - Amy Murasaki
#215 - Ao Shiro Murasaki / Ao Murasaki / 青さ玲葉で津
#216 - Aoi Homura
#217 - Aoi Mizuki / 水木青い
#218 - Yuki Shizuka / 静か雪
#219 - Yume Nakamura / 中村夢
#220 - Yumeki Tamashine / 夢来魂音")
![[UTAU MEL UST Release] Kahit Maputi Na Ang Buhok Ko [An English UTAU Sings Tagalog!]](https://i.ytimg.com/vi/nCOj9ZwIZqU/mqdefault.jpg "[UTAU MEL UST Release] Kahit Maputi Na Ang Buhok Ko [An English UTAU Sings Tagalog!]
An English UTAU sings Tagalog?!
Yours can too!
Rey Valera – Kahit Maputi Na Ang Buhok Ko
Download the UST here:
https://drive.google.com/file/d/1rtPgEmivMJxlTw8wE3grP6DtH-fKs4E5/view?usp=drivesdk
(note - if I made any mistakes, feel free to correct them! I only know a few words of Tagalog.)
How to make a bank that can sing this:
https://drive.google.com/file/d/1rEKjaMy9pd_7amL4ZMrbhY7hQ_LFRKPu/view?usp=drivesdk
Vocals: Nicky B. MEL
Shes singing an octave lower than her actual average pitch at times, so she sounds a little strange
Video footage from Pexels.")
![[Utan German Test] 99 Luftballons - NENA](https://i.ytimg.com/vi/nOGO76wn_JA/mqdefault.jpg "[Utan German Test] 99 Luftballons - NENA
I thought Id have more time to explain in the video, but I guess not 😛
A voicebank that cant sing Ballons sings 99 Luftballons by Nena!
Thank you @hataori301 for making my favorite ever synth ☺️
Thank you to @zim-p for giving me encouragement to make this list!
This bank was recorded using my new German word list. I do not speak German, but I cross-referenced Wiktionary and an AI German to IPA site to make sure they agreed with the pronunciation. However, I may have messed up in some places because the TTS seems to have said a few things incorrectly.
https://pastebin.com/4TUMJVz2
The TTS recorded the list in fifteen minutes, so I would estimate a human to take around 45 minutes. The length is roughly 1.5 Japanese VCV banks.
I was planning on releasing this bank as an utau, but no. It is not good. I will use the bank of the first person to seriously record this to create the timed base OTO. I ask for the recordings to be in order in one large WAV file because I will create an Utan bank and then cut it up to create the base oto. Once I have the base OTO, then anyone will be able to slap the recording list into OREMO and use that fancy base oto 😎
If you dont speak German, this is a very, very difficult list. Please give love to zimty_p and record their German CVVC instead!!
https://germancvcv.weebly.com/
I used X-SAMPA because I copy and pasted the transcriptions from the transcriber. I can change the aliases to suit the needs of the voice provider. Only native German phonemes are included in this list so that the TTS wouldnt struggle with it.
Video made in https://vizzy.io
Background from Pexels")
