⏩ Next tutorial: Overview of all tutorials: -. To open a MIDI file into the UTAU program, go to “FileImport” and select your MIDI file. Pick the “3x0sc” Track, as that’s the one you worked on. When you import it, it’ll probably look something like this: Not to worry! This always happens. Manually editing the UST presets themselves. An option is to click on the OPT button (you can find this button on the far right of the secondary taskbar in the UTAU program itself) - this will optimize cross fading. Most USTs are already optimized in this division, so normally there's no need for that.
So we want to create our own UTAU. Consider it done!First off - here's a GREAT glossary of EVERYTHING UTAU related, so check this out!!
Summary of links; (these can be found below in the tutorial, I recommend reading through it all before clicking any of these links as it may just end up confusing you. Read and follow the tutorial before clicking the links if you haven't already)
Download UTAU here
English patch here
Audacity here
UTAU Glossaryhere
How to make a oto.ini file
Reclists / Recording Lists:
UTAU recordings (Japanese) Must record these for your UTAU to function!!
UTAU Download Site (Japanese)
UTAU recordings (english)
Credits to Hikari-P for the reclists
-------------------------------------
First off, you have to download UTAU from here (If you download the .zip file, the folder will be opened in WinRAR. I would extract it to your desktop. If you download the normal version, it will install as UTAU in your 'Programs' folder after you've run the .exe file)
You can download the english patch for it here (read how to in the forum posts)
For recording the samples, the easiest way would be downloading AudaCity, which is a totally free software many UTAU users, including myself, use in their UTAU making. This is for extracting the recordings as .wav files, if you have another software that can do that then there's no need to download AudaCity (though this tutorial will use it for teaching)
Next, for making our own UTAU, we want to create a folder with the UTAU's name. This is where we'll extract our recordings from AudaCity later on. Drag the folder into the UTAU folder's voice folder.
This is what it basically looks like in my voice folder. The voice folder should be in Programs -> UTAU, or if you downloaded the .zip version on your desktop/wherever you extracted it to under the name 'utau207' or something like that.
To add more UTAUs, search for a voicebank you want from YouTube/NicoNico and simply download it! Then just repeat what we did when we created our own voicebank by extracting the voicefolder from the downloaded UTAU into UTAU -> voice. Now you should be able to use it in UTAU! [OBSERVE! Users who have not installed Japanese on their computers won't be able to use Japanese UTAUs with voicebanks are encoded in hiragana, romaji UTAUs will work]
Next, you should take a look at this recording list for the Japanese Hiragana alphabet (the alphabet UTAU uses for making your UTAU sing in Japanese)
If you would like to download this as a .txt file, do so here
a i u e o
ka ki ku ke ko
sa shi su se so
ta chi tsu te to
na ni nu ne no
ha hi fu he ho hu
ma mi mu me mo
ya yu yo
ra ri ru re ro (sounds like 'dL' rather than 'R', so don't record 're', do a 'le' if you're having trouble pronouncing a Japanese 'dLee')n
ga gi gu ge go
za ji zu ze zo
da de do
ba bi bu be bo
pa pi pu pe po
kya kyu kyo
sha shu sho
cha chu cho
nya nyu nyo
hya hyu hyo
mya myu myo
rya ryu ryo
gya gyu gyo
ja ju jo
bya byu byo
pya pyu pyo
ye kye she che nye mye rye
gye jye bye pye
wa wi wu we wo
fa fi fe fo
ti
di
tu
du
It's notnecessary to record ALL of these, but the standard voicebank needs to have every letter from a - z with the vowels a, i, e, o and u to work properly with every UST.Onto recording then... [OPEN AUDACITY]
Utau Like Program
See All Results For This Question
| Original author(s) | Ameya/Ayame |
|---|---|
| Developer(s) | Ameya/Ayame |
| Initial release | March 2008; 13 years ago |
| Stable release | 0.4.18(e) (Windows); 1.0.0 b18 (Mac) / September 5, 2013; 7 years ago |
| Written in | VB6 |
| Operating system | Windows 2000 / XP / Vista / 7 / 8 / 10 Mac OS X |
| Platform | Windows, Mac OS X |
| Available in | Japanese and English (and other languages via patch files) |
| Type | Musical Synthesizer Application (Music sequencer) |
| License | Shareware (by donations) |
| Website | here |
UTAU is a Japanese singing synthesizer application created by Ameya/Ayame. This program is similar to the VOCALOID software, with the difference being it is shareware instead of under a third party licensing.[1]
Overview[edit]
In March 2008, Ameya/Ayame released UTAU, a free, advanced support tool shareware software that was free-to-download from its main website. UTAU (歌う), meaning 'to sing' in Japanese, has its origin in the activity of 'Jinriki Bōkaroido' (人力ボーカロイド, Manual Vocaloid), where people edit an existing vocal track, extract phonemes, adjust pitch, and reassemble them to create a Vocaloid-esque singing voice. UTAU was originally created to assist this process using concatenative synthesis. UTAU is able to use WAV files provided by the user, so that a singing voice can be synthesized by introducing song lyrics and melody. It comes with AQUEST's voice synthesizer 'AquesTalk' for synthesizing the voice samples of the default voicebank, Utane Uta (also nicknamed Defoko (Defoko meaning Default Girl in Japanese)) on UTAU's initial launch, after which the generator deletes itself. Voices made for the UTAU program are officially called 'UTAU' as well, though they are colloquially known as 'UTAUloids', a reference to VOCALOID. They are also called 'voicebanks' (more common in English-speaking areas) and '(voice) libraries' in Japan. A myriad number of voicebanks have been developed by independent users. These voicebanks are normally distributed directly from their creators via internet download, but some are sold as part of commercial projects.
UTAU is mostly a Japanese program and thus many of its voices are created specifically for the Japanese language. However, the number of available languages has been expanded by the users. English is a common language for UTAU to sing in. While there are a high number of bilingual UTAU, there are also multilingual UTAU that can sing in three or more languages. Often, X-SAMPA format is used for English voicebanks. Regardless of the voice's language, a user's computer must be in the Japanese locale or use AppLocale in order to run the software. Most of its documentation is in Japanese, but the User Manual has been translated into English. The program's interface was translated to English by Ameya, and other translations are still pending. However, the program still requires support for Japanese text.
UTAU's project files are saved under the '.ust' (Utau Sequence Text) extension. These files can be freely distributed, allowing different UTAU to sing the same piece. It is important to make note of the guidelines the UST creator has provided in terms of the .ust's distribution and use. Producers have developed several methods of producing their sound banks and results for the voicebanks vary because of this.[2] UTAU also supports MIDI format and .vsq format.
Ameya/Ayame added support for Unicode in an unreleased newer version of UTAU as per the screenshots posted on Twitter. The corresponding backend support tail fixed region as well as several other audio encodings has already been released, while frontend support is yet to be released as of September 2020. Ameya also updated UTAU to be compatible with 64-bit systems.
Configuration[edit]
The editor is capable of placing notes, entering phonemes, and changing pitch and volume on the piano roll. Only one track can be created in UTAU, and notes cannot be placed on top of each other. By default, only notes are displayed on the piano roll, but display settings can be changed to show the pitch curve, volume intensity, envelope, and flags. UTAU uses flags to change aspects of the voice, such as with low-pass and high-pass filters, and reducing or adding breathiness. These flags differ depending on the resampler used. Score information and data in the voicebank is processed with a resampler and wavtool based on the score created with the editor. Only one resampler can be utilized in a single .ust file. A formant filter is used to control changes in voice quality, which can be turned off.
The audio file to be loaded in is found by matching the symbols on the note with the audio file name in the library. However, a prefix.map file can change which subfolder the sample is taken from. The pitch of the synthesized voice is adjusted according to the difference between the original sound file and the pitch of the note in the editor. UTAU uses formant filters to prevent extreme changes in voice quality, which can be disabled. Batch processing is used to generate multiple notes at once. Cache files are created during this process. Depending on the resampler, the amount of cache files may increase. There are settings in the menu to delete cache files when the program is closed.
There are built-in plugins which can automatically merge vowels, and the 'Omakase/A la carte' settings which can add automatic pitch and vibrato to an entire file. Other plugins created by users can be added into the software, which preform various functions. The colors of the editor can also be changed in the setting.ini file.
Voices[edit]
As mentioned above, WAV files can be ported into UTAU. There can be hundreds of these files in a single voicebank. Voices are installed by either placing them in the 'voice' folder or dragging and dropping them onto the UTAU icon. These files also come with an oto.ini file which determines the timing and configuration of each sample. When outputting audio from the score data in the editor, the program uses the oto.ini to set timing and pronunciation. Oto.ini files can be created using UTAU's GUI. Frequency tables (.frq files) are used to process the waveform when changing the pitch in the editor. Some resamplers use other file types instead of .frq. The voices may also come with image files and standalone voice dialogues as some Vocaloids do. They also often include readme files which contain software information and terms of use.
Some voicebanks are monosyllabic, whereas others use diphthongs to produce a smoother sound.[3] These are collectively referred to as 'VCV' (vowel-consonant-vowel). These take considerably more time and effort to make, but produce a more natural result.
Later UTAU voices would include phonemes composed of vowels+consonants (VC) to accommodate languages other than Japanese. This method is referred to as 'CVVC', in which a VC phoneme is placed between two CV phonemes. Two rarer voice recording methods are CVC, where one phoneme consists of a consonant-vowel-consonant and is split up in the program by using the oto.ini, and a method called 'rentan-jutsu(れんたんじゅつ)', in which a series of CV syllables are recorded in multiple wav files in order to create a smoother result without resorting to full VCV.
Since the audio files are independent files, they can be used in other software such as a DAW.
Development[edit]
The development of UTAU started when Ameya began to use Audacity to recombine samples of other singers, and Melodyne to pitch correct the samples and set them to music. The act of doing this was referred to as 'human-powered VOCALOID'. LOLI.COM, a musician who posted his own rap music to Nico Nico Douga, used his own voice for human-powered Vocaloid and released an audio editing software which could help users do the same. Since the process of doing 'human-powered VOCALOID' by hand took a substantial amount of time and effort, Ameya began to develop a new tool which would aid the process.
The tool was announced on Nico Nico Douga on January 11, 2008. At that time, it was possible to adjust the timing of the sound, change the envelope of a note, and generate batch files. On 5 February 2008, a video was released showing the GUI. Here, it was possible to time stretch samples, create oto.ini files, and adjust the pitch bends of notes. [4] On 5 March 2008, a video explaining the program's specifications was released on Nico Nico Douga,[5] and on 15 March 2008, the tool was renamed UTAU.
The creator was a programmer by trade and not a specialist in vocal synthesis, but used previous knowledge to create UTAU. After its release, Ameya continued to improve UTAU, and started developing it in collaboration with other text-to-speech developers.[6]
In June 2008, Ameya rejected the label of 'Jinriki Bōkaroido' (人力ボーカロイド, Manual Vocaloid) for UTAU, calling it singing voice synthesis software instead.[7]
Audio files and copyright[edit]
Since UTAU can create a singing voice using any WAV files, it is possible to take the voice of an existing person and use it as data. Often, actors, singers, and celebrities will have clips of their voices re-purposed for use in UTAU. The creator, Ameya, once created a voice using data from a voice actor's CD.
In May 2008, Ameya decided to stop using audio data without permission for the time being, unless the voice actor allowed it.[8]
Cultural impact[edit]
Though the software is very popular in Japan, its origins and cultural impact are owed to the already established popularity of the Vocaloid software. UTAU itself was first made famous when the creator of Kasane Teto released the character posing as a Vocaloid character as part of an April Fool's joke in 2008. The influence of the Vocaloid software also led to both programs commonly being used side by side. Often popular UTAU mascots like Kasane Teto appear in VOCALOID-based media such as Maker Hikōshiki Hatsune Mix or Hatsune Miku: Project DIVA.
Later, the UTAU software would have its own impact on Vocaloid and other vocal synthesizers, with a number of vocals either referencing UTAU or being produced for the engine to begin with. For example, Megurine Luka V4x was influenced by the UTAU vocal 'Gahata Meiji'.[9] Wat from Crypton Future Media also spoke to someone very familiar with UTAU and said that the conversation was 'very interesting'.[10]Macne Nana of the Macne series later would become both a UTAU voice and a Vocaloid voice. The voice provider of English Vocaloid Ruby, Misha, had previously produced a Japanese-language UTAU named Makune Hachi (MAKU音ハチ). In addition, the vocalist for Dex, Kenji-B, created Kenji Baionoto (倍音音ケンジ) for UTAU, and AkiGlancy, the vocalist behind Dex's partner Daina, gave her voice to a UTAU called Namida (ナミダ). Kikuko Inoue, the voice actress of Macne Coco White and Black (Mac音ココ白・黒) (see Macne series) went on to voice a Vocaloid5 product by the name of Haruno Sora (桜乃そら). The product came with two voicebanks, 'Natural' and 'Cool'.[11] After the release of Vocaloid 3 vocal Tohoku Zunko, her two sisters Tohoku Itako and Tohoku Kiritan received UTAU vocals.[12] Kiritan would later have a crowdfund campaign for her to become a Voiceroid.[13]
Its main attraction is not only based on it being freely distributed on the internet, but because it allowed a user to insert their own voice into the database for use for music, opening the doors for users to further develop their own music. UTAU owes its growing popularity to its ability to provide a free method of creating voices for music use and has established numerous music producers working with the software on sites such as Nico Nico Douga and YouTube. Users also see it as an alternative to the Vocaloid software, which only offers a more limited supply of voices at a costly price and may not offer the voice types they are seeking for music, as the large database of voices often has a much greater chance of offering the voice they seek. However, despite the number of voicebanks offered, the software has overall far fewer producers working with it than Vocaloid.[14]
A radio station set up a 1 hour program containing nothing but Vocaloid and UTAU-based music.[15]
Utau Program Download English
In addition, an event called 'The UTAU M@STER' was held regularly from 19/7/2012 onwards. The event was the main gathering of groups or circles and was held in a similar fashion to the Vocaloid related event 'THE VOC@LOID M@STER' which had existed since 2007.[16]
Related software[edit]
Unlike Vocaloid, UTAU files are not restrictive as it is not a proprietary based license. Therefore, it is possible to use open-source license products with the UTAU software, such as those produced for the Macne series (Mac音シリーズ), released for the programs Reason 4 and GarageBand. These products were sold by Act2 and by converting their file format, were able to also work with the UTAU program.[17] Later, the Macne packages Whisper☆Angel Sasayaki, Macne Nana 2S and Macne Petit 2S came with pre-built UTAU voicebanks.
The default voicebank 'Defoko' (Uta Utane) borrows her voice from the software AquesTalk, specifically the voice 'AquesTalk Female-1' produced by A-quest. Permission had been granted for her distribution free with the software.[18] Koe Utane, Uta's 'sister', also borrows her voice from the AquesTalk software. Namine Ritsu (波音リツ), a vocal originally built for UTAU, also was later added to another software called 'Sinsy' as 'Namine Ritsu S'. Another vocal originally developed for the UTAU software, Yamine Renri (闇音レンリ), was also later added to a different software called 'Synthesizer V'.
Due to the software's own copyright agreement, non-open license software such as VOCALOID are not permitted to be imported into the UTAU software.[19]
A number of plug-ins for the software have also been developed by users of the software which add and enhance the vocals of the software.
The software 'Sugarcape', based on the same freeware intention as UTAU, has already entered beta stage.[20]There was an official Mac version of UTAU released on May 27, 2011, named UTAU-Synth.[21] It has approximately the same features as the Windows version. UTAU-Synth version can import both voices and songs made with the Windows version, but its project files and voicebank configurations are not fully compatible with the Windows version.
In late 2017 it was mentioned that Plogue Art et Technologie, Inc. had a working redirect adaptation that would make UTAU vocals appear in its engine Alter/Ego.[22]
Usage in music[edit]
The licensed songs from the album Graduation from Lie, featuring Teto Kasane, were released for music downloads from Karen-T, under Crypton Future Media, as a special release. This is the first licensed release of any UTAU.[23]Kasane Teto is famous for singing 'Ochame Kinou', a song famous for being catchy and having nonsensical lyrics. Momo Momone is also famous for singing 'Nyanyanyanyanyanyanya!', a song originally composed by daniwellP and sung by the VOCALOID Hatsune Miku. This song was made popular with the YouTube video of 'Nyan Cat'.
See also[edit]
References[edit]
- ^'歌声合成ツールUTAU' [Vocal Synthesis Tool UTAU] (in Japanese). Utau. Retrieved July 9, 2010.
- ^''Continuous Sound' Recording: UTAU Upgrades Realism – Vocaloidism'. Vocaloidism. Archived from the original on 27 March 2012. Retrieved 27 April 2016.
- ^''Continuous Sound' Recording: UTAU Upgrades Realism – Vocaloidism'. Vocaloidism. Archived from the original on 27 March 2012. Retrieved 27 April 2016.
- ^'自作ツールを使ってテキスト読み上げソフトに『片道キャッチボール』を'. Niconico. Retrieved 29 June 2021.
- ^'人力ボーカロイド支援ツールらしきものを作ってみた その１ 導入編'. Niconico.
- ^'あなたの声で歌うソフト「UTAU」の奇妙な世界'. ASCII.jp. Retrieved 29 June 2021.
- ^''真の人力Vocaloid'とは'. ＵＴＡＵについて. Retrieved 29 June 2021.
- ^Ameya. 'テト声の調整に本腰が入った理由 (Why I got serious about adjusting the Teto voice)'. Retrieved 31 July 2021.
- ^'crypton_wat'. Twitter. Retrieved 27 April 2016.
- ^'crypton_wat'. Twitter. Retrieved 29 April 2016.
- ^'井上喜久子のVOCALOID、VOICEROIDがついに登場！ 新VOCALOID5に対応！ 『VOCALOID 桜乃そら』『VOICEROID2 桜乃そら』 2018年7月26日発売'. ahsoft.com. AH-Software. Retrieved 29 June 2021.
- ^'東北イタコ、きりたんのUTAU音源'. Retrieved 27 April 2016.
- ^'クラウド出版'. Retrieved 27 April 2016.
- ^'How Big Is The Japanese Vocaloid Community?'. Archived from the original on 2010-12-13.
- ^'NHK の本気!ボカロラジオ「エレうた」の高き志' [NHK's Determination! High Aspirations with Vocaloid Radio 'Ere Uta'] (in Japanese). ASCII Media Works. February 5, 2011. Retrieved February 25, 2011.
- ^'「THE UTAU M@STER」UTAU only event'. Retrieved 27 April 2016.
- ^'Mac音ナナ シリーズ' [Macne Nana Series] (in Japanese). Act2. Archived from the original on May 11, 2011. Retrieved July 9, 2010.
- ^'音声合成ライブラリ製品の紹介 - 株式会社アクエスト'. Retrieved 27 April 2016.
- ^'Controversy Concerns/POCALOID and illegal modifications'. Vocaloid Wiki. Retrieved 2019-09-01.
- ^'Macで動くボーカルシンセを作る'. Retrieved 27 April 2016.
- ^'UTAU for Mac: UTAU-Synth'. Vocaloidism. Archived from the original on 27 March 2012. Retrieved 27 April 2016.
- ^'@chipspeech 5:19 p.m.—Nov 10, 2017 Tweet'. Twitter. Retrieved 1 December 2017.
- ^'Kasane Teto 'Graduation from Lie'' (in Japanese). Crypton Future Media. Retrieved October 2, 2010.
External links[edit]
- (in Japanese)Official website
- (in Japanese)Official website
- (in Japanese)Article on Japanese Wikipedia
- (in Japanese)Developer blog