Kasane Teto (Synthesizer V Studio)

Kasane Teto	SynthV Studio	SynthV Studio 2	UTAU	VOCALOID	others	|	Originals	|	Gallery

Kasane Teto (Synthesizer V Studio)
Product Information
Catalog No.	SAHS-40484 (physical) SAHS-40485 (digital)
Company	TWINDRILL AH-Software Co. Ltd.
Release Date(s)	April 27, 2023
Status	Released
System Requirements	Windows, MacOS, Linux
Base Language(s)	Japanese
Type	Synthesizer V Studio (AI)
Licensing	Proprietary
Affiliations	Dreamtonics Co., Ltd. 2ch Crypton Future Media, Inc.
Product Page	Physical copies: AHS Store AHS Store (user discount) Amazon Japan Digital copies: AHS Store AHS Store (Starter Pack) AHS Store (Starter Pack; user discount) animate GAMES DLSite DMM GAMES Dwango JP Store SONICWIRE Vector PC Shop Lite versions: AHS Dreamtonics

This article is about the Synthesizer V Studio software known as a voice database. If you are looking for the Synthesizer V character then click here.

History

Following the rising popularity of Hatsune Miku, "Vippers" (Vip News Bulletin@2ch users), the creators behind the VIPPERloid series, schemed a troll "new VOCALOID release" as an April Fool's joke. Sen (線) provided the rough sketch and Nobuyo Oyama (小山 乃舞世 Oyama Nobuyo), whose name was a spoof of Doraemon's former voice actress Nobuyo Ōyama (大山 のぶ代 Ōyama Nobuyo), provided the vocal. The Teto project continued after the troll campaign, and her vocal was recorded again for use on UTAU, which vocal synthesis software was released two months earlier. UTAU and Kasane Teto were both unnoticed among VOCALOID composers at first, but during the last half of the year of her release, several creators started composing songs for her, causing her fame to be established during the following year. The voice provider's name reading was then changed to Oyamano Mayo (小山乃 舞世 Oyamano Mayo) to avoid unnecessary confusion.

Teto was given official acceptance to piapro on April 1, 2010, and to the Hatsune Miku -Project DIVA- series on October 10, 2011.

At some point in 2012, Tomohide Ogata from AH-Software Co. Ltd. came into contact with Oyamano Mayo, discussing the idea of turning Teto into a VOCALOID. However, the voice could not be reproduced in a satisfactory manner.

2021

At some point during Tsuina-chan's production for Synthesizer V Studio, Saki Ohenri from Tsuina, the Ogre Hunter Project contacted Oyamano Mayo about promoting Tsuina-chan, resulting in illustrating for the demo "Warau Kimi ni wa Fukukitaru". Around the same time, AH-Software contacted TWINDRILL to talk to them about Synthesizer V AI, suggesting that they could possibly reproduce Kasane Teto's voice through this voice synthesizer engine.

2022

Production of Kasane Teto's Synthesizer V AI project began around 2022 when Oyamano Mayo suggested that something interesting should be done for Teto's fifteenth anniversary though the ideas were vague. Companies they contacted for ideas included piapro and Crypton Future Media, Inc.. There were many ideas for Teto's new outfit and a lot of time was spent on deciding the final piece. Oyamano Mayo decided on a compilation of a military uniform and an idol look. Sakauchi Waka was commissioned for the artwork. Oyamano Mayo sent many data files to AH-Software to help them understand Teto's signature sound so it could be reproduced. She focused on four main types of voices, with four to six songs provided for each of them so AH-Software could analyze and decide which ones could be created.

Regarding Crypton Future Media, the team apologized to the company as Teto began as a sort of "Hatsune Miku rip-off" as a joke. In order to have Teto become a commercial product, Crypton's permission was a necessity as they served as a point of contact regarding her commercial use. If the company refused, then TWINDRILL needed to comply. Crypton gave the team their full support in commercializing Kasane Teto Synthesizer V AI.

2023

On April 1, 2023, TWINDRILL celebrated Kasane Teto's fifteenth anniversary since her release on UTAU and posted a teaser for an announcement scheduled for April 3. That day, AH-Software Co. Ltd. and TWINDRILL announced that Teto was expected to release as a Synthesizer V AI voice database on April 27 as physical and digital copies, and was eligible for the Synthesizer V Studio Pro Starter Pack. Her four Vocal Modes were confirmed to be "Joyful", "Cute", "Power", and "Mellow". A lite version was also expected to release. Oyamano Mayo returned to reprise her role as Teto's voice provider and the illustration was confirmed to be done by Sakauchi Waka. Her voice database would be shown during the AHS Official Live Broadcast Episode 190 on April 6.

According to a livestream hosted later in the day, Crypton Future Media assisted in coordinating and organizing the Kasane Teto Synthesizer V AI project. In addition, the voice provider requested that the demos would be mostly covers. This way, it would be easier to compare the improvement of the voice. The team chose certain songs that they felt would suit each Vocal Mode. It was also noted that there was uncertainty that OSTER project would accept the request to create an original song as they were considered "out of our league" but after asking, OSTER project accepted, resulting in the composition of "April Star". When the team first heard the song, they were moved to tears. It was noted that the decision to have OSTER project create the original was not only Oyamano Mayo's decision, but she and kappa were among those who wanted to have this specific producer compose for Teto. On April 6, in the AHS Official Live Broadcast Episode 190, it was announced that the Lite version will be released around May 8. In response to questions about a VOICEPEAK library, TWINDRILL reminded fans that there was a TALQu library available for speech synthesis. With how real people could make the TALQu voice sound, it served as a catalyst for creating the Synthesizer V AI library.

Pre-orders for physical copies began shipping on April 26. She released on April 27 as intended. Her Lite version was released later on May 8.

Updates

Kasane Teto AI v101b1 - June 21, 2023 

A free update for Kasane Teto was released following the Synthesizer V Studio 1.9.0 update. This implemented the new rap feature available for the English and Mandarin languages. Cantonese Chinese was added to the Cross-lingual Singing Synthesis feature as well as general improvements to the overall function, resulting in more accurate pronunciation that sounds closer to a native speaker when singing foreign words.

Kasane Teto AI v101 - July 6, 2023 

Final version update compatible for Synthesizer V Studio 1.9.0 which enables Kasane Teto to use the rap feature (English and Mandarin Chinese only) and allows for Cantonese Chinese Cross-lingual Singing Synthesis if the beta versions were not installed previously.

Kasane Teto AI v102b1 - August 2, 2023 

A free update for Kasane Teto was released following the Synthesizer V Studio 1.10.0b1 update. This enhanced pitch generation by utilizing Reinforcement Learning from Human Feedback (RLHF), translating to fewer off-key errors, making better use of vibrato, and creating more expressive transitions between notes. This also allowed for the use of the new "Enhancement" slider in the AI Retakes panel, which controlled the level of changes introduced by RLHF. For Synthesizer V Studio Pro users, feedback submission was enabled, allowing users to consensually share their preferred takes with only Dreamtonics for research and development purposes, where models trained with this feedback would be deployed in future voice database updates. Users may also opt out of this feature if undesired.

Kasane Teto AI v102b2 - September 28, 2023 

A free update for Kasane Teto was released following the Synthesizer V Studio 1.10.0b2 update, which was the second beta version following version 1.10.0b1 that introduced enhancements to voice databases and integrated the latest user feedback via Reinforcement Learning from Human Feedback (RLHF). Regarding the editor, numerous reported issues were addressed for a more fluid experience. A new generation of pitch models were trained using the extensive feedback from users over the past month, and the new models offered greater accuracy in voice timbre reproduction, as well as a reduction in mispronunciations. Dreamtonics also focused on issues from the previous beta release that made Vocal Modes seem less distinct on certain vocals, ensuring clearer differentiation in the 1.10.0b2 update. The latest update also introduced a new feature in the Note Properties Panel that allowed for even division of a note into multiple syllables, proving to be a useful tool for songs with faster tempos.

Kasane Teto AI v102 - October 19, 2023 

Final version update compatible for Synthesizer V Studio 1.10.0 which enables Kasane Teto to use Reinforcement Learning from Human Feedback (RLHF) as well as other enhancements (as listed in v102b1 and v102b2's notes) if the beta version was not installed previously.

Kasane Teto AI v103 - October 26, 2023 

A free update for Kasane Teto was released that added support for the Japanese language to the rap feature.

Kasane Teto AI v104 - April 4, 2024 

A free update for Kasane Teto was released following the Synthesizer V Studio 1.11.0 update. This implemented support for the Spanish language in the Cross-lingual Singing Synthesis feature.

Voice Database Information

Demonstrations

Demonstrations
右に曲ガール (Migi ni Ma Girl) - "Joyful" Vocal Mode	NicoNico YouTube
スカイスイマー (Sky Swimmer) - "Cute" Vocal Mode	NicoNico YouTube
エイプリルスター (April Star)	NicoNico YouTube
Alive - "Power" Vocal Mode	NicoNico YouTube
S.A.S - "Mellow" Vocal Mode	NicoNico YouTube
Dancing in the binary - Short Acapella Version; English Cross-lingual Singing Synthesis	YouTube
眠たいの歌 (Nemutai no Uta)	YouTube
Teto is Sleepy - English Cross-lingual Singing Synthesis	YouTube

Voice Databases

Product Information

Optimum

  Range: D3~G5

Versions

  Lite Version/FLT Available?: Yes (Lite)  Starter Pack Available?: Yes  Web Version Available?: No

Package details as noted:

Kasane Teto is a feminine Japanese voice database based on the singing style of Oyamano Mayo and was intended to carry the UTAU version's signature sound. As expected of an AI voice database, this enables her to sing with a more human-like and realistic voice. Teto's voice was described as both childlike and mature. She can sing in any genre with her straightforward and distinct sound.

Vocal traits as noted:

• While the Synthesizer V version of Teto is also considered "a new Teto", it was important that she and her Vocal Modes still sounded like her in addition to how people would want her to sound or else it would be considered a failure.
• With Diffusion Probabilistic Models (DPM), Teto can sing more realistically through changes in volume and breath, further enriching singing details, making each singing unique, and providing creators with more options. Through this mode, she can use AI Retakes to create multiple "takes" of a sung section to find an ideal vocal without the need for "laborious tuning". This feature is only available in the Synthesizer V Studio Pro Editor.
  • This does not apply to the Lite version.

Phonetic notes as noted:

• Phoneme format: Romaji
• Through Cross-lingual Singing Synthesis, Kasane Teto can sing in not only Japanese but also in English and Mandarin Chinese. Since the release of her v101b1 update on June 21, 2023, she can also sing in Cantonese Chinese with this feature; since her v104 update on April 4, 2024, she can also sing in Spanish with this feature. Cross-lingual Singing Synthesis is only available in the Synthesizer V Studio Pro Editor.
  • This does not apply to the Lite version, thus restricting the voice database to Japanese only.

Vocal Modes as noted (Synthesizer V Studio Pro Editor only):

• The paid version of Kasane Teto comes with four variations within the Vocal Mode function:
  • "Joyful": A bright and lively singing voice.
  • "Cute": A sweet, cute, and gentle singing voice.
  • "Power": A powerful and passionate singing voice.
  • "Mellow": A gentle and calm singing voice.
    • For the "S.A.S" demo featuring "Mellow", fans thought that it sounded like a "whisper" type of voice library. However, it was confirmed that the whisper-like voice was done by the producer's tuning work. "Mellow" should not be confused for a whisper-like voice database by default.

System requirements as noted:

Hardware Requirements:

• CPU:
  • Intel Core series 4th generation i5 (i5-4xxx) or higher
  • AMD Athlon X4 845, Ryzen series or higher
• RAM: 2GB or higher
• Disk Space: 1 GB or higher (for installing one voice database)
  • The amount of space required depends on the number of voice databases installed.
• Display: 1280 x 800 or higher

Software Requirements:

• Operating System:
  • Windows 11/10/8.1
  • Mac OS X: 10.11 or higher
  • Linux Ubuntu 18.4 or higher

Other:

• DVD-ROM Drive (physical edition only)
• Sound card
• Internet connection is necessary for activation and obtaining updaters.

License agreements as noted:

• TWINDRILL's Guidelines - Japanese; As of April 2023
• AH-Software's End User License Agreement - Japanese
• AH-Software's End User License Agreement - English
• Regarding the Lite version:
  • AH-Software does not accept technical inquiries regarding free software nor do they guarantee or support the operation of all free software.
  • AH-Software is not liable for any damages (including loss of data) caused by using free software. Users are cautioned to use the free software at their own risk.
  • The program may not be transferred, sold, lent, distributed or rented without AH-Software's permission, regardless of whether it is paid or free of charge.
  • Reverse engineering, including modification, decompilation, and disassembly, of their program for any purpose is prohibited.
  • Kasane Teto Lite may not be used commercially in any way
  • When using the Lite version of this voice database, "This work uses the Lite version" must be mentioned on any uploads.

Voice database sample

• Kasane Teto Solfège:
  
  • Vocal Mode Solfèges:
    • "Joyful":
      
    • "Cute":
      
    • "Power":
      
    • "Mellow":
      
• Kasane Teto Lite Solfège: