Kyomachi Seika (Synthesizer V Studio)

Kyomachi Seika	SynthV Studio	SynthV Studio 2	VOICEROID	VOICEPEAK	|	Originals	|	Gallery

Kyomachi Seika (Synthesizer V Studio)
Product Information
Catalog No.	SAHS-40308 (Complete) SAHS-40309 (Standard, digital) SAHS-40310 (AI, digital) SAHS-40377 (AI, physical)
Company	AH-Software Co. Ltd. Seika Town
Release Date(s)	January 27, 2022
Status	Released
System Requirements	Windows, MacOS, Linux
Base Language(s)	Japanese
Type	Synthesizer V Studio (Standard & AI)
Licensing	Proprietary
Affiliations	Dreamtonics Co., Ltd.
Product Page	Physical copies: AHS Store (AI) AHS Store (AI; user discount) AHS Store (Complete, Std & AI) AHS Store (Std & AI; user discount) Amazon (AI) Amazon (Complete, Std & AI) Digital copies: AHS Store (Std & AI) AHS Store (Starter Pack, Std or AI) AHS Store (Starter Pack, Std or AI; user discount) animate GAMES (AI) animate GAMES (Std) DLSite (AI) DLSite (Std) Dwango JP Store (AI) Dwango JP Store (Std) SONICWIRE (AI) SONICWIRE (Std) Vector PC Shop (AI) Vector PC Shop (Std) Lite versions: AHS (Std & AI) Dreamtonics (Std & AI)

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

In 2013, Seika was created as a mascot and public relations character for the city of Seika, which is located in Kyoto. As an official mascot, her character is used for promotions and collaborations that aimed to promote the city and encourage people to visit. After a successful crowdfunding campaign in 2015, she later became a VOICEROID in June 2016.

On December 21, 2020, a new crowdfunding campaign aimed at funding a Synthesizer V voice database was announced and set to begin two days later on December 23. The campaign aimed to raise enough funds for the production of a Standard singing voice database for Synthesizer V, an original song featuring Seika and her voice provider, Rika Tachibana, and ultimately a Synthesizer V AI voice database.

2021

On January 11, 2021, the crowdfunding campaign reached its initial goal of ¥4,000,000 for production of her Synthesizer V Standard voice database. In response to a fan on January 12, Seika's Twitter stated a Lite version of her Synthesizer V library was undecided. On January 21, the crowdfunding campaign reached its fourth goal of ¥ 6,000,000 for the production of her Synthesizer V AI voice database. The crowdfund officially concluded on January 31 with over ¥9,395,000 raised. Following the crowdfund, Rika Tachibana presented a congratulatory message for Seika on February 2.

On June 16, Seika's Twitter congratulated Tsurumaki Maki for her upcoming Synthesizer V release. It was also noted that Seika was making good progress in production and asked fans to wait a while longer. On July 28, AH-Software noted that Seika's voice database was in the process of being made at the time. On September 30, it was confirmed that Rika Tachibana had already finished recording for the Synthesizer V software and that development was going smoothly. A release was not expected until the beginning of 2022.

On November 21, new information about Kyomachi Seika was revealed during SEIKA Subculture Festival 2021. Her Synthesizer V design was revealed and confirmed to be illustrated by VOFAN, a Taiwanese artist, who was chosen due to the desire to market to Taiwan, though the COVID-19 pandemic prevented direct interactions. Her voice database was shown during the event for the first time and it was confirmed that Rika Tachibana was asked to sing about 40 songs for Seika's recordings. She chose fun and sad songs but was instructed to sing them all with Seika's bright voice and retain the same tone. Seika's beta version was then shown during the event, performing the song "Tsubasa".

On December 23, it was announced that Seika would be released on January 27, 2022 as physical and digital copies, as well as a starter pack with the editor. For the time being, she was available for pre-orders. Lite versions were also confirmed to be released at a later date.

2022

On January 21. 2022, Seika's Lite versions for both Standard and AI were released. On January 26, pre-order physical packages were announced to have been shipped out. Seika released on January 27 as intended.

On March 25, after the implementation of Vocal Mode via Synthesizer V Studio Version 1.6.0., AH-Software announced that other AI voice libraries, such as Tsurumaki Maki, were planned to receive them. On June 30, it was announced that Seika AI would be receiving a standalone physical package, which was expected to release on July 21, with pre-orders beginning on July 1.

On July 21, Kyomachi Seika AI was one of the AI voice databases to receive an update for HDVM compatibility (a feature introduced in Synthesizer V Studio Pro 1.7.0, also released the same day). This update also gave Seika access to four new vocal modes, including: Breathy, Bright, Straight, and Tight, respectively.

However, some users complained about unstable voice-quality results when re-rendering in 1.7.0 projects saved under earlier versions of the editor that made use of her voice database (after updating it to v106). On July 22, Dreamtonics explained that by default, the AI Retakes feature favors "rich timbre and expressions over smooth and stable vocalization", resulting in inconsistent behavior relative to previous versions; as a workaround to stabilize the voice output, both Dreamtonics and AH-Software offered these steps below:

• Empty the selection.
• Open AI Retakes panel, go to Timbre tab.
• Under Takes -> Global Settings, reduce Expressiveness.

Responding to requests from users, both Dreamtonics and AHS made available for download that same day rolled-back versions of Kyomachi Seika AI (as well as other affected AI voice databases distributed by them) by logging in to their respective websites.

Updates

Kyomachi Seika AI v106 - July 21, 2022 

A free update for Kyomachi Seika AI was released following the Synthesizer V Studio 1.7.0 update. This enables her to use the new High Dynamics Voice Models and AI Retakes features, as well as giving her access to the Vocal Modes feature from the 1.6.0 update. Her Vocal Modes are named "Breathy", "Bright", "Straight", and "Tight".

Kyomachi Seika AI v104 - July 25, 2022 

A free downgrade for Kyomachi Seika AI that removes HDVM compatibility, but retains the Vocal Modes introduced in v106.

Kyomachi Seika AI v108b1 - November 10, 2022 

A free update for Kyomachi Seika AI was released following the Synthesizer V Studio 1.8.0b1 update. This enables her to use the new Diffusion Probabilistic Models (DPM) feature.

Kyomachi Seika AI v108 - November 24, 2022 

Final version update compatible for Synthesizer V Studio 1.8.0 which enables Kyomachi Seika AI to use the new Diffusion Probabilistic Models (DPM) feature if the beta version was not installed previously.

Kyomachi Seika AI v109b1 - June 21, 2023 

A free update for Kyomachi Seika AI 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.

Kyomachi Seika AI v109 - July 6, 2023 

Final version update compatible for Synthesizer V Studio 1.9.0 which enables Kyomachi Seika AI 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.

Kyomachi Seika AI v110b1 - August 2, 2023 

A free update for Kyomachi Seika AI 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.

Kyomachi Seika AI v110b2 - September 28, 2023 

A free update for Kyomachi Seika AI 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.

Kyomachi Seika AI v110 - October 19, 2023 

Final version update compatible for Synthesizer V Studio 1.10.0 which enables Kyomachi Seika AI to use Reinforcement Learning from Human Feedback (RLHF) as well as other enhancements (as listed in v110b1 and v110b2's notes) if the beta version was not installed previously.

Kyomachi Seika AI v111 - October 26, 2023 

A free update for Kyomachi Seika AI was released that added support for the Japanese language to the rap feature.

Kyomachi Seika AI v112 - April 4, 2024 

A free update for Kyomachi Seika AI 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

Synthesizer V Studio Standard

Demonstrations
メガロポリス納税 (Megalopolis Nouzei) - Full Version	NicoNico YouTube

Synthesizer V AI

Demonstrations
翼 (Tsubasa)	YouTube
メガロポリス納税 (Megalopolis Nouzei) - Short Version	AH-Software
大好き♥精華町！ (Daisuki♥Seika-chou!) - Short Version	AH-Software
メガロポリス納税 (Megalopolis Nouzei) / 大好き♡精華町！ (Daisuki ♡ Seika-chou!) - Short Versions	YouTube Twitter
ウラナク (Uranaku) - Short Version	AH-Software Twitter
大好き♡精華町！ (Daisuki ♡ Seika-chou!) - Full Version	NicoNico YouTube
メガロポリス納税 (Megalopolis Nouzei) - Full Version	NicoNico YouTube
ウラナク (Uranaku) - Full Version	NicoNico YouTube

Voice Databases

• Standard
• AI

Product Information

Optimum

  Range: B3~F5  Pitch Group: C4, F4, A4, D5

Versions

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

Package details as noted:

Seika is a feminine Japanese voice database with a solid and stable midrange and a sharp high range, which is best for creating a straight and candid tone.

Vocal traits as noted:

According to Rika Tachibana, Seika's voice provider, she was asked to record with a bright tone of voice.

Phonetic notes as noted:

• Phoneme format: Romaji

Software issues as noted:

As the Lite voice databases are generally restricted to monopitch (one pitch) only, Seika's range is noted to be F4 in this version.

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:

• Seika Town's Character Usage Guidelines - Japanese
• 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.
  • Kyomachi Seika Standard 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

• Kyomachi Seika Standard Solfège:
  
• Kyomachi Seika Standard Lite Solfège:
  
• A preview of Kyomachi Seika's Synthesizer V Studio AI and Standard voice databases (provided by the Dreamtonics website):
  

Product Information

Optimum

  Range: B3~D5

Versions

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

Package details as noted:

Seika is a feminine Japanese voice database with a solid and stable midrange and a sharp high range, which is best for creating a straight and candid tone. As expected of an AI voice database, this enables her to sing with a more human-like and realistic voice. Her voice database is based on the singing style of Rika Tachibana.

Vocal traits as noted:

• According to Rika Tachibana, Seika's voice provider, she was asked to record with a bright tone of voice.
• As per the Synthesizer V Studio 1.7.0 update launched on July 21, 2022, through High Dynamics Voice Models (HDVM), which later migrated to Diffusion Probabilistic Models (DPM) per the 1.8.0b1 update on November 10, AI voice databases may use AI Retakes to create multiple "takes" of a sung section with variations in pitch, dynamics, and timbre. This replicates the randomness of human vocalists, adds a more realistic feel, and allows users 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
• Rika Tachibana was asked to sing about 40 songs for Seika's recordings.
• As per the Synthesizer V Studio 1.5.0 update, through Cross-lingual Singing Synthesis, AI voice databases are able to sing in not only their base language but also in the other two available languages for the engine. This meant that Seika AI can sing in Japanese as her base language, and in English and Mandarin Chinese using this feature. However, it was found that upon purchase of her AI voice database, Seika was not available for Cross-lingual Singing Synthesis. A patch was later distributed to allow her to use this feature. Since the release of her v109b1 update on June 21, 2023, she can also sing in Cantonese Chinese with this feature; since her v112 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):

• As of July 21, 2022, the paid version of Kyomachi Seika AI became compatible with the Vocal Mode function introduced in Synthesizer V Studio 1.6.0. Her v106 update included four variations:
  • "Breathy"
  • "Bright"
  • "Straight"
  • "Tight"

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:

• Seika Town's Character Usage Guidelines - Japanese
• 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.
  • Kyomachi Seika AI 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

• Kyomachi Seika AI Solfège:
  
  • Vocal Mode Solfèges:
    • "Breathy":
      
    • "Bright":
      
    • "Straight":
      
    • "Tight":
      
• Kyomachi Seika AI Lite Solfège:
  
• A preview of Kyomachi Seika's Synthesizer V Studio AI and Standard voice databases (provided by the Dreamtonics website):