The "Status on Synthesizer V" page acts as a guide for readers and editors alike. The "Status" page lists all the voice databases produced using Synthesizer V technology; this includes any commercial releases, announcements, developments, and projects involving the Synthesizer V franchise.
Releases[]
The most commonly known Synthesizer Vs are the free or commercially sold units produced by first and third party studios. These are produced under license by Dreamtonics Co., Ltd. and are able to be downloaded for free or bought by any bidding producers through commercial outlets. Their quality and capabilities vary, as do the licensing agreements issued by the respected studios involved.
Synthesizer V[]
A total of 8 releases were available for Synthesizer V in English, Japanese, and Mandarin Chinese. It should be noted that not every voice database was deemed "completed", but were available for use regardless. This version of the engine and its compatible voice databases were officially retired on July 10, 2020.
| Product | Developer | Language | Voice Type | Sample | Release |
|---|---|---|---|---|---|
| Eleanor Forte | Dreamtonics Co., Ltd. VOLOR |
English | Feminine | Unrevealed | August 18, 2018 |
| Yamine Renri | Dreamtonics Co., Ltd. VOLOR Yuzuri |
Japanese | Feminine | Yuzuri | November 11, 2018 |
| GENBU | VOLOR | Japanese | Masculine | Gallo | December 23, 2018 |
| AiKO | VOLOR | Mandarin Chinese | Feminine | Liang Xiao Miao | December 28, 2018 |
| Chiyu | Beijing Photek S&T Development Co., Ltd. | Mandarin Chinese | Feminine | YouMao (UNEKO) | April 30, 2019 |
| Shian | Beijing Photek S&T Development Co., Ltd. | Mandarin Chinese | Feminine | Warma | June 20, 2019 |
| Cangqiong | Beijing Photek S&T Development Co., Ltd. | Mandarin Chinese | Feminine | Kinoko Mogu | July 9, 2019 |
| Haiyi | Beijing Photek S&T Development Co., Ltd. | Mandarin Chinese | Feminine | Huazheng Anly | September 6, 2019 |
Web Synthesizer V[]
Web Synthesizer V is an internet browser-integrated vocal synthesis engine developed by Dreamtonics Co., Ltd.. It was introduced as a branch off of the "SVR2" (later known as Synthesizer V Studio) development, but released during Synthesizer V's era. Web Synthesizer V uses minimized database versions of vocalists and have no system requirements aside from an internet connection and a supported browser.
A total of 3 releases were available for Web Synthesizer V in Japanese. It should be noted that only JA-F2's vocal remains functional as of December 2021.
| Product | Developer | Language | Voice Type | Sample | Release |
|---|---|---|---|---|---|
| JA-F2 | Dreamtonics Co., Ltd. | Japanese | Feminine | Unrevealed | December 31, 2019 |
| Saki | Dreamtonics Co., Ltd. | Japanese | Feminine | Unrevealed | July 22, 2020 |
| Kotonoha Akane & Aoi | AH-Software Co. Ltd. AI, Inc. |
Japanese | Feminine | Yui Sakakibara | July 22, 2020 |
Synthesizer V Studio[]
Synthesizer V Studio was initially introduced in July 2020 and only had Standard (initially known as "R2") voice database types available. AI voice database types were added in December that year. Lite versions were introduced as free downloads that encouraged trialing, and were single-pitched voice databases that had their own set of rules for commercial use. It should be noted that not every Synthesizer V Studio release would have both a Standard and AI voice database, and may only release as either one. They may also not have lite options available. With the introduction of rap-focused voice databases included since Synthesizer V Studio version 1.9.0, Feature-Limited Trials or "FLT" editions have been released as free downloads that also encouraged trialing, These vocals may be released for a limited time or are restricted to specific engine versions.
Synthesizer V Studio Standard[]
A total of 16 releases were available for Synthesizer V Studio in English, Japanese, and Mandarin Chinese as Standard voice databases.
Synthesizer V Studio Standard Lite[]
This is a list compiling the Standard voice databases available for Lite.
| Product | Developer | Language | Voice Type | Sample | Release |
|---|---|---|---|---|---|
| Eleanor Forte | VOLOR | English | Feminine | Unrevealed | July 30, 2020 |
| GENBU | VOLOR | Japanese | Masculine | Gallo | July 30, 2020 |
| Saki | Dreamtonics Co., Ltd. | Japanese | Feminine | Unrevealed | July 30, 2020 |
| AiKO | VOLOR | Mandarin Chinese | Feminine | Liang Xiao Miao | July 30, 2020 |
| Chiyu | Beijing Photek S&T Development Co., Ltd. | Mandarin Chinese | Feminine | YouMao (UNEKO) | July 30, 2020 |
| Kotonoha Akane & Aoi | AH-Software Co. Ltd. AI, Inc. |
Japanese | Feminine | Yui Sakakibara | September 24, 2020 |
| Koharu Rikka | TOKYO6 ENTERTAINMENT AH-Software Co. Ltd. |
Japanese | Feminine | Yoshino Aoyama | March 18, 2021 |
| Tsurumaki Maki | AH-Software Co. Ltd. | Japanese | Feminine | Manami Tanaka | June 3, 2021 |
| Tsurumaki Maki English | AH-Software Co. Ltd. | English | Feminine | Manami Tanaka | June 3, 2021 |
| Tsuina-chan | AH-Software Co. Ltd. Tsuina, the Ogre Hunter Project |
Japanese | Feminine | Mai Kadowaki | November 19, 2021 |
| Kyomachi Seika | AH-Software Co. Ltd. Seika Town |
Japanese | Feminine | Rika Tachibana | January 21, 2022 |
Synthesizer V AI[]
A total of 54 releases were available for Synthesizer V Studio in English, Japanese, Mandarin Chinese, and Cantonese Chinese as AI voice databases. As of Synthesizer V Studio version 1.11.0, all AI vocals are capable of Cross-lingual Singing Synthesis, which allows any AI voice database to not only sing in their base language but also fluently in the other four available languages despite not being trained nor recorded in them. Classification of multiple base languages is determined by a company's description of the product, confirmed recorded training materials, and/or separate releases. Cross-lingual Singing Synthesis is only available to the "Pro" version of the editor and only works with full releases.
| Product | Developer | Base Language(s) | Voice Type | Sample | Release |
|---|---|---|---|---|---|
| Saki | Dreamtonics Co., Ltd. | Japanese | Feminine | Unrevealed | December 25, 2020 |
| Koharu Rikka | TOKYO6 ENTERTAINMENT AH-Software Co. Ltd. |
Japanese | Feminine | Yoshino Aoyama | March 18. 2021 |
| Tsurumaki Maki | AH-Software Co. Ltd. | Japanese | Feminine | Manami Tanaka | June 18, 2021 |
| Tsurumaki Maki English | AH-Software Co. Ltd. | English | Feminine | Manami Tanaka | June 18, 2021 |
| Tsuina-chan | AH-Software Co. Ltd. Tsuina, the Ogre Hunter Project |
Japanese | Feminine | Mai Kadowaki | November 26, 2021 |
| Qing Su | Dreamtonics Co., Ltd. | Mandarin Chinese | Feminine | Unrevealed | December 1, 2021 |
| Eleanor Forte | VOLOR | English | Feminine | Unrevealed | December 6, 2021 |
| ANRI | AUDIOLOGIE Co., Ltd. | English | Feminine | kurapichu | December 11, 2021 |
| SOLARIA | Eclipsed Sounds, LLC | English | Feminine | Emma Rowley | January 19, 2022 |
| Kyomachi Seika | AH-Software Co. Ltd. Seika Town |
Japanese | Feminine | Rika Tachibana | January 27, 2022 |
| Ryo | Dreamtonics Co., Ltd. | Japanese | Masculine | Unrevealed | February 4, 2022 |
| Kevin | Dreamtonics Co., Ltd. | English | Masculine | Unrevealed | February 4, 2022 |
| Xingchen Infinity | Beijing Photek S&T Development Co., Ltd. | Mandarin Chinese[1] | Feminine | Chalili | February 20, 2022 |
| Mo Chen | Dreamtonics Co., Ltd. | Mandarin Chinese | Masculine | Unrevealed | April 9, 2022 |
| Natsuki Karin | TOKYO6 ENTERTAINMENT AH-Software Co. Ltd. |
Japanese | Feminine | Miyu Takagi | April 13, 2022 |
| An Xiao | Dreamtonics Co., Ltd. | Mandarin Chinese | Masculine | Unrevealed | May 4, 2022 |
| Feng Yi | Dreamtonics Co., Ltd. | Mandarin Chinese | Feminine | Unrevealed | May 27, 2022 |
| Weina | Dreamtonics Co., Ltd. Ready Steady Sound! Sound & Vision Media Studio |
Mandarin Chinese & English[2] | Feminine | Weina Hu | July 21, 2022 |
| Yuma | Dreamtonics Co., Ltd. | Japanese | Masculine | Unrevealed | October 7, 2022 |
| Natalie | Dreamtonics Co., Ltd. | English | Feminine | Natalie Nicole Gilbert | October 7, 2022 |
| Hanakuma Chifuyu | TOKYO6 ENTERTAINMENT AH-Software Co. Ltd. |
Japanese | Feminine | Kaya Okuno | October 20, 2022 |
| Mai | Dreamtonics Co., Ltd. | Japanese | Feminine | Honoka Kitta | November 10, 2022 |
| ASTERIAN | Eclipsed Sounds, LLC | English | Masculine | Eric Hollaway | December 2, 2022 |
| Xuan Yu | Dreamtonics Co., Ltd. | Mandarin Chinese | Masculine | Unrevealed | December 12, 2022 |
| Cong Zheng | Dreamtonics Co., Ltd. | Mandarin Chinese | Feminine | Unrevealed | December 12, 2022 |
| Cheng Xiao | Dreamtonics Co., Ltd. | Mandarin Chinese | Feminine | Unrevealed | January 9, 2023 |
| XIA YU YAO | E-CAPSULE Co. Ltd. VOICEMITH |
Mandarin Chinese | Feminine | Mi Yang | January 30, 2023 |
| Ninezero | Dreamtonics Co., Ltd. | English | Masculine | NINEZERO | February 16, 2023 |
| JUN | AUDIOLOGIE Co., Ltd. | English | Masculine | Lavy | April 20, 2023 |
| Kasane Teto | TWINDRILL AH-Software Co. Ltd. |
Japanese | Feminine | Oyamano Mayo | April 27, 2023 |
| Lin Lai | Dreamtonics Co., Ltd. | Mandarin Chinese | Masculine | Unrevealed | June 17, 2023 |
| Yun Quan | Dreamtonics Co., Ltd. | Mandarin Chinese | Feminine | Unrevealed | June 17, 2023 |
| Ritchy | Dreamtonics Co., Ltd. | English | Masculine | MBanja Ritchy | July 4, 2023 |
| D-Lin | Dreamtonics Co., Ltd. | Mandarin Chinese[3] | Masculine | Unrevealed | July 4, 2023 |
| Haruno Sora | AH-Software Co. Ltd. | Japanese | Feminine | Kikuko Inoue | August 24, 2023 |
| Eri | Dreamtonics Co., Ltd. | Japanese | Feminine | Unrevealed | October 26, 2023 |
| Sheena | Dreamtonics Co., Ltd. | Japanese & English[4] | Feminine | Unrevealed | October 26, 2023 |
| Hayden | Dreamtonics Co., Ltd. | English | Masculine | Unrevealed | October 26, 2023 |
| Wei Shu | Dreamtonics Co., Ltd. | Cantonese Chinese | Masculine | Unrevealed | October 26, 2023 |
| SAROS | Eclipsed Sounds, LLC | English | Masculine[5] | Unrevealed | November 24, 2023 |
| Ayame | Dreamtonics Co., Ltd. | Japanese | Feminine | Unrevealed | December 7, 2023 |
| Jin | Dreamtonics Co., Ltd. | Japanese | Masculine | Unrevealed | December 7, 2023 |
| ANRI Arcane | AUDIOLOGIE Co., Ltd. | English | Feminine | kurapichu | December 11, 2023 |
| Yongye Minus | Beijing Photek S&T Development Co., Ltd. | Mandarin Chinese | Feminine | Sawako Sui Hua Zi | December 17, 2023 |
| Megpoid | AH-Software Co. Ltd. Internet Co., Ltd. |
Japanese | Feminine | Megumi Nakajima | December 20, 2023 |
| POPY | AH-Software Co. Ltd. Bushiroad Inc. |
Japanese | Feminine | Aimi | December 21, 2023 |
| ROSE | AH-Software Co. Ltd. Bushiroad Inc. |
Japanese | Feminine | Aina Aiba | December 21, 2023 |
| OSCAR | E-CAPSULE Co. Ltd. VOICEMITH |
Mandarin Chinese | Masculine | Myles | December 26, 2023 |
| Yi Xi | Dreamtonics Co., Ltd. | Mandarin Chinese | Feminine | Unrevealed | March 15, 2024 |
| Frimomen | AH-Software Co. Ltd. | Japanese | Masculine | Koga Akira | April 25, 2024 |
| ROSA | ZAN-SHIN Co., Ltd. AH-Software Co. Ltd. Internet Co., Ltd. |
Japanese | Feminine | Shirayuki | June 3, 2024 |
| Ling Wan | Dreamtonics Co., Ltd. | Cantonese Chinese | Feminine | Unrevealed | July 19, 2024 |
| NOA Hex | AUDIOLOGIE Co., Ltd. | English | Masculine | Ashe | September 7, 2024 |
| Miyamai Moca | AH-Software Co. Ltd. | Japanese | Feminine | Mayu Mineda | September 26, 2024 |
| NYL | Eclipsed Sounds, LLC | English | Feminine | Zay Driver | October 11, 2024 |
Synthesizer V AI Lite[]
This is a list compiling the AI voice databases available for Lite.
Synthesizer V AI Feature-Limited Trials[]
This is a list compiling the AI voice databases available for Feature-Limited Trials.
| Product | Developer | Language | Voice Type | Sample | Release |
|---|---|---|---|---|---|
| Ritchy | Dreamtonics Co., Ltd. | English | Masculine | MBanja Ritchy | July 4, 2023 |
| D-Lin | Dreamtonics Co., Ltd. | Mandarin Chinese[3] | Masculine | Unrevealed | July 4, 2023 |
| Eri | Dreamtonics Co., Ltd. | Japanese | Feminine | Unrevealed | October 26, 2023 |
Current Developments[]
Announced Vocals[]
These are Synthesizer V voice databases known to be in production. Their status and licensing are unknown, but most are presumed to have commercial licenses.
| Image | Product | Developer |
|---|---|---|
 |
Topaz | Studio ENTRE Inc. & GONZO K.K. |
|
On August 5, 2024, a collaboration project between two companies, Studio ENTRE Inc. (a company with the goal of creating new businesses by combining the broad entertainment business with technology)[6] and the Japanese animation studio GONZO K.K., announced the formation of a new A.I. singer label, "GEMVOX". GEMVOX was announced to be a next generation label that includes A.I. singers, all named after gemstones, developed using the latest voice synthesizer technology aimed with the goal of having new works created daily by various creators and to provide a series of captivating "AI Singers" that inspire creators' imagination, curate the works produced, and encourage collaboration among creators. The project was launched together with Shinichiro Ishikawa, president of GONZO, who continues to pioneer the use of technology in the anime industry, while also taking advantage of the activities of the AI research group "ARS"（AI Resonate Society). The first announced vocalist of the company was Shimon Topaz, a mysterious girl with a dark appearance who has a beautiful and clear voice and is trilingual, fluent in Japanese, English, and Korean. At the time, it was not specified which synthesizer Topaz would be developed for. Topaz was also announced to be featured as the main vocalist for the theme song for the upcoming anime PV, "Gloria".[7][8][9][10] On August 21, the president of Studio ENTRE inc., Norikazu Yamaguchi (山口哲一), followed up on a blog detailing further details of Topaz's development, confirming she would be launching on September 25 and would be sold as a singing voice database for Synthesizer V Studio. The technology was not only to be linked to Dreamtonics, but would also be collaborating with Techno-Speech, Inc. and Yamaha Corporation, intent to create AI singers from various platforms and are preparing various projects.[11] On September 22, an interview was held by SynthV News (an unofficial Synthesizer V news blog) with Norikazu Yamaguchi, who elaborated further on the project providing additional details on Topaz and the GEMVOX project. Yamaguchi noted the origin of the project was based on thought process that "the time had come for the world of VOCALOID producers, which had been dominated by amateurs, to expand to include top-class professional musicians, as the threshold for singing voice generation AI was exceeded." He noted that GEMVOX is a "dream team" made up of three industry veterans: "a music business person, and a music creative person, as well as an anime producer." The goal of GEMVOX was noted to contribute to the development of the creator economy. It was noted that Yamaguchi first met Kanru Hua when he came to Japan as a university student to take part in a music hackathon organized by Yusuke Asada (浅田祐介) and himself. Becoming friends of Kanru Hua and being an avid supporter of Synthesizer V sparked the creation of Topaz, the companies' first Synthesizer V project.[12][13] Amid concerns regarding Studio ENTRE's production of NFT projects, such as the "SAMURAI Cryptos" music NFT project, Yamaguchi noted that GEMVOX and Topaz are not associated with NFT technology.[14] Yamaguchi noted on his personal Twitter account that Topaz was expected to be released on October 16, in addition to publishing voice demos and tutorial videos before launch.[15] Despite the announcement of Korean, it was stated also by Yamaguchi that Topaz's launch would only include Japanese and English as a bilingual vocalist, though Korean support was announced to be added at a future date.[16] | ||
 |
KAFU | KAMITSUBAKI STUDIO & AH-Software Co. Ltd. |
|
On July 7, 2023, at the end of the "V.I.P -Virtual Isotope Phenomenon- 1st" livestream, it was announced that KAFU would be in development for Synthesizer V AI and was expected to release in Winter 2023.[17][18] She was confirmed to be developed by AH-Software Co. Ltd., though would be published by KAMITSUBAKI STUDIO.[19] Pre-orders for KAFU's physical copy and starter pack were opened on September 4 and would run until November 27 at 12:00 JST or if the available stock had sold out as she is a made-to-order product. Her release date was confirmed to be January 15, 2024.[20] On December 23, KAMITSUBAKI announced that her release date was being postponed due to various unspecified circumstances, with new release date being yet undetermined but to be announced as soon as details are decided.[21] | ||
 |
Upcoming AI voice database(s) | Eclipsed Sounds, LLC |
|
On November 24, 2023, Eclipsed Sounds launched a Spanish implementation survey for users of SAROS to submit feedback regarding pronunciation and desired accents.[22] The feedback would be used to improve Spanish synthesis before additional Spanish vocals were added to Synthesizer V Studio, including a native Spanish vocal planned by ES that was said to be announced later in 2024.[23] On March 22, 2024, Eclipsed Sounds redesigned its website. A new "upcoming genre-focused vocal line" provisionally dubbed "Eclipsed Sounds Phase 2" was added to the bottom of the homepage; while the Starry Court (SOLARIA, ASTERIAN, SAROS, and a then-unnamed Alto vocal that months later would adopt the name NYL) was described as a "lineup of genre-flexible vocalists", Phase 2 was said to "provide voices designed to suit single genres, with a lineup based on our current backlog of user requests", with no further information about any specific vocal to be grouped there.[24] | ||
  |
SAROS Lite | Eclipsed Sounds, LLC |
|
On December 14, when asked by an anonymous user regarding SAROS's license mentioning a Lite version, Eclipsed Sounds responded that, like SOLARIA and ASTERIAN before, SAROS will have a Lite voice database sometime after their next project in 2024.[25] | ||
  |
miki | AH-Software Co. Ltd. |
|
On December 1, 2023's AH-Software livestream, it was announced that both miki and Hiyama Kiyoteru (two of the company's three debut vocals for VOCALOID in December 2009) would be receiving AI voice databases for Synthesizer V Studio for their joint 15th anniversary in 2024.[26] | ||
| |
Hiyama Kiyoteru | AH-Software Co. Ltd. |
|
On December 1, 2023's AH-Software livestream, it was announced that both miki and Hiyama Kiyoteru would be receiving AI voice databases for Synthesizer V Studio for their joint 15th anniversary in 2024.[26] With regards to Kaai Yuki (AHS's third debut VOCALOID), it was noted that it would be very difficult to record a new voice library for her (due to the fact that her original voice provider, who back then in 2009 was a child and as of today still remains unrevealed for legal reasons, is now an adult and her voice quality has changed), and as for using her existing VOCALOID4 voicebank to derive a new voice database (whether it would be a new Standard voice database based on her existing raw samples or a Synthesizer V Plus-style AI voice database trained from songs performed by her V4 Natural voicebank was not mentioned, though), they would still have to first consult with Yamaha Corporation before carrying it out.[27] | ||
 |
Chiyu AI | Beijing Photek S&T Development Co., Ltd. |
|
On March 11, 2023, in response to some fans' questions regarding the production of AI voice databases, Ddickky said that the other "AI" voice databases were promoted with Xingchen Infinity and that the voice providers were invited at the same time in the prior year. He said that he had no issue with the funding, but that some of the voice providers were concerned that the AI would be "stealing their jobs" while some were procrastinating with the work until recently. There was also a concern that the databases would not sound like the previous R1 and R2 "Standard" versions. The commercialization would be determined after the production was completed, but it was expected to be handled similarly to Xingchen Infinity and would be sold directly since the technical workload and input cost were completely different. If there were no issues or delays, Chiyu and Minus were expected for 2023.[28][29][30] Minus AI, who was formally given the name "Yongye Minus", released on December 17; no further word on Chiyu AI was heard from since her announcement in March. | ||
  |
PASTEL | Bushiroad Inc. |
|
On December 31, 2023, the official Twitter account of the Yumenokessho project tweeted end-of-year greetings, thanking fans for their support for the project. They announced that in 2024, a new character would join the project, and further announcements would be made "around the time when the spring cold eases and the buds begin to bloom".[31] The tweet was met with widespread excitement from fans, sparking speculations about which BanG Dream! character would receive a voice database and which synthesis engine would be used. In an interview published by Sound & Recording magazine, when asked about future release plans, Yumenokessho project producer Tsuho Kusumi revealed, "The next two release characters have been decided. We will be able to release information around spring, so please look forward to it!".[32] On April 25, 2024, during a live announcement called Girls Band Party! Station, the silhouettes of PASTEL and HALO were shown, before showcasing their full renders and their reference sheets, announcing both of the characters for the Synthesizer V AI engine.[33][34] However, no release date for either of them was given yet, though PASTEL would be voiced by Ami Maeshima. | ||
  |
HALO | Bushiroad Inc. |
|
On December 31, 2023, the official Twitter account of the Yumenokessho project tweeted end-of-year greetings, thanking fans for their support for the project. They announced that in 2024, a new character would join the project, and further announcements would be made "around the time when the spring cold eases and the buds begin to bloom".[31] The tweet was met with widespread excitement from fans, sparking speculations about which BanG Dream! character would receive a voice database and which synthesis engine would be used. In an interview published by Sound & Recording magazine, when asked about future release plans, Yumenokessho project producer Tsuho Kusumi revealed, "The next two release characters have been decided. We will be able to release information around spring, so please look forward to it!".[32] On April 25, 2024, during a live announcement called Girls Band Party! Station, the silhouettes of PASTEL and HALO were shown, before showcasing their full renders and their reference sheets, announcing both of the characters for the Synthesizer V AI engine.[33][34] However, no release date for either of them was given yet, though HALO would be voiced by Miku Itou. | ||
Restricted access[]
These are vocals that producers have or currently have limited access to.
Private Vocals[]
There are some Synthesizer V voice databases that are privately owned by (and exclusively used by) certain companies for certain projects, with no intention of releasing them commercially (even if complete enough to be considered to be finished products).
| Image | Product | Developer |
|---|---|---|
  |
Shirakami Meito | En-gene (TMIK Co., Ltd. & agehasprings Holdings Corp.) |
|
Shirakami Meito debuted as a virtual utaite (or VSinger)[35] under the En-gene label (a joint venture co-owned by TMIK Co., Ltd. and agehasprings Party) on March 22, 2024.[36] Kazunari Shirane, from agehasprings Party, was credited for "vocal programming" on all of her song uploads, thus hinting at her voice being based on a vocal-synthesis engine that would eventually be revealed to be Synthesizer V in the coming days (at least on YouTube and very deep into its video descriptions, as the songs were not yet being tagged as such on bilibili, TikTok, or Twitter until much later). Neither Dreamtonics Co., Ltd. nor any other then-known vocal-synthesizer company was known to have retweeted, shared, or commented on her content, thus contributing to keeping her out of the vocal-synth community's radar. On April 20, Meito started to sign bilibili-centric tweets with the phrase "M-type" (M型);[37][38] it was unknown what was being meant with that. Later on April 21, she tweeted about Chinese language being installed into her system, again ending the tweet with "M-type",[39] which may have implied that M-type was a new voice-database version trained with Mandarin-Chinese song material that would use Cross-lingual Singing Synthesis to sing in that new language. On April 23, her first Mandarin song cover was demonstrated using this updated library.[40] On May 31, it was announced on a press release by En-gene that Shirakami Meito had recorded a new jingle for Japanese radio station FM802, which was celebrating its 35th anniversary. The jingle was a joint composition between Kazuma Nagasawa (a songwriter from agehasprings) and AI music-track generation software FIMMIGRM (a product of TMIK Co., Ltd.), with arrangement by Shogo Ohnishi (also from agehasprings); on this press release, En-gene confirmed that Meito's voice was based on an original Synthesizer V voice database. The jingle was set to premiere via broadcast on June 1.[41] On June 6, the western vocal-synth community started to take notice of her existence as a private Synthesizer V vocal.[42][43][44] | ||
Retired Vocals[]
There are some Synthesizer V voice databases that were available commercially that have now been removed from sale or will be removed from sale in the near future. Vocals that have seen retirement may continue to be sold for some time after their initial retirement; however, they are on limited supply and will sell only while the stock lasts. Their usage is limited to those who are able to access these vocals before or since their retirement, as no new stock has been released containing their vocals.
Please note that when a new version of the engine is released, there is a risk of support for older versions being removed. They may or may not be removed from sale.
| Product(s) | Developer |
|---|---|
| ANRI | AUDIOLOGIE Co., Ltd. |
| ANRI's debut Synthesizer V Studio voice database was officially delisted from the AUDIOLOGIE store as of December 5, 2023, marking her official discontinuation, in preparation for the release of ANRI Arcane and leaving only the Lite edition of ANRI available for digital download. It was noted that customers who purchased ANRI's debut voice database before December 5, 2023 will have until June 11, 2024 to redeem their code to receive a free digital download code of ANRI Arcane.[45] A consideration to release ANRI's debut voice database alongside ANRI Arcane as a special collector's edition bundle is currently in consideration for the future provided that there is enough user interest.[46] | |
Beta/Prototype voice databases[]
These vocals exist but are only prototypes and may not become commercial products.
| Product | Developer |
|---|---|
| JA-F1 | Dreamtonics Co., Ltd. |
| JA-F1 is a work-in-progress feminine Japanese voice database created for internal use by Dreamtonics when developing Synthesizer V. There are currently no plans to release the voice database. | |
| MAN-M1 | Dreamtonics Co., Ltd. |
| MAN-M1 is an unreleased masculine Chinese voice database developed for internal use by Dreamtonics when developing Synthesizer V. There are currently no plans to release the voice database. | |
| MAN-F1 | Dreamtonics Co., Ltd. |
| MAN-F1 is a work-in-progress feminine Chinese voice database developed for internal use by Dreamtonics when developing Synthesizer V. There are currently no plans to release the voice database. The latest mention of MAN-F1 was during Qing Su's (MAN-F3) livestream, where it was asked if the pair shared a voice provider. Dreamtonics confirmed that they did not. It was restated that MAN-F1 (and similar voice databases) were used for internal alpha and beta tests. These types of voice databases would only see comercialization if the quality was considered satisfactory.[47] | |
| SOLARIA Standard | Eclipsed Sounds, LLC |
| On May 10, 2021, Eclipsed Sounds officially revealed a small sample of SOLARIA (previously known as "SOLARIS").[48] According to the company, the demo used a test library based on the standard recording method and was created with a very limited recording list, meaning that it would only give listeners an idea of what the vocal would be like.[49] A crowdfunding campaign for the production of a Synthesizer V AI voice database was confirmed to begin on May 14.[50] Depending on how her crowdfunding campaign proceeded, a standard voice database could be a possible option for a stretch goal depending on the demand. This was later restated to be based on high demand in the future.[51] Otherwise, there was no intention to release this voice database.[52] | |
| Cangqiong SV Plus, Muxin SV Plus, Chiyu SV Plus, Shian SV Plus, Haiyi SV Plus, Minus SV Plus | Beijing Photek S&T Development Co., Ltd. |
|
On December 23, 2021, it was announced that Chiyu, Shian, Cangqiong, Haiyi, Muxin, and Minus were expected to be upgraded with AI voice databases and would be able to support Synthesizer V Studio 1.5.0's Cross-lingual Synthesis capabilities. It was clarified that the AI versions were trained by the Standard voice databases, and were not meant to be replacements for Standard nor would the update be available directly via the editor. As a separate type of voice database, the new libraries would need to be repacked in new installation packages, which required separate activation codes. The upgrades would be distributed to existing users for free and prices would be raised for new buyers soon due to the new inclusions.[53] They were originally slated for release that day, however, Beijing Photek decided to delay them due to a lack of confidence about their performance as rushed products. A limited beta-testing would run first. The voice databases would release after their performances were proven satisfactory. By then, Quadimension hoped to find an efficient way to distribute the AI activation codes.[54] According to Creuzer, one of the beta testers, Cangqiong AI was the only beta voice database out of the six that was available at the time. Haiyi AI's beta was expected to be on the way.[55] On December 30, the voice databases were officially called "Synthesizer V Plus".[56] Throughout 2022, Cangqiong Synthesizer V Plus and Muxin Synthesizer V Plus received multiple examples demonstrating their capabilities as Standard-trained AI voice databases, including the Cross-lingual Singing Synthesis function. However, news about the development and future releases in general for all six characters were not available. On September 29, in response to a fan's question about whether the Plus versions of the six voice databases would be released soon, Quadimension wrote that it was probably not likely due to the qualities being unfit for commercial use.[57] On November 22, in response to a fan, Ddickky confirmed that the Plus series of voice databases were created with the intention of demonstrating the effects of training AI with Standard voice databases and were not meant to be released. The voice databases were sent to shareholders as a technology demonstration and not as a full product update. As these voice databases were to show the effects and technology of splicing AI training, they could not be noted as "Synthesizer V AI" as they would affect the brand quality of AI voice databases, thus the need of calling these "Synthesizer V Plus".[58][59] | |
Rumour mill[]
These vocals are rumoured or hinted to be released but their status has not been made official.
Possible future voice databases[]
This section contains hints, confirmations and suggestions put out by Synthesizer V studios.
| Product | Developer |
|---|---|
| Yamine Renri Chinese | VOLOR & Yuzuri |
|
VOLOR confirmed through email that Yamine Renri's update was postponed due to the COVID-19 pandemic, but they confirmed that they were thinking about giving her a Chinese voice database due to her voice provider studying it.[60] News about this potential voice database is currently unknown. | |
| CUL, REV, WhiteCUL, and other concepts | ZAN-SHIN Co., Ltd. |
|
Throughout 2020, HirotoP had been composing tweets in regards to CUL and the many parts of her project. He revealed that REV was meant to become a VOCALOID, but his project fell through, and later revealed that CUL had conceptual sisters themed around the following colors: blue, white, yellow, and red. It was also confirmed that she had a twin sister known as "Black CUL" (Wet Crow). In response to a fan, HirotoP also expressed interest in updating CUL but did not give further details.[61] It was confirmed that after ROSA is released, an official livestream would be launched for announcements.[62] Depending on if ROSA sells well, REV may also be considered for development.[63] REV later released as a DeepVocal voicebank on May 24, 2021, with HirotoP voicing him. He is being considered for a commercial voicebank depending on his popularity, and should it happen, a proper voice actor or singer would be assigned to him.[64] On June 3, 2022, ROSA tweeted that she and WhiteCUL would be performing at the 柚子花主催LIVE -Planet Station- STAGE.3 online concert on June 19, however, WhiteCUL's character design would not be shown.[65][66][67] On the day of the concert, it was later clarified that the singing voices for ROSA and WhiteCUL were performed by their voice providers rather than using singing voice synthesizers. HirotoP hoped that the performances would give listeners an idea of what an AI singing voice database would sound like. It was then unknown if WhiteCUL would be receiving a singing voicebank as, at the time, only ROSA was confirmed to be receiving a Synthesizer V AI voice database.[68] On July 25, 2023, HirotoP tweeted information regarding CUL and her future developments noting that she would be renewed at a later point in time. She was announced to be receiving a new design and would likely be referred to as RE:CUL or REDCUL, however the project would be a long ways off. As CUL's voice was provided by famous voice actress Eri Kitamura, HirotoP noted that it would be difficult to ask her to return as CUL's voice provider due to her busy schedule. As a result he made a suggestion of holding an audition to seek out a new fitting provider for CUL's new image. It was noted that the production of CUL would not begin until after ROSA and WhiteCUL's productions have completed.[69] Following the announcement of ROSA's Synthesizer V crowdfunding campaign to begin in mid-November (later postponed to at least two months later), the official CUL Twitter account excitedly asked fans to support ROSA while also stating that after ROSA and WhiteCUL's developments, that it would be her turn next, hinting at the possibility of CUL being in consideration for a voice database, depending on how successful ROSA and WhiteCUL perform.[70] On May 20, 2024, WhiteCUL announced a crowdfunding campaign for an AI singing voicebank for VOCALOID6,[71] which started on May 24.[72] When asked earlier about whether she would be too made for Synthesizer V AI, WhiteCUL limited her response to just saying that, if this crowdfund were highly successful, then ZAN-SHIN would hopefully be able to develop various software products, including for Synthesizer V.[73] | |
| Quaid | Beijing Photek S&T Development Co., Ltd. |
|
On May 27, 2021, Ddickky gave on Bilibili an explanation for the origin of the name Quaid (奎德) as applied to the upcoming MEDIUM⁵ 2050 game's big villain boss: originally, after considering Quadimension's full English name to be too long (due to the English part being "not conducive to dissemination"), he wanted to enable "Quad" both as an abbreviation for Quadimension and as the name of the game's protagonist, but then feeling that the Chinese transliteration of "Quaid" at that time "didn't sound like a good guy's name", he chose to reuse it instead for the villain.[74] Later on October 2, Ryan, one of Quadimension's tuners,[75] published on Bilibili a status where he mused about national holidays being good days for working on tunings while also complaining about having a "queue of hobby to-dos" before him after finishing business tunings: "I used to be a person who would want to learn to sing whenever I heard a song I liked, but now when I listen to it, I only think about who" (the vocal) "would be more suitable for tuning it. As a result, there's always new to-dos entering my desk, (and thus) I can never get finished with my backlogs."[76] There, he attached an almost-completely-censored screenshot of some lengthy memo of "candid songs", with its title and headings being the only readable lines there: the bottom-most headings were the names of all Quadimension vocals (including Xingchen), Eleanor Forte, and an "English Male" (Dreamtonics' then-unnamed vocal who would later become Kevin), but also the name Quaid was inserted between Minus (given there as 减减, Jiǎnjiǎn) and Muxin, leading some Weibo user one day later to speculate whether there was more information or updates on Quaid (as a potential voice), "otherwise how can Ryan judge whether Quaid is suitable for singing?"[77] There is, however, no explicit mention of any (private or beta) voice library for Quaid, nor any mention of a vocal-synth engine for it. | |
| JOAN & ZETA | E-CAPSULE Co. Ltd. & VOICEMITH |
|
On May 31, 2022, after XIA YU YAO's AI voice library production crowdfund launched, a fan asked if there would be AI voice libraries for the other VOICEMITH voice synthesizer characters: OSCAR, JOAN, and ZETA. The company replied "Possibly but not this year".[78] Some time after the release of YU YAO's Synthesizer V AI library in January 2023, VOICEMITH's website was modified to no longer include the other voice synthesizer characters. There was no announcement regarding the change to the website nor was a reason provided.[79] In April, OSCAR was confirmed to be planned for Synthesizer V AI;[80] after a successful crowdfund, he was released on December 26.[81] On March 5, 2024 (VOICEMITH's 10th anniversary), Juxer's Twitter account announced VOICEMITH's incursion into ACE Studio with a poster titled "Original Classic" showing six characters: YU YAO, OSCAR, JOAN, ZETA, and two then-unknown characters.[82] | |
| Shian AI, Cangqiong AI, Haiyi AI, & Muxin AI | Beijing Photek S&T Development Co., Ltd. |
|
On March 11, 2023, in response to some fans' questions regarding the production of AI voice databases, Ddickky said that the other "AI" voice databases were promoted with Xingchen Infinity and that the voice providers were invited at the same time in the prior year. He said that he had no issue with the funding, but that some of the voice providers were concerned that the AI would be "stealing their jobs" while some were procrastinating with the work until recently. There was also a concern that the databases would not sound like the previous R1 and R2 "Standard" versions. The commercialization would be determined after the production was completed, but it was expected to be handled similarly to Xingchen Infinity and would be sold directly since the technical workload and input cost were completely different. If there were no issues or delays, Chiyu and Minus were expected for 2023, though the other vocalists have not been mentioned.[28][29][30] | |
| Momoka Akino | TOKYO6 ENTERTAINMENT |
|
On April 19, 2022, TOKYO6 ENTERTAINMENT introduced a fourth character known as Momoka Akino (百花秋乃), who was Natsuki Karin's senior and was themed around the autumn season.[83] She made her debut in Karin's audio drama and was voiced by Nene Hieda, who won the Rookie of the Year award at the Voice Actor Awards in 2022, prompting the company to contact her.[84] There was an offer with an idea of making a voice synthesized character in the future, however, TOKYO6 ENTERTAINMENT wanted to think further about the development of the three existing cast members (Koharu Rikka, Natsuki Karin, and Hanakuma Chifuyu) at the moment, thus putting the idea aside.[85] | |
Awaiting further confirmation[]
The following are possible upcoming voicebanks whose statuses are not yet clarified, or they are vocal developments that were announced but have not had any updates about their statuses within the last six months.
| Product | Developer |
|---|---|
| ZERO | Beijing Photek S&T Development Co., Ltd. |
|
On March 28, 2019, Ddickky posted on Weibo that two Xingchen voice databases were being planned for Synthesizer V. These voice databases were labelled as "Xingchen/ZERO English" and "Xingchen/ZERO Chinese", as the character would be determined based on the differences between the new voice databases and Xingchen's original VOCALOID voicebank. If the differences were too great, the voice databases would be known as ZERO rather than Xingchen.[86] On August 25, 2021, Xingchen Infinity was announced to be in production for Synthesizer V AI, though information about ZERO was not mentioned. Due to Xingchen's production launch for Synthesizer V, it may be possible that ZERO may not receive a voice database for the software. | |
| Eleanor Forte Standard | VOLOR |
|
Eleanor was confirmed to be updating to Synthesizer V Studio. While a Lite version was released on July 30, 2020, a full release was not yet made available. On October 30, 2020, in response to a fan's tweet regarding the update, VOLOR stated there would be a compromise of the schedule due to attempting to fully utilize the cutting edge technology for Synthesizer V.[87] On May 11, 2021, VOLOR noted that plans were set back due to the COVID-19 pandemic. They also noted that there was an interest in making an AI edition for Eleanor, but noted that she may sound very different compared to her original Synthesizer V release, while a Standard voice database would sound more faithful. Though a full Standard voice database is still being planned, it may take years to develop.[88] Eleanor's AI voice database was eventually released several months later on December 6, 2021. However, there have been no Standard voice databases released for the last two years as of April 2024, since Kyomachi Seika. | |
| GENBU AI | VirVox Project & VOLOR |
|
On August 1, 2021, VirVox Project announced that a crowdfund campaign for GENBU's AI voice database would be launched in Mid-August.[89] Due to discrepancies, the crowdfund for his AI voice database was canceled.[90] Continued production of GENBU's AI voice database is unknown. On December 24, 2022, VirVox Project confirmed that they were not giving up on creating AI singing voice databases. The goal for 2023 was to implement AI singing voice synthesis, but it was noted that this was premature and that the production process may have obstacles. Specific characters and voice synthesis engine were not specified at the time.[91] | |
| Male Cantonese AI voice database | Dreamtonics Co., Ltd. |
|
On February 27, 2023, Dreamtonics posted a poem on bilibili along with an announcement that new songs and other news were expected for February 28 at 17:00 GMT+8.[92][93] Details were not specified but the first part of the poem seemed to describe the beauty of song and pronunciation in music across any language.[94][95] The second part described the role of melodies and pitches in music, emphasizing the importance of rhythm.[96][97] On February 28, a technical demo announcing the future support for the Cantonese dialect and rap was uploaded, showing a new male AI voice database singing in the new supported language respectively. The new male vocal was confirmed to be entirely trained on Cantonese songs and was noted to be the first Cantonese voice library in the history of commercial singing voice synthesis software.[98] On March 15, after receiving feedback in improving the song to be more in line with Cantonese songwriting habits, Dreamtonics replaced the bilibili version of the debut video, which implemented corrections made to the male vocal's and Feng Yi's demos.[99][100] On September 26, Dreamtonics announced that they would be showcasing a "soon-to-be-released" dedicated Cantonese Chinese AI voice database (who on a later date was named Wei Shu) at the Music China event in Shanghai, which ran from October 11 to 14. This vocal was noted to have outstanding mixed Mandarin and Cantonese singing with proficient and smooth Cross-lingual Singing Synthesis across the four available languages for Synthesizer V Studio.[101] It is currently unknown if this voice database was the same one shown in February or if it's a new vocalist. | |
Unreleased or assumed cancelled[]
This section contains unreleased voice databases that are likely or assumed to be cancelled in the absence of further information.
| Product | Developer |
|---|---|
| Xingchen English | Beijing Photek S&T Development Co., Ltd. |
|
On March 28, 2019, Ddickky posted on weibo that two Xingchen voice databases were being planned for Synthesizer V. These voice databases were labelled as "Xingchen/ZERO English" and "Xingchen/ZERO Chinese", as the character would be determined based on the differences between the new voice databases and Xingchen's original VOCALOID voicebank. If the differences were too great, the voice databases would be known as ZERO rather than Xingchen.[86] Xingchen Infinity was later announced on August 25, 2021. This was planned to be a Synthesizer V AI voice database. It is currently unknown if the English voice database would still be produced, especially since Cross-lingual Singing Synthesis (introduced since Synthesizer V Studio Pro 1.5.0) allows AI voice databases to sing in all officially-supported languages regardless of the language the singing data that the voice database was originally recorded in. In addition, Xingchen Infinity had additional Japanese and English recordings to enhance her capabilities in those languages through the function. | |
| XIA YU YAO Lite | E-CAPSULE Co. Ltd. & VOICEMITH |
|
On August 24, 2022, VOICEMITH officially announced XIA YU YAO to be in production for Synthesizer V AI. Her full version was released on January 30, 2023 as physical and digital copies. A Lite version was planned to be in production.[102] In response to a fan on February 23, 2023. VOICEMITH stated that the Lite version of XIA YU YAO would not be released. No additional information was provided.[103] | |
No longer in consideration[]
The following are vocal developments that were once considered (or rumored to be considered, based on hints and suggestions) for Synthesizer V but were later dismissed in favor of other vocal synthesizer engines.
| Product | Developer |
|---|---|
| Shiki Rowen | MUGEN Co., Ltd. |
|
On May 17, 2021, Yuuma, a Japanese Virtual YouTuber, tweeted that Kemonone Row and Shiki Taigen were expected to have commercial voicebanks developed on a software that would support English input. It was noted that the English voicebanks would be based on Japanese pronunciation.[104] The platform was not confirmed at the time.[105] In regards to Row's name, Yuuma noted that he wasn't sure which would be better for a person's name as he didn't know enough English to make a decision, leaving this to fans to give suggestions.[106] This later led to Yuuma tweeting that the name would be changed to "Rowen Shiki", Row's real name, after the development of a commercial voicebank was decided. It would serve to unify with the family name "Shiki", which was the same as Shiki Taigen, Row's great-grandfather.[107] Later on July 5, Yuuma expressed interest in creating a Synthesizer V AI database for Rowen, though a crowdfund would be necessary to produce it.[108] He later asked overseas fans on July 7 if Rowen's voicebank should be on Synthesizer V, and if so, a Standard voice database was considered due to budget.[109] Synthesizer V was not a final decision, but it was confirmed to still be a consideration. A decision on crowdfunding would be dependent on support and encouragement from fans.[110] The estimated budget would be based on previous successful Synthesizer V crowdfunds.[111] On July 26, 2022, Yuuma announced that Shiki Rowen was now being recorded for an AI singing voicebank[112] which would be first released for free on the NNSVS engine.[113] In response to inquiries by fans, he said that Synthesizer V was no longer in consideration[114][115] but that other commercial platforms were being considered;[116] budgetary reasons (allocating everything for A.I.VOICE and blanking out AI singing synthesis) were cited for the dismissal of Synthesizer V as a platform for Rowen.[117][118] Instead, Rowen was later developed for the VOCALOID6 engine[119][120] and released by Yamaha Corporation on April 24, 2024.[121][122] | |
References[]
- ↑ https://t.bilibili.com/619866988878952464 - Despite confirmations that Xingchen Infinity was also trained with English and Japanese songs, she is not considered to be a multilingual library by Beijing Photek S&T Development Co., Ltd.
- ↑ https://store.dreamtonics.com/product/weina-voice-database/ - Weina is marketed by Dreamtonics as both a Mandarin Chinese and English voice database, with confirmation that she was trained with Mandarin and English songs. However, Mandarin is set as her default language, thus making it the only option available on the Synthesizer V Studio Basic editor.
- ↑ 3.0 3.1 https://store.dreamtonics.com/product/d-lin-voice-database/ - Despite confirmations that D-Lin was also trained with English samples, he is not considered to be a multilingual library by Dreamtonics Co., Ltd.
- ↑ https://store.dreamtonics.com/product/sheena-voice-database/ - Sheena is marketed by Dreamtonics as both a Japanese and English voice database, with confirmation that she was trained with Japanese and English songs. However, Japanese is set as her default language, thus making it the only option available on the Synthesizer V Studio Basic editor.
- ↑ https://i.imgur.com/CpYg6xx.png - Screenshot from Taylor Hennessy, also known as celestrai "celest", regarding the description of SAROS' vocal.
- ↑ https://entre.studio/about
- ↑ https://gemvox.ai/posts/opening
- ↑ https://prtimes.jp/main/html/rd/p/000000047.000062348.html
- ↑ https://japan.cnet.com/release/31011412/
- ↑ https://gemvox.ai/topaz
- ↑ https://note.com/yamabug/n/nd0e6ddda0672
- ↑ https://note.com/synthv_news/n/n8411b5cb6cd2
- ↑ https://x.com/synthvnews/status/1838020631201304642
- ↑ https://x.com/yamabug/status/1838096918498738534
- ↑ https://x.com/yamabug/status/1838385054600614130
- ↑ https://x.com/yamabug/status/1838032350707667183
- ↑ https://www.youtube.com/watch?v=y1nyhLn2QdY
- ↑ https://x.com/musicalisotope/status/1677284636215623681
- ↑ https://x.com/ahsoft/status/1678238243253551105
- ↑ https://x.com/musicalisotope/status/1698623590655201624
- ↑ https://x.com/musicalisotope/status/1738363800066355499
- ↑ https://x.com/eclipsedsounds/status/1727982516026442208
- ↑ https://x.com/eclipsedsounds/status/1728047093388869817
- ↑ https://x.com/PositiveVSynth/status/1771272015686623686
- ↑ https://www.tumblr.com/eclipsedsounds/736722574474657792/i-was-reading-about-saros-license-and-i-saw-that
- ↑ 26.0 26.1 https://x.com/ahsoft/status/1730572443927167143
- ↑ https://x.com/vocaspherenews/status/1730573495829152247
- ↑ 28.0 28.1 https://t.bilibili.com/771690836003913744
- ↑ 29.0 29.1 https://cdn.discordapp.com/attachments/695380056155095054/1084001776069525515/Screenshot_2023-03-11-14-25-20-306_com.png?ex=665d6453&is=665c12d3&hm=c1e4d326d2715400921ae53eff5d1f716da9bece50249cab48031c6e4dcfd80b& - "ai声库是和星尘ai一起推进的，去年就同时邀约了生源，这点资金我也完全没问题。只是有些声源会担心ai抢饭碗，有些声源单纯有点拖…而对我而言，商业策略角度现在出声库并不是很好的时机，所以我也只能做到过俩月去催一下，不至于急道周周催天天问。于是结果如你所见，但不出意外不是过于拖的话，今年minus和赤羽应该可以吧。" "不过另一点是，不光声源觉得ai和自己太像，我也觉得如果这么像声源而非角色之前的声库。不是很合适。星尘一定要做是因为v4性能过于差，所以硬顶着声音变化的反对也做了。而其他几个角色是sv2带拼接式，性能过得去，那做了ai产生与星尘类似的声音变化风波，在外加商业角度（卖声库）不是那么挣钱，你能理解我逻辑了吧。"
- ↑ 30.0 30.1 https://cdn.discordapp.com/attachments/695380056155095054/1084001780926525450/Screenshot_2023-03-11-14-25-45-806_com.png?ex=665d6454&is=665c12d4&hm=b3099795dd35246207093f0191c4aec662eccc950dc5655d74a8d68877ce617a& - "回复 @覆雪繁花 :这个还是等快出了看情况才能定，不过基本应该是类似星尘ai的直接卖新的，因为和之前拼接式完全是不同技术工作量和投入成本上也完全不相干，所以会是大几百重新卖，这也是我觉得不好卖商业上不太合适出的一个原因"
- ↑ 31.0 31.1 https://x.com/yumenokessho/status/1741398848306893120
- ↑ 32.0 32.1 https://www.snrec.jp/entry/PR/special/yumenokessho_intro
- ↑ 33.0 33.1 https://www.youtube.com/watch?v=vJHtSsAO0PI
- ↑ 34.0 34.1 https://x.com/yumenokessho/status/1783491469208383869
- ↑ Not to be confused with Shanghai HENIAN Information Technology Co. Ltd.'s Vsinger series of VOCALOID voicebanks.
- ↑ https://x.com/shirakamimeito/status/1771024002582208621
- ↑ https://x.com/shirakamimeito/status/1781654865040781700
- ↑ https://x.com/shirakamimeito/status/1782004034788057450
- ↑ https://x.com/shirakamimeito/status/1782035041591464057
- ↑ https://x.com/shirakamimeito/status/1782711010912252245
- ↑ https://engene.tmik.tokyo/posts/240531
- ↑ https://x.com/PositiveVSynth/status/1798773614357172533
- ↑ https://x.com/andresfelipeb25/status/1799132523483762760
- ↑ https://x.com/SynthVNews/status/1799140623410438223
- ↑ https://audiologie.us/blogs/news/anri-arcane-free-upgrade-campaign-information
- ↑ https://x.com/audiologie_en/status/1716080084690579585
- ↑ https://www.bilibili.com/video/BV11f4y1u7Sw
- ↑ https://x.com/eclipsedsounds/status/1391755378761900040
- ↑ https://x.com/eclipsedsounds/status/1391783842831343622
- ↑ https://eclipsedsounds.tumblr.com/post/650819684299685888/the-voice-provider-for-solaris-is-incredible-if
- ↑ https://eclipsedsounds.tumblr.com/post/660049293304119296/is-there-still-a-possibility-of-a-standard
- ↑ https://eclipsedsounds.tumblr.com/post/650818891907481600/will-solaris-be-both-an-ai-and-standard-synth-v
- ↑ https://t.bilibili.com/607304690576678463
- ↑ https://t.bilibili.com/607379895452471472
- ↑ https://x.com/Creuzer1/status/1474394755262201859
- ↑ https://t.bilibili.com/609647028303295976
- ↑ https://x.com/Imsupposed2/status/1586069151314870277
- ↑ https://www.bilibili.com/read/cv19899475
- ↑ https://cdn.discordapp.com/attachments/986786656084455434/1044406907152113664/image.png?ex=665db4fa&is=665c637a&hm=68a41a1e37b8de2826dd3e0a1d26a1297ce81b55d63faacf1dc64d8a030d9489& - Screenshot as of November 21, 2022
- ↑ https://vocaverse.network/threads/synthesizer-v-discussion-thread.202/page-25
- ↑ https://x.com/deecloud/status/1374892420937121793
- ↑ https://x.com/deecloud/status/1375846268044386304
- ↑ https://x.com/deecloud/status/1378370426783469575
- ↑ https://x.com/deecloud/status/1392880445344280579
- ↑ https://x.com/ROSA_ROSA_15/status/1532679142629834752
- ↑ https://x.com/deecloud/status/1533618023600635904
- ↑ https://x.com/CUL1224/status/1534119892915752961
- ↑ https://x.com/deecloud/status/1538484753372151810
- ↑ https://x.com/deecloud/status/1683647754122452993
- ↑ https://x.com/CUL1224/status/1716493362700996631
- ↑ https://x.com/whitecul_yuki/status/1792404895762624841
- ↑ https://x.com/Whitecul_yuki/status/1792404895762624841
- ↑ https://x.com/Whitecul_yuki/status/1792436016080617715
- ↑ https://h.bilibili.com/136375946
- ↑ https://t.bilibili.com/401052488345306866?tab=2
- ↑ https://h.bilibili.com/168854093
- ↑ https://weibo.com/7490323330/KAZIenlWt
- ↑ https://x.com/YuyaoOfficial/status/1531899506890969091
- ↑ https://cdn.discordapp.com/attachments/695380056943493280/1085810360520560732/image.png?ex=665e09f3&is=665cb873&hm=d2c4dd0f0f5c84098defed4d5862f967c80e1cdadebe8b21c53b8c1f01b5f3b3& - Screenshot of VOICEMITH's website as of March 15, 2022
- ↑ https://x.com/VM_OscarAI/status/1642527041382916098
- ↑ https://x.com/VM_OscarAI/status/1739538488805212185
- ↑ https://x.com/juxerofficial/status/1764833211698540886
- ↑ https://x.com/s_akasakov/status/1527328339945746433
- ↑ https://x.com/tokyo6info/status/1516604792701091841
- ↑ https://www.dtmstation.com/archives/60921.html
- ↑ 86.0 86.1 https://weibo.com/2182360953/Hn3f83q9L
- ↑ https://x.com/OfficialVolor/status/1322055460661309443
- ↑ https://x.com/OfficialVolor/status/1403668596316774401
- ↑ https://x.com/VirVox_pjt/status/1421485816942153745
- ↑ https://note.com/virvoxproject/n/n17f5051a2ea3
- ↑ https://x.com/VirVox_pjt/status/1606310684178149377
- ↑ https://t.bilibili.com/767295924844101665
- ↑ https://x.com/LenKiMo/status/1630132094893719552 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132100216287233 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132108072218624 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132104104415233 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132111452811264 - Translation by @LenKimo
- ↑ https://www.youtube.com/watch?v=mcJU0Wq-u7w
- ↑ http://www.bilibili.com/video/BV1zs4y1f7QJ - "Dreamtonics 已于 3 月 15 日将 Synthesizer V AI 粤语歌声合成技术预览的测试曲目更换为更加符合粤语歌曲创作习惯的版本，感谢各位创作者的关心与鞭策。未来 Dreamtonics 将陆续发布更多关于粤语歌声合成与跨语言合成的信息，敬请期待。"
- ↑ https://t.bilibili.com/773207552189005831
- ↑ https://t.bilibili.com/845594879243321396
- ↑ https://x.com/YuyaoOfficial/status/1571798117137395712
- ↑ https://x.com/shiweimigi/status/1760814253227851835
- ↑ https://x.com/Homurano_Yuma/status/1394160123866599426
- ↑ https://x.com/Homurano_Yuma/status/1394312575353950210
- ↑ https://x.com/Homurano_Yuma/status/1394518565856759816
- ↑ https://x.com/Homurano_Yuma/status/1394512725829513221
- ↑
https://twitter.com/yumakemononerou/status/1411920644497764353- Archive of deleted tweet - ↑
https://twitter.com/yumakemononerou/status/1412628895896014853- Archive of deleted tweet - ↑
https://twitter.com/yumakemononerou/status/1412635485416001545- Archive of deleted tweet - ↑ https://x.com/Homurano_Yuma/status/1412640266041786368
- ↑ https://x.com/Homurano_Yuma/status/1551790771602264065
- ↑ https://x.com/Homurano_Yuma/status/1551791655505694720
- ↑ https://x.com/Homurano_Yuma/status/1551792064534196224
- ↑
https://twitter.com/yumakemononerou/status/1551792301558468610- Deleted tweet, no archive available; Discord screenshot of only surviving embed - ↑ https://x.com/Homurano_Yuma/status/1551795645421301760
- ↑
https://twitter.com/yumakemononerou/status/1551798688317521920- Archive of deleted tweet - ↑ https://x.com/Homurano_Yuma/status/1551804577170698241
- ↑ https://x.com/Rowen_ShikiG/status/1762024703928021116
- ↑ https://x.com/Rowen_ShikiG/status/1762025160985768109
- ↑ https://x.com/Rowen_ShikiG/status/1783043200447295959
- ↑ https://x.com/vocaloid_yamaha/status/1783088509022261606