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[]
Originally, Natsuki Karin and Hanakuma Chifuyu's voice synthesizer production announcement was meant to be announced during Koharu Rikka's first live concert, "Koharu Rikka 1st LIVE! First Day of School!", in Fall 2020. However, because the concert was postponed due to the COVID-19 pandemic, the pair's production was unannounced.[1]
2021[]
Natsuki Karin was introduced in a campaign titled "Koharu Rikka x Otaru Collaboration (小春六花×小樽コラボ)" on May 22, 2021. She was confirmed to be a student enrolled at the fictional Otaru Shiokaze High School and was in the same music club as Koharu Rikka.[2][3] Details about Karin as a character were released and she was confirmed to be voiced by Miyu Takagi for a promotional video.[4][5] She was illustrated by Teshima Nari and the logo was created by Hiroaki Watanabe.[6] It was noted in a TOKYO6 ENTERTAINMENT livestream that there were plans to create a voice library for Karin and Hanakuma Chifuyu, which were confirmed in June to be Synthesizer V AI and CeVIO AI after TOKYO6 ENTERTAINMENT adjusted their website.[7]
On August 8, due to some concerns regarding business activities related to Synthesizer V, Dreamtonics Co., Ltd. noted that Karin was on the list of "yet-to-be-published" voices and initiatives.[8] For many overseas fans, this was the first time they became aware of these voice databases as there was no official announcement via social media, newsletter, or website adjustments regarding the productions. Due to language barriers, the livestream featuring the announcement was overlooked. On September 30, a livestream was confirmed to begin on October 3.[9]
On October 3, it was confirmed that Karin would be produced as the second TOKYO6 character to release. Demonstrations of her Synthesizer V AI and CeVIO AI voice databases, along with a set of Pitagoe samples, were released in addition to an announcement of her crowdfunding campaign, which was set to begin on October 8 and would run until October 28.[10] Separate illustrations for Karin's Synthesizer V and CeVIO designs were also revealed.[11] Karin was expected to release in April 2022.[12]
On October 8, Karin's crowdfunding campaign was launched with a goal of 6,800,000 yen.[13] The main goal was reached in less than three hours since launch, then the final stretch goal was reached on October 11.[14]
2022[]
During the AH-Software Co. Ltd. live broadcast on February 17, 2022 (where TOKYO6 acknowledged their cooperation in the development of VOICEPEAK, AH-Software's new text-to-speech software based on Dreamtonics' Syllaflow AI speech-synthesis engine), Natsuki Karin's release month was reconfirmed to be April.[15] Also, Karin's voice provider Miyu Takagi was confirmed to be making a guest appearance on March 25's AHS livestream.[16]
On March 24, it was announced that Karin would be releasing for CeVIO AI and Synthesizer V AI on April 13 as physical and digital copies. She was also confirmed to be available for the AH-Software starter pack. Details about her voice were provided and pre-orders were launched, and a lite version of her voice database was expected.[17][18] Crowdfund backers for Karin were to receive her in early April.[19] On March 26, the release of Synthesizer V Studio version 1.6.0 brought new features: Vocal Mode and Instant Mode. TOKYO6 announced that these features would be brought to Rikka and Karin later due to the need of making adjustments to the voice databases.[20]
Karin's Synthesizer V AI voice database and CeVIO AI Talk Voice were released to crowdfund backers on April 1; other crowdfund rewards were also being delivered.[21] Karin was released on April 13 as expected for both voice synthesizers. The Lite voice database was released later in the day at 12:00 JST.[22][23]
On July 21, Karin 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), as well as giving Karin access to five new vocal modes, including: Kawaii, Soft, Cool, Happy, and Falsetto, respectively, that had previously been teased about four months prior.[24][20]
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 v104). 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;[25] as a workaround to stabilize the voice output, both Dreamtonics and AH-Software offered these steps below:[26][27]
- 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 Natsuki Karin (as well as other affected AI voice databases distributed by them) by logging in to their respective websites.[28][29] However, it was also noted by AHS that, even after removing HDVM compatibility, voice quality for Karin was still affected by AI Retakes which was not supported in the then-available rollback version.[30]
An update for Karin was announced on October 14. TOKYO6 ENTERTAINMENT would like to implement it as soon as possible, but it still needed time.[31] On November 14, after the release of Karin's v106b1 installer, TOKYO6 ENTERTAINMENT released a survey for its feedback.[32] On November 22, the company noted that the beta version would be used as the official update after receiving mostly positive feedback.[33]
Updates[]
Usage on Synthesizer V Studio 2[]
The paid version of Natsuki Karin can be imported into (and used on) Synthesizer V Studio 2 Pro by simply registering her SVS1 activation code into the My Dreamtonics website. The Lite version cannot be imported into (nor used on) the new software, not even in its feature-limited trial mode.
Voice Database Information[]
Demonstrations[]
| Demonstrations | |
|---|---|
|
| |
| あの星を探して (Ano Hoshi o Sagashite) - Short Version; Prototype Database | |
| イエナイコトバ (Ienai Kotoba) - Short Version; Prototype Database | |
| イエナイコトバ (Ienai Kotoba) - Short Version | |
| Dancing in the binary - Short Acapella Version; English Cross-lingual Singing Synthesis | |
| 一生之幸 (Yīshēng zhī Xìng) - Short Acapella Version[60] | |
| イエナイコトバ (Ienai Kotoba) - Full Version | |
| ゼロになって (Zero ni Natte) | |
| シャニシャニ☆デイズ (Shiny Shiny ☆ Days) | |
| Datte | |
| 夏空ノスタルジー (Natsuzora Nostalgia) | |
Voice Databases[]
- Similar to her voice actress, Karin has a clear and high tone.[1]
- Karin has a cute voice but her low notes have a slightly mature tone.[1]
- She has a voice that is not easily drowned by intense instrumentals, making her a preferable voice for producers specialized in hard rock and metal genres.[1]
- 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,[39] 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[61] and Synthesizer V Studio 2 Pro editors.
- This does not apply to the Lite version.
- Phoneme format: Romaji
- Through cross-lingual singing synthesis, Karin is able to sing in not only Japanese but also in English and Mandarin Chinese. Since the release of her v107b1 update on June 21, 2023, she can also sing in Cantonese Chinese with this feature; since her v110 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 and Synthesizer V Studio 2 Pro editors.
- This does not apply to the Lite version, thus restricting the voice database to Japanese only.
- Downloadable Pitagoe voice files are available for those with Karin's CeVIO AI Talk Voice or Synthesizer V AI voice database after user registration on AH-Software's website. There are over 900 audio files, including ASMR, to use for a wide variety of genres.[62]
- List of recorded audio
- On April 4, 2022, AH-Software announced that some of the file names were garbled for the Pitagoe voice. A modified version was released to correct these.[63]
- As of July 21, 2022, the paid version of Natsuki Karin became compatible with the Vocal Mode function introduced in Synthesizer V Studio 1.6.0. Her v104 update included five variations:
- "Kawaii"
- "Soft"
- "Cool"
- "Happy"
- "Falsetto"
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.
- TOKYO6 ENTERTAINMENT'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.
- Natsuki Karin 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.
- Natsuki Karin AI Solfège:
- Vocal Mode Solfèges:
- "Kawaii":
- "Soft":
- "Cool":
- "Happy":
- "Falsetto":
- "Kawaii":
- Vocal Mode Solfèges:
- Natsuki Karin AI Lite Solfège:
References[]
- ↑ 1.0 1.1 1.2 1.3 https://www.dtmstation.com/archives/60921.html
- ↑ https://x.com/tokyo6info/status/1396090971088211973
- ↑ https://x.com/tokyo6info/status/1396092229597470723
- ↑ https://x.com/tokyo6info/status/1396092229555470337
- ↑ https://note.com/tokyo6/n/nc5e32c933fa1
- ↑ https://x.com/tokyo6info/status/1396092481008066565
- ↑ https://www.youtube.com/watch?v=M9wDSETvuzY
- ↑ https://x.com/dreamtonics_en/status/1424533859752812545
- ↑ https://x.com/tokyo6info/status/1443499343445594117
- ↑ https://x.com/tokyo6info/status/1444648429351800841
- ↑ https://x.com/_17meisai23/status/1444654409766498315
- ↑ https://www.youtube.com/watch?v=MskBg1dEGW4
- ↑ https://x.com/rikka_info/status/1446445271399944192
- ↑ https://x.com/tokyo6info/status/1447492290834944002
- ↑ https://x.com/tokyo6info/status/1494296032750219267
- ↑ https://x.com/tokyo6info/status/1494298937528053760
- ↑ https://www.ah-soft.com/press/cevio/20220324.html
- ↑ https://x.com/ahsoft/status/1506831478369714186
- ↑ https://x.com/tokyo6info/status/1506834090401869824
- ↑ 20.0 20.1 https://x.com/tokyo6info/status/1507669520500273153
- ↑ https://x.com/karin_info1/status/1509809811395059712
- ↑ https://x.com/karin_info1/status/1513923454067949572
- ↑ https://x.com/ahsoft/status/1514077001103319046
- ↑ https://x.com/dreamtonics_en/status/1550050403613835264
- ↑ https://x.com/dreamtonics_en/status/1550520904291012609
- ↑ https://x.com/dreamtonics_en/status/1550520905868009472
- ↑ https://x.com/ahsoft/status/1550385484027035649
- ↑ https://x.com/dreamtonics_en/status/1550520907159851009
- ↑ https://x.com/ahsoft/status/1550385686389616640
- ↑ https://x.com/ahsoft/status/1551766239516979202
- ↑ https://twitter.com/s_akasakov/status/1580837785623142401 (deleted account; archive)
- ↑ https://x.com/tokyo6info/status/1591981747180163072
- ↑ https://x.com/tokyo6info/status/1594852826085494784
- ↑ https://dreamtonics.com/en/synthesizer-v-studio-1-7-0-update-ai-retakes-feature/
- ↑ https://x.com/tokyo6info/status/1550387952882450432
- ↑ https://x.com/tokyo6info/status/1551769998216966144
- ↑ https://x.com/ahsoft/status/1551774834983866368
- ↑ https://dreamtonics.com/en/synthesizer-v-studio-1-8-0b1-update/
- ↑ 39.0 39.1 https://dreamtonics.com/en/synthesizer-v-studio-1-8-0-final-update/
- ↑ https://x.com/ahsoft/status/1595674717200916481/
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-9-0-final-update/
- ↑ https://x.com/dreamtonics_en/status/1671427830629154816
- ↑ https://www.bilibili.com/read/cv24826703/
- ↑ https://x.com/ahsoft/status/1676865674898206720
- ↑ https://x.com/dreamtonics_en/status/1686648078571655168
- ↑ https://t.bilibili.com/825177687051993121
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-10-0b1-update-enhancing-pitch-generation-with-user-feedback/
- ↑ https://x.com/ahsoft/status/1686653272474738689
- ↑ https://x.com/dreamtonics_en/status/1707304150059639108
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-10-0b2-update/
- ↑ https://x.com/ahsoft/status/1707304906535956719
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0b1-update/
- ↑ https://x.com/ahsoft/status/1727970395691856025
- ↑ https://x.com/tokyo6info/status/1727987685288206599
- ↑ https://note.com/tokyo6/n/n742c974716b9 - The main reasoning behind TOKYO6's request to disable RLHF by default (which prevented the release of finalized versions of Koharu Rikka AI v124, Natsuki Karin v110, and Hanakuma Chifuyu v106 and also resulted in the permanent withdrawal of their last respective beta versions) was that the then-current implementation of RLHF learned AI-retake data selected as favorable by various different users of Rikka AI, Karin, and Chifuyu and then reflected it across all installations of their voice databases, thus affecting their overall preference trend; TOKYO6 believed that, due to things like variations in preferred vibrato swing size from user to user, etc., some users would get undesirable results out of their vocals, and in internal beta test results, TOKYO6 noted that the vocals' vibrato tended to be exaggerated and deviating from their character image. TOKYO6 was also concerned about RLHF results automatically affecting the default singing style (with no Vocal Modes applied) to a large extent, resulting in the decision to postpone any further updates to their voice databases until they were given the possibility to disable RLHF by default in the next update.
- ↑ https://x.com/tokyo6info/status/1717458061949026415
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0-update/
- ↑ https://x.com/ahsoft/status/1775800933538320621/photo/4
- ↑ https://x.com/tokyo6info/status/1775804166952403019
- ↑ "Yīshēng zhī Xìng" was meant to demonstrate Mandarin Chinese Cross-lingual Singing Synthesis, but the language setting was still set to Japanese
- ↑ https://x.com/dreamtonics_en/status/1550048543624564736
- ↑ https://x.com/tokyo6info/status/1510290073253969921
- ↑ https://x.com/ahsoft/status/1510829159211503616