SynthV Wiki
SynthV Wiki
Synthesizer V Wiki
404
pages
in: Voice databases, AH-Software Co. Ltd., Synthesizer V Studio voice databases,
and 5 more

Haruno Sora (Synthesizer V Studio)

Sign in to edit
Haruno Sora
SynthV Studio
SynthV Studio 2
VOCALOID5
VOICEROID2
VOICEPEAK
|
Originals
|
Gallery

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[]

On July 12, 2018, VOCALOID5 was officially launched and Haruno Sora, voiced by Japanese voice actress and singer Kikuko Inoue, made her debut as an upcoming VOCALOID5 product with two singing voicebanks ("Natural" and "Cool") and as an upcoming speech voicebank for VOICEROID2. She was released on both engines on July 26.

2023[]

On May 18, 2023, Haruno Sora was announced to be in production for Synthesizer V Studio as a singing AI voice database and as a speech voice library for VOICEPEAK. A silhouette of a new design was shown and it was confirmed that her Synthesizer V voice database would be shown at VVV MUSIC LIVE on June 25.[1][2] She would be performing a self-cover of "Koi no Jumon wa Sorasora" by EHAMIC, which originally released in July 2018 and served as a demo for her VOCALOID5 voicebanks.[3] On the day of the performance, it was revealed that she sang two songs: the previously mentioned "Koi no Jumon wa Sorasora" and "Rera", a song that was originally sung by Nekomura Iroha.

On July 18, to commemorate Sora's fifth anniversary and character birthday, it was announced that Kikuko Inoue would be attending AH-Software Co. Ltd.'s next livestream scheduled for July 26. Information about Sora's Synthesizer V and VOICEPEAK development would be presented as well.[4] On July 24, AH-Software revealed Sora's new designs and demonstrations. The Synthesizer V outfit was designed by Hasegawa Umi and the final version was illustrated by Umetani Atarō.[5] Pre-orders for Sora's Synthesizer V and VOICEPEAK libraries opened, and it was confirmed that she would release on August 24.[6] Sora released on August 24 as expected. Her Lite version was released a week later on August 31.[7]

Updates[]

Haruno Sora AI v101b2 - September 28, 2023[8][9][10] 
A free beta update for Haruno Sora 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.

For Sora specifically, she was the only new vocalist since the release of Synthesizer V Studio 1.10.0b1, thus, she did not have a "b1" update available like the past Synthesizer V AI vocalists.

Haruno Sora AI v101 - October 19, 2023[11][12] 
Final version update compatible for Synthesizer V Studio 1.10.0 which enables Haruno Sora to use Reinforcement Learning from Human Feedback (RLHF) as well as other enhancements (as listed in v101b2's notes) if the beta version was not installed previously.
Haruno Sora AI v102 - October 26, 2023[13] 
A free update for Haruno Sora was released that added support for the Japanese language to the rap feature.
Haruno Sora AI v103 - April 4, 2024[14][15] 
A free update for Haruno Sora 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.
Haruno Sora AI v104 (Synthesizer V Studio 2 only) - March 21, 2025[16] 
A free same-day update for Haruno Sora's Synthesizer V Studio 2-compatible version (called by Dreamtonics Co., Ltd. a "compatibility update") was issued at 16:30 JST, after users who imported her (v103) into Synthesizer V Studio 2 Pro had reported experiencing quality degradations affecting her phoneme timings, making her sound off-beat.[17] This update fixed that off-beat issue.

Usage on Synthesizer V Studio 2[]

The paid version of Haruno Sora 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

Rera - Short Preview Favicon-ytYouTube
恋の呪文はソラソラ (Koi no Jumon wa Sorasora) - Short Preview Favicon-ytYouTube
赤い橋 (Akai Hashi) Favicon-nnNicoNico Favicon-bbbilibili
また1つ好きになった (Mata 1-tsu Suki ni Natta) Favicon-nnNicoNico Favicon-ytYouTube Favicon-bbbilibili
なにがレトロブームじゃい (Nani ga Retro Boom Jai) Favicon-nnNicoNico Favicon-ytYouTube Favicon-bbbilibili
ラズベリー (Raspberry) Favicon-nnNicoNico Favicon-ytYouTube Favicon-bbbilibili
Dance! Dance!! Dance!!! Favicon-nnNicoNico Favicon-ytYouTube Favicon-bbbilibili
翼 (Tsubasa) - Short Version Favicon-ttTwitter
アレカコニア (Arekakonia) - Short Acapella Version Favicon-ytYouTube
どんな言葉なら届きますか？ (Donna Kotoba Nara Todokimasu ka?) - Short Version Favicon-ytYouTube
KevinLead - English Cross-lingual Singing Synthesis Favicon-ytYouTube
Stir Crazy - Short Acapella Version; English Cross-lingual Singing Synthesis Favicon-ytYouTube
故事的最结尾 (Gùshì de Zuì Jiéwěi) - Short Acapella Version; Mandarin Chinese Cross-lingual Singing Synthesis Favicon-ytYouTube
view

Voice Databases[]

Product Information
Optimum
Range: C3~E5

Versions
Lite Version/FLT Available?: Yes (Lite; retired)  Starter Pack Available?: Yes (with SVS2)  Trial Version Available?: Yes  Web Version Available?: No

Package details as noted:
Haruno Sora is a feminine Japanese voice database based on the singing style of Kikuko Inoue. As expected of an AI voice database, Sora can sing with a more human-like and realistic voice.

Vocal traits as noted:
  • Sora can express a wide range of intonations, from a soft and gentle voice quality to a powerful and cool style in the lower range.
  • With Diffusion Probabilistic Models (DPM), Sora can sing more realistically through changes in volume and breath, further enriching singing details, making each singing unique, and providing creators with more options. Through this mode, she can use AI Retakes to create multiple "takes" of a sung section to find an ideal vocal without the need for "laborious tuning". This feature is only available in the Synthesizer V Studio Pro and Synthesizer V Studio 2 Pro editors.
    • This does not apply to the Lite version.

Phonetic notes as noted:
  • Phoneme format: Romaji
  • Through Cross-lingual Singing Synthesis, Sora can sing in not only Japanese but also in English, Mandarin Chinese, and Cantonese Chinese. Since the release of her v103 update on April 4, 2024, she can also sing in Spanish with this feature. This feature 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.

Vocal Modes as noted (Synthesizer V Studio Pro and Synthesizer V Studio 2 Pro editors only):
  • The paid version of Haruno Sora comes with five variations within the Vocal Mode function:
    • "Sweet"
    • "Soft"
    • "Adult"
    • "Pop"
    • "Cool"

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
    • Mac OS X: 10.13 or higher
    • Linux Ubuntu 20.4 or higher

Other:

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

License agreements as noted:
  • 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.
    • Haruno Sora 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

References[]

  1. ↑ https://x.com/harunosora17/status/1659182465200852992
  2. ↑ https://www.youtube.com/watch?v=ZUt4OypVc9Q
  3. ↑ https://x.com/harunosora17/status/1666253826758967296
  4. ↑ https://x.com/ahsoft/status/1681296462054055936
  5. ↑ https://x.com/ahsoft/status/1683688360479723521
  6. ↑ https://www.ah-soft.com/press/voice/20230725.html
  7. ↑ https://x.com/ahsoft/status/1697144953645011266
  8. ↑ https://x.com/dreamtonics_en/status/1707304150059639108
  9. ↑ https://dreamtonics.com/synthesizer-v-studio-1-10-0b2-update/
  10. ↑ https://x.com/ahsoft/status/1707304906535956719
  11. ↑ https://dreamtonics.com/synthesizer-v-studio-1-10-0-final-update/
  12. ↑ https://x.com/ahsoft/status/1714919114182181140
  13. ↑ https://x.com/ahsoft/status/1717451110305366047
  14. ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0-update/
  15. ↑ https://x.com/ahsoft/status/1775800933538320621/photo/4
  16. ↑ https://forum.dreamtonics.com/t/official-synthesizer-v-studio-2-post-launch-follow-up-updates/1380#p-4163-error-400-when-adding-activation-codes-to-my-account-5
  17. ↑ https://forum.dreamtonics.com/t/official-synthesizer-v-studio-2-post-launch-follow-up-updates/1380#p-4163-compatibility-updates-for-kasane-tetoharuno-sora-sounding-off-beat-7

Navigation[]

v • e
Synthesizer V Wiki Directory
Voice Databases
Introduced since
Synthesizer V
Eleanor Forte (SV • SVS) • Yamine Renri (SV • SVS) • GENBU (SV • SVS) • AiKO (SV • SVS) • Chiyu (SV • SVS) • Shian (SV • SVS) • Cangqiong (SV • SVS) • Haiyi (SV • SVS)
Introduced since
Web Synth V
Introduced since
Synthesizer V Studio & AI
Muxin (SVS • SVS2) • Minus (SVS) • Koharu Rikka (SVS) • Tsurumaki Maki (SVS: JPN • ENG – SVS2) • Tsuina‑chan (SVS • SVS2) • Qing Su (SVS • SVS2) • ANRI (SVS: Debut • Arcane – SVS2) • SOLARIA (SVS • SVS2) • Kyomachi Seika (SVS • SVS2) • Ryo (SVS • SVS2) • Kevin (SVS • SVS2) • Xingchen (SVS) • Mo Chen (SVS • SVS2) • Natsuki Karin (SVS) • An Xiao (SVS • SVS2) • Feng Yi (SVS • SVS2) • Weina (SVS • SVS2) • Yuma (SVS • SVS2) • Natalie (SVS • SVS2) • Hanakuma Chifuyu (SVS) • Mai (SVS • SVS2) • ASTERIAN (SVS • SVS2) • Xuan Yu (SVS • SVS2) • Cong Zheng (SVS • SVS2) • Cheng Xiao (SVS • SVS2) • XIA YU YAO (SVS • SVS2) • Ninezero (SVS • SVS2) • JUN (SVS • SVS2) • Kasane Teto (SVS • SVS2) • Lin Lai (SVS • SVS2) • Yun Quan (SVS • SVS2) • Ritchy (SVS • SVS2) • D‑Lin (SVS • SVS2) • Haruno Sora (SVS • SVS2) • Eri (SVS • SVS2) • Sheena (SVS • SVS2) • Hayden (SVS • SVS2) • Wei Shu (SVS • SVS2) • SAROS (SVS • SVS2) • Ayame (SVS • SVS2) • Jin (SVS • SVS2) • GUMI/Megpoid (SVS • SVS2) • POPY (SVS • SVS2) • ROSE (SVS • SVS2) • OSCAR (SVS • SVS2) • Yi Xi (SVS • SVS2) • Frimomen (SVS • SVS2) • ROSA (SVS) • Ling Wan (SVS • SVS2) • NOA (SVS • SVS2) • Miyamai Moca (SVS • SVS2) • NYL (SVS • SVS2) • Topaz (SVS • SVS2) • Felicia (SVS • SVS2) • Riku (SVS • SVS2) • Hibiki Koto (SVS • SVS2) • Otomachi Una (SVS • SVS2)
Introduced since
Synthesizer V Studio 2
Liam (SVS2) • Mo Xu (SVS2) • miki (SVS2) • Hiyama Kiyoteru (SVS2) • UNI (SVS2) • HXVOC (SVS2) • GALENAIA (SVS2) • PASTEL (SVS2) • HALO (SVS2) • Nakuru (SVS2) • Natsume Itsuki (SVS2) • Amara (SVS2) • Archie (SVS2) • Yi Wei (SVS2) • Asumi Shuo (SVS2) • Asumi Ririse (SVS2) • Nekomura Iroha (SVS2) • Lang Chuan (SVS2) • Yun Hua (SVS2) • Danny (SVS2) • Etta (SVS2) • AVER (SVS2) • REMMANT (SVS2) • Choir Voices (SVS2: Collection 1 • Collection 2 • Collection 3)
Upcoming
Unreleased
JA-F1 • MAN-F1 • MAN-M1 • KAFU — Private: Shirakami Meito • Yumi AraI
Companies
Projects & Series
Other Information
Community content is available under CC-BY-SA unless otherwise noted.