Overview
HARU (羽累) is the fifth voice synthesis software in KAMITSUBAKI STUDIO’s “Musical Isotope” series. Built on the CeVIO AI platform, she is created using AI technology based on the vocal data of virtual rapper/singer HARUSARUHI (春猿火) to generate highly realistic singing voices.
As the final voicebank revealed in the initial lineup of the project, the name “HARU” is taken from the “Haru” (春 - Spring) in Harusaruhi’s name, while reflecting the concepts of “emergence” (羽化) and “accumulation” (累ねて). She inherits Harusaruhi’s sharp phrasing and high-speed rap/singing capabilities.
Character and Creative Positioning
Designed by illustrator Isshiki (一色), HARU’s visual identity includes long white hair (with a braid on the right side), a headset with cyan and red earcups, and bright yellow eyeshadow and lip gloss. She wears a black-and-white outfit combining traditional oriental wide sleeves and a gothic fishtail skirt.
In terms of vocal performance, HARU features crisp pronunciation and excels in rapid rap sequences and explosive high notes. In March 2024, the VOICEPEAK-compatible “TALK EXTENSION” was released, adding natural text-to-speech capabilities to her portfolio.
Basic Profile and Character Setting
HARU is a musical-isotope voicebank and character based on HARUSARUHI’s vocal data. It translates the source singer’s rhythmic drive, rap delivery, and explosive emotional attack into a synthetic voice for creators.
| Item | Detail |
|---|---|
| Voice source | HARUSARUHI |
| Platform | CeVIO AI and VOICEPEAK TALK EXTENSION |
| Character design | Isshiki |
| Main projects | HARU original-song contest, V.I.P |
Activity History
- October 18, 2022: The teaser video for HARU was officially unveiled during the studio’s 3rd anniversary livestream, announcing the project.
- November 13, 2023: The singing voice synthesis software “CeVIO AI Musical Isotope HARU” was officially released.
- March 29, 2024: The text-to-speech software “Musical Isotope HARU TALK EXTENSION collaboration with VOICEPEAK” was officially released.
- July 7, 2024: Performed at the first virtual joint mini-concert of the Musical Isotopes, “V.I.P 1st MINI LIVE ETHEREAL WORLD”.
- Since her release, HARU has integrated into the studio’s virtual singer chorus line and has become a popular choice among UGC creators.
Representative Works and Related Entries
Expand full albums and EPs
Albums & EPs
| Release date | Type | Title |
|---|---|---|
| 2024-09-18 | Album | 制定のオーバーラップ |
| 2024-10-16 | Album | 対峙のオーバーラップ |
| 2024-10-30 | Album | 結尾のオーバーラップ |
| 2026-04-26 | EP | ビビッド |
Expand full singles list
Singles
| Release date | Title |
|---|---|
| 1997-11-26 | promise |
| 2013-04-28 | 思い出の帰り道 |
| 2016-01-26 | 小さな冒険 |
| 2024-03-27 | Follow Me Now! |
| 2024-05-26 | 送り雨道 |
| 2024-06-27 | 拒絶反応 feat. 羽累 |
| 2024-08-31 | ヒットパレル |
| 2024-10-16 | ロースピードフェイクリリック |
| 2024-10-25 | バーナリゼーション |
| 2024-11-26 | ラジオヒーロー |
| 2025-02-20 | 過去を刺す |
| 2025-06-26 | 光速セオリー |
| 2025-06-29 | 森の中のピアノ |
| 2025-07-01 | 夢のステップ |
| 2025-08-31 | ゾンビフラッカ |
| 2026-07-29 | meguru |
| 2026-07-31 | 森の夕暮れのピアノ |
Representative Songs and Creator Ecosystem
HARU is widely used for rap, fast electronic pop, and rhythm-driven works. Demonstration songs, the HARU original-song contest, and TALK EXTENSION are the main public routes through the project. The relationship with HARUSARUHI is a voice-source relationship, not shared authorship or a shared personal discography.
Name and Identity Boundaries
HARU is the isotope character and voicebank; HARUSARUHI is the virtual singer whose vocal data supports it. Official demonstrations, creator songs, and joint V.I.P performances should be listed separately so that the source artist and user-generated works are not merged.
Official Compilations and Naming System
Built from HARUSARUHI’s voice and inheriting her dense diction and rap cadence, it represents the “rap / experimental” strand.
| Item | Detail |
|---|---|
| First compilation | HARU+YOU HARU COMPILATION ALBUM Catharsis (2024-03-20) |
| Naming | Follows the formula “source-witch code + YOU”, meaning “HARUSARUHI and you” |
| Voice template | HARUSARUHI |
| Release system | KAMITSUBAKI STUDIO Musical Isotope series |
What the naming means: titling the official compilations “X+YOU” redefines the Isotope from a “tool” into “a partner who creates alongside the listener”. Every track on the compilations comes from an invited or selected creator, making them a direct intersection of the official and community creative ecosystems.
Acoustic Engines and Library Specifications
The Musical Isotope project is built on a dual-engine acoustic architecture, each engine serving a different purpose.
| Engine | Developer | Technical character |
|---|---|---|
| CeVIO AI | Techno-Speech | Evolved from a hybrid of HMM and deep neural networks (DNN), it captures vibrato, breath and vocal-fold micro-noise — the “imperfect but alive” detail of a real singer — to an extreme degree |
| Synthesizer V AI | Dreamtonics (5th generation) | A fully autoregressive acoustic model with cross-lingual singing (natural Japanese/English/Chinese transitions), seamless morphing of emotion parameters (Power / Soft / Clear), and very high render speed and editability |
Why both: CeVIO AI preserves human imperfection; Synthesizer V AI handles cross-lingual work and deep editability. Together they cover everything from reproducing a live vocal texture to giving global creators full creative latitude.
Open Licensing and the Derivative-Work Ecosystem
For the Musical Isotope project KAMITSUBAKI abandoned the closed restrictions of conventional artist management and built an open, self-reinforcing licensing loop.
- A commercial-use threshold instead of a ban: doujin musicians may freely use the voice libraries within a defined revenue ceiling and release the resulting originals straight to streaming platforms.
- Official compilations that absorb the scene: through open calls for official compilation albums, outstanding community creators and works are brought onto major releases, creating a cycle of “community creation → official validation → wider reach”.
- Results: this mechanism produced phenomenon-level UGC hits such as “キュートなカノジョ” and “フォニイ”, carrying AI singing into the centre of mainstream pop culture.
Industry significance: where the traditional record system restricts derivative works, KAMITSUBAKI treats a voice library as a gateway into an ecosystem rather than a closed asset — the fundamental reason the Isotope family accumulated such a vast body of UGC within a few years.
Related Projects / Setting
HARU is the fifth member of the “Musical Isotope Project”. By digitizing Harusaruhi’s personal rap and vocal styling, this project makes virtual rap creation accessible to more creators. As a digital creative partner, HARU continues to expand the possibilities of vocal synthesis in cutting-edge musical genres.
Relationship to the Source Witch
| Item | Detail |
|---|---|
| Voice template | HARUSARUHI |
| System | One node of the five-witch isotope matrix of V.W.P |
| First release | CeVIO AI (a Synthesizer V AI edition followed) |
| Position in the lore | The digital-side counterpart of KAMITSUBAKI’s “song singularity”, sharing one source of “singing voice” with HARUSARUHI |
Naming rule: each Isotope’s official name is drawn directly from its source witch (KAFU←KAF, RIME←RIM, SEKAI←ISEKAIJOUCHO, COKO←KOKO, HARU←HARUSARUHI). The convention itself declares the core idea: different forms of one existence.