Site tools

ENG

COKO

Edit article

A CeVIO AI musical isotope built from KOKO's vocal data, bringing the power and clarity of the original voice to synthesized music creation.

Observation formConnected identities, individual records.
Contents

Overview

COKO (狐子) is the fourth voice synthesis software in KAMITSUBAKI STUDIO’s “Musical Isotope” series. It is built using AI technology based on the vocal data of virtual singer KOKO (幸祜) to generate highly realistic singing voices on the CeVIO AI platform.

As a member of the Musical Isotope series, COKO inherits KOKO’s high-pitched, powerful, and energetic vocal tone. In Japanese, the pronunciation “COKO” forms a playful homophonic pairing with KOKO’s name.

Character and Creative Positioning

Designed by SWAV, COKO’s visual appearance is defined by short white hair, sky-blue inner highlights, active fox ears, and a tailbone accessory representing the nine-tailed fox. This design combines futuristic tactical gear with fantasy elements.

Vocally, COKO preserves KOKO’s strong long notes while featuring realistic breathing sounds and crystal-clear vocals, making her highly suitable for high-energy music genres such as rock and electronic music. In January 2024, the VOICEPEAK-compatible “TALK EXTENSION” software was released, providing COKO with highly natural speech synthesis capabilities for spoken dialogues.

Basic Profile and Character Setting

COKO is a musical-isotope voicebank and character based on KOKO’s vocal data, not KOKO herself. Its design and sound preserve the source singer’s strong projection, sustained notes, and emotional drive while making those qualities available for new creator works.

ItemDetail
Voice sourceKOKO
PlatformCeVIO AI and VOICEPEAK TALK EXTENSION
Character designSWAV
First releaseJanuary 25, 2023
Demonstration work“the last bullet”

Activity History

  • July 15, 2022: The first teaser video for COKO was released, introducing her silhouette.
  • October 9, 2022: During KOKO’s 2nd ONE-MAN LIVE “PLAYER Ⅱ -AraRe-”, it was announced that COKO would be released on January 25, 2023, and pre-orders were opened.
  • January 25, 2023: The voicebank “CeVIO AI Musical Isotope COKO” was officially released.
  • January 25, 2024: The speech synthesis software “Musical Isotope COKO TALK EXTENSION collaboration with VOICEPEAK” was officially released.
  • COKO regularly appears as a guest performer in studio events like “KAMITSUBAKI FES”, showcasing a vibrant stage presence.
Expand full singles list

Singles

Release dateTitle
2015-10-11スカイライン (feat. 狐子)
2015-10-11てやんでいっ! (feat. 狐子)
2020-05-24Ballerina (feat. Lil wick)
2021-06-19KiLLer TuNe (feat. 狐子)
2023-03-26心の傘
2023-11-27FAKE
2024-03-14ギフテッド・ギミック
2024-12-10おぼえてろ
2024-12-10キツネガミ
2025-02-28NEVERMIND NEVERLAND
2025-11-14消えてしまいたい夜に
2026-01-28Sugar-High
2026-04-29神羅 (feat. ゆうゆ)
2026-05-26TOKYO MIDNIGHT FANTASY

Representative Songs and Creator Ecosystem

“the last bullet” is the clearest bridge between KOKO’s live impact and COKO’s synthetic voice. TALK EXTENSION expands COKO beyond singing into speech, while V.I.P places the character alongside other Kamitsubaki musical isotopes. Community-created rap, electronic pop, and high-energy songs form the broader catalogue.

Name and Identity Boundaries

COKO, KOKO, and songs made with COKO must be recorded as separate layers: synthetic character, source virtual singer, and creator work. A COKO release is not automatically a KOKO performance, even where official projects reference one another.

Official Compilations and Naming System

Built from KOKO’s voice and inheriting her piercing rock delivery, it represents the “high-tension rock” strand.

ItemDetail
First compilationKOKO+YOU COKO COMPILATION ALBUM Ecstasy (2023-08-30)
NamingFollows the formula “source-witch code + YOU”, meaning “KOKO and you”
Voice templateKOKO
Release systemKAMITSUBAKI 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.

EngineDeveloperTechnical character
CeVIO AITechno-SpeechEvolved 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 AIDreamtonics (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.

  1. 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.
  2. 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”.
  3. Results: this mechanism produced phenomenon-level UGC hits such as “キュートなカノジョきゅーとなかのじょcute na kanojo” and “フォニイふぉにいphony”, 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.

COKO is a key software product of the “Musical Isotope Project”. The project digitizes and extends KOKO’s voice, enabling it to act not only as a personal singer’s voice but also as an open-source vocal asset for creators to program and restructure, stimulating diverse cross-dimensional creations.

Relationship to the Source Witch

ItemDetail
Voice templateKOKO
SystemOne node of the five-witch isotope matrix of V.W.P
First releaseCeVIO AI (a Synthesizer V AI edition followed)
Position in the loreThe digital-side counterpart of KAMITSUBAKI’s “song singularity”, sharing one source of “singing voice” with KOKO

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.

KAMITSUBAKI WIKI

Sign in to the Wiki

Use your existing AI account. Sync your library across devices; reading the Wiki remains open.

My space →