Vocaloid

Vocaloid is a vocal synthesis software, internet culture, and way of life. There are many different kinds of Vocaloid, from the well-known alternative UTAU, to the pop producer and famed Hatsune Miku collaborator DECO*27, to whatever the fuck producers like ぬぬぬぬ are up to. The program can be used to input notes and phonemes to have a selected voicebank sing a pattern on playback. There are many similar softwares, either competing, or similarly in speech synthesis (text-to-speech).

A figure of Kasane Teto, a famous vocal synth character, in her UTAU outfit. Figures, plushes, and other merchandise exists of many characters, even including themed frames for glasses.

This article contains many Japanese names, where the surname is listed first.

As a program

A vocal synth program, Synthesizer V Studio. The interface is similar to a DAW, but much more task-specific. Kyomachi Seika is loaded.

Vocal synth programs are similar in function to a digital audio workstation. Both use patterns, clumps, or groups, containing MIDI notes and extra data, alongside having playback of audio files. While DAWs send those notes to instrument plugins, support effect plugins on those audio and instrument track, and allow complex routing of audio, vocal synths focus on their core feature, attaching extra metadata to notes and groups, including lyrics, phonemes, and tuning, then sending this data into the software's backend, whether that be a resampler, in the case of UTAU, or deep learning and related technology, in the case of "AI" voicebanks and software.

The recent usage of neural networks in vocal synthesis has allowed a great increase in realism and fidelity, being able to resynthesize and store much more detailed characteristics of a voice, with characters sometimes sounding vastly different between traditional sample-based synthesis and deep learning. Different software has also chosen to handle this differently, however, with Synthesizer V being focused on high fidelity, realistic synthesis, while Vocaloid 6's VOCALOID:AI keeps a majority of the quirks and specialties of the Vocaloid engine, and CeVIO AI having a distinct, omnipresent layer colouring the sound. 'AI' voicebanks can take substantially less storage space; Synth V AI voices are usually around 40 megabytes for Studio 1, and around 130-140 megabytes for Studio 2; and VOICEVOX being around 2 gigabytes packaged.

As a culture

Akita Neru, despite not being a Vocaloid, is also a Vocaloid.

While Vocaloid has been categorized as a genre, its only defining trait as one is the usage of synthesized voices in any amount. It can be better described as a community or culture, particularly in the earlier days connecting with other nearby circles like Touhou. Vocal synth is generally vast and accepting in influence, genre, and topic, being an affordable way to have a professional voice sing any song the heart desires. As vocals and lyrics are common in most genres, vocal synth tends to appear in many places. Often, specific characters and voices can be found singing anything, from electro swing to jazz fusion, from post-hardcore metal to gentle ballads, or even the most experimental of sounds. Many popular songs have their project files available, allowing anyone to make a cover of the song with any vocalist one wishes.

Most popular characters are intentionally left as mostly blank slates for the producers and artists, leading to a wide range of personalities and interpretations. Hatsune Miku is well-defined as a world-famous idol able to perform no matter the song, Hiyama Kiyoteru is a harmless elementary school teacher trying his hardest to be cool again (and failing), and Haruno Sora is just doing her best.

Vocaloid is also inherently gay, with yuri abound and immense potential for philosophical debates on identity and artificial intelligence, robotics as trans allegories, and generally queer-coded happenings. However, there is basically no yaoi, as there are no men, similar to Touhou.

Vocal synth

Vocaloid

Vocaloid is the most famous, and one of the oldest with VOCALOID 1 dating to 2004; the first two voicebanks being the pair LEON and LOLA. Their cover images are just stock images with text and a filter. The software is by far the most influential, hosting the likes of Hatsune Miku, Megurine Luka, Megpoid, KAITO, and many more. The first generation had not much of note, except for the two other voicebanks by Crypton Future Media, MEIKO and KAITO. VOCALOID 2 would be where everything started spicing up, with Miku and the rest. Other less renowned characters had also shown up around this time, like AH-Soft's Kaai Yuki, SF-A2 miki, and that other guy. Voices can be tuned with a set of parameters, shaping the character of the sound in various ways; DECO*27 has a very distinct tuning of Hatsune Miku, for example. Many popular characters have Append voicebanks, featuring a different vocal tone.

The sample-based Vocaloid engine has a distinctive sound, different from much of the rest of the field and even Vocaloid 6's VOCALOID:AI. In some cases, certain voicebanks have unique timbres different from any other software, such as v flower or Yuzuki Yukari. While Appends are the main method of substantially different vocal tones, Vocaloid 6 doesn't seem to have many, if at all.. VOCALOID:AI supports cross-language multilingual synthesis in English, Japanese, and Chinese.

UTAU

UTAU is a free program similar to Vocaloid, albeit being free and therefore... Look, all I'm saying is when you have one of the most popular girl on the internet, you can afford some quality programming.

One of the big features is that voicebank creation and editing is included, allowing anyone with a microphone and free time to make their own. UTAU brings us the likes of Adachi Rei, Kasane Teto, Utane Uta (Defoko), and Momone Momo, not-very-well-known to be the voice of Nyan Cat. (Yes, daniwell made the original, which featured Miku, but the original video with the Nyan Cat featured a cover with Momone Momo on it.) A large majority of all the total voicebanks ever are UTAU, due to the accessibility of creation. It still takes a lot of time and effort, but that's free in comparison to the unknown vast sums it would cost for any other engine.

A primary feature of UTAU is modularity, being able to install new resamplers to use the voicebank samples in a different way. These have developed over time, while still being part of a free software and mostly done out of enthusiasm, and the engine is far from the cutting edge of technology. The resampler Moresampler was created by the eventual founder of Dreamtonics and creator of Synthesizer V.

Despite appearing as a distinct character, Akita Neru does not have her own official voice, usually being derivative of Hatsune Miku or Kagamine Rin. Other derivative characters include Yowane Haku.

CeVIO Creative Studio

CeVIO Creative Studio. It won an award from Microsoft, apparently. Speech synthesis is available for supported voicebanks.

Synthesizer V

Synthesizer V was originally released in 2018, later dubbed Synthesizer V R1 for clarity. Deriving from an advanced library for an alternate resampler for UTAU, the first generation wasn't much of note, with the only name having much of any fame being Eleanor Forte. 2020 brought the release of Synthesizer V Studio, being among the first to adopt neural network based synthesis and helped bring 'AI' to everything vocal synth. Synthesizer V Studio and AI voicebanks gave impressive fidelity, and while lacking the fine-tune control of Vocaloid tuning, it brings Vocal Modes allowing for a much wider range of sounds from the same voicebank, replacing Appends. Synthesizer V Studio 2 released in 2025, bringing generational uplifts, reducing engine noise and enhancing tuning controls.

Synthesizer V AI voicebanks support multilingual synthesis, in English, Japanese, Mandarin and Cantonese, Spanish, and Korean with Synth V Studio 2.

NEUTRINO

NEUTRINO, also stylized as n3utrino, is described as a "Neural singing synthesizer", and initially released in 2020 effectively as an early demonstration of AI voicebanks. It kind of just... exists, but at least it's more notable than CeVIO Creative Studio. A few well-known names showed up here, before mostly moving on to more renowned software: Kotonoha Aoi and Akane, Tohoku Zunko and... oh, it's just first-party voices, the Kotonohas, and various SSS LLC characters.

NEUTRINO is available for free, and has received updates since release.

CeVIO AI

CeVIO AI. It has voices and characters, including noteworthy ones like KAFU, IA, Ci flower, and has a very present engine noise shaping the sound.

VoiSona

VoiSona is CeVIO AI but more is. And also subscription service model. It has voices and characters, including noteworthy ones like Chis-A.

VoiSona derives from CeVIO AI, but is managed by Techno-Speech Ltd., instead of... Damn, I already forgot who runs CeVIO. Most voicebanks from CeVIO AI are present on VoiSona.

New Type

New Type (Piapro Studio NT) is a singing synthesizer that only has Piapro characters. Well, maybe only Hatsune Miku and Kagamine Rin/Len. Okay, basically only Miku.

ACE Studio

ACE虚拟歌姬 (ACE Studio)... Well, it's also there, but it's moreso just there in the back rather than the distinct void of existence that is CeVIO. It's Chinese, subscription service, and supports creating voicebanks, similar to UTAU. It has Luo Tianyi, one of the original Vsingers. ACE Studio features multilingual synthesis in English, Japanese, and Chinese.

Text-to-speech

Text-to-speech has an extensive history largely unrelated to Vocaloid, but famous or relevant ones include DECtalk, being the voice of Stephen Hawking and the game Moonbase Alpha, and AquesTalk, whose Female Voice 1 is the provider for Utane Uta.

The majority of its scene influence is on the Japanese side of the internet, primarily Niconico and part of YouTube, with many of the characters here having much more clearly defined traits, characters, and personalities, either via consensus or specific authors' choices. By sheer volume, a substantial amount of all Japanese vocal synth consists of voiceovers, let's-plays, and anything that could be done with having full access to a voiced character.

VOICEROID

VOICEROID is the first speech synthesis offering from AH-Soft, originally releasing in late 2009 using the AITalk speech synthesis engine. At first, not much was going on, but VOICEROID+, out a year later, soon brought many more iconic characters. VOICEROID+ EX was an upgrade from that in 2014, followed by VOICEROID2 in 2017. This and similar later software supports inputting a script for one or more characters, to optionally construct dialogue, with adjustment options depending on specific program. Other similar but independent character-specific products were built on the same AITalk engine, including Gynoid TALK, Talk Ex, and galaco Talk, including a limited set or just one character each. The engine noise is clearly defined breaks between samples, similar to Vocaloid.

Characters include Tsurumaki Maki, Yuzuki Yukari, Kizuna Akari, Kotonoha Aoi, Kotonoha Akane, Iori Yuzuru, Tohoku Zunko, Tohoku Kiritan, and others.

A.I.VOICE

A.I.VOICE is effectively the sequel to VOICEROID2. Like Voiceroid, the primary language is Japanese, but now a few supporting voicebanks are available for English and Chinese. Most characters from VOICEROID have versions here, along with many more additional ones, including Adachi Rei and flower. A.I.VOICE is built on AITalk, but despite its name and recent release, it doesn't seem to use neural network-based voicebanks.

VOICEVOX

VOICEVOX is a fully freely available speech and vocal synthesis software utilising neural network technology. It features many defining characters, including Zundamon, Kasukabe Tsumugi, Tohoku Kiritan, Nurse Robot_Type T, and other related ones. Like VOICEROID, the program and documentation are only in Japanese. The engine noise is that of typical neural networks, being a fluid and coherent sound with reduced audio fidelity.

VOICEPEAK

VOICEPEAK is a speech synthesis software by AHS and Dreamtonics, the developers of Synthesizer V. The main features are the AHS characters and very high fidelity synthesis. It features characters such as Kasane Teto, Tsurumaki Maki, Tohoku Kiritan, Haruno Sora, and Hanakuma Chifuyu.

CoeFont and COEIROINK

CoeFont and COEIROINK are two unrelated but similar text-to-speech with AI tech. Both support creating voicebanks, and have free options, with CoeFont having a paid version. COEIROINK doesn't include notable characters, but CoeFont has the limited selection of SAYO, Kazehiki, Nurse Robot_Type T, Yokune Ruko, Allial, Millial, and Averuni. The latter three are first-party and multilingual.

List of characters

Entries are listed by character, not product name, in arbitrary but usually chronological order. Cross-language synthesis like in Vocaloid 6, Synth V Studio, or ACE Studio will be marked, but not listed as native languages.

Crypton Future Media (Piapro)

Character	Programs	Notes	Languages
MEIKO	Vocaloid (1, 3, 4)	All Piapro characters have multiple Append voicebanks.	Japanese, English
KAITO	Vocaloid (1, 3, 4)		Japanese, English
Hatsune Miku	Vocaloid (2, 3, 4, 6), New Type	初音ミク. Early access for her V6 was released on the 10th of December, 2025.	Japanese, English, Mandarin Chinese
Kagamine Rin	Vocaloid (2, 4), New Type	New Type	Japanese, English
Kagamine Len	Vocaloid (2, 4), New Type	The twins share a voice actor.	Japanese, English
Megurine Luka	Vocaloid (2, 4)	First bilingual Vocaloid.	Japanese, English

VOCALOMAKETS

Vocaloid 3 and 4, Voiceroid, and exVOICE bonus sample packs distributed by AH-Soft. Vocaloid 6 distributed by Internet Co. . Others distributed first-party.

Managed by Bumpy Factory Corporation, owned by and named after Bumpyうるし.

Character	Programs	Notes	Languages
Yuzuki Yukari	Vocaloid (3, 4, 6), Voiceroid (+, +EX, 2), A.I.VOICE (1, 2), Seiren Voice	Has multiple variants, Appends, and unique costumes for most.	Japanese* (V6)
Kizuna Akari	Vocaloid (4, 6), Voiceroid (2), A.I.VOICE (1, 2), Voidol, Seiren Voice	Has multiple variants. Voidol and Seiren Voice are voice changers.	Japanese* (V6)
Yuzuki Yukari (Shizuku)	A.I.VOICE (1)	A younger derivative of Yuzuki Yukari, and a distinct character.	Japanese
Kizuna Akari (Tsubomi)	A.I.VOICE (1)	A younger derivative of Kizuna Akari.	Japanese
Kizuna Akari (Moe)	A.I.VOICE (1)	An even younger derivative of Kizuna Akari.	Japanese

AHS (AH-Soft)

Since 2020, AHS is in yuri with Dreamtonics, and new voicebanks are mostly on Synthesizer V and VOICEPEAK. Internet Co. handles many Vocaloid 6 releases where previous versions were AHS.

Character	Programs	Notes	Languages
SF-A2 開発コード miki	Vocaloid (2, 4), Synthesizer V (Studio 2)	SF-A2 codename miki. Voiced by and named after Furukawa Miki.	Japanese* (SynthV)
Kaai Yuki	Vocaloid (2, 4)	Voiced by a child. Famous for Lagtrain.	Japanese
Hiyama Kiyoteru	Vocaloid (2, 4), Synthesizer V (Studio 2)	The teacher of Kaai Yuki. Original 3 released on the same day.	Japanese* (SynthV)
Tsurumaki Maki	Voiceroid (+, +EX), CeVIO AI, VoiSona, Synthesizer V (Studio 1, 2), VOICEPEAK	Voiceroid has a different voice actor. Has 5 total Synth V voicebanks.	Japanese, English* (SynthV)
Kotonoha Aoi	Voiceroid (+, 2), A.I.VOICE (1, 2), Voidol, NEUTRINO, Synthesizer V (Studio 1), Seiren Voice, Vocaloid (6)	Seiren Voice and Synthesizer V have one voicebank for both sisters.	Japanese, English, Chinese* (V6)
Kotonoha Akane	Voiceroid (+, 2), A.I.VOICE (1, 2), Voidol, NEUTRINO, Synthesizer V (Studio 1), Seiren Voice, Vocaloid (6)	Both share a voice provider, but Akane has a Kansai dialect.	Japanese, English, Chinese* (V6)
Nekomura Iroha	Vocaloid (2, 4), Synthesizer V (Studio 2)	Themed after Hello Kitty. Has a vast vocal range. Voiced by a trans guy!	Japanese* (SynthV)
Minase Kou	Voiceroid (+EX), VOICEPEAK		Japanese
Kyomachi Seika	Voiceroid (+EX), Synthesizer V (Studio 1, 2), VOICEPEAK	Her voice dispels any focus.	Japanese* (SynthV)
Tsuina-chan	Voiceroid (2), Synthesizer V (Studio 1, 2), Vocaloid (6)		Japanese* (SynthV, V6)
Miyamai Moca	Synthesizer V (Studio 1, 2), VOICEPEAK	Draws the focus Seika dispels.	Japanese* (SynthV)
Haruno Sora	Vocaloid (5), Voiceroid (2), Synthesizer V (Studio 1, 2), VOICEPEAK	Contains whimsy and sillyness. Has a deep and soft voice.	Japanese* (SynthV)
Iori Yuzuru	Voiceroid (2), A.I.VOICE (1,2), Seiren Voice		Japanese
Frimomen	Synthesizer V (Studio 1, 2), VOICEPEAK	Included with VOICEPEAK voicebanks. Has a superhero transformation.	Japanese* (SynthV)
Super Frimotan	VOICEPEAK	Girl Frimomen. Available with 5 Frimomen activation codes.	Japanese
Asumi Ririse	VOICEPEAK, Synthesizer V (Studio 2)		Japanese* (SynthV)
Asumi Shuo	VOICEPEAK, Synthesizer V (Studio 2)		Japanese* (SynthV)

Both Kotonoha sisters have Tsubomi variants, but aren't as notable as the VOCALOMAKETS characters.

INTERNET Co., Ltd

As AHS has moved over to Synthesizer V, Internet Co. handles many Vocaloid 6 ports of voicebanks.

Character	Programs	Notes	Languages
GUMI	Vocaloid (2, 3, 4, 6), Voidol, A.I.VOICE (1, 2), Synthesizer V (Studio 1, 2), own talk software	The character is GUMI, but the product name is Megpoid (or AI Megpoid).	Japanese, English* (SynthV, V6)
galaco	Vocaloid (3, 6), own talk software, A.I.VOICE (1, 2)	In lowercase. First split into a Red and Blue duo, with White and Black for V6.	Japanese* (V6)
Otomachi Una	Vocaloid (4, 6), own talk software, Voiceroid (2), Voidol, VOICEPEAK, Synthesizer V (Studio 1, 2), A.I.VOICE (2)	On 4 separate talk softwares. AHS do Synthesizer V and VOICEPEAK.	Japanese* (SynthV, V6)
Kamui Gakupo	Vocaloid (2, 3, 4)		Japanese
Hibiki Koto	Vocaloid (6), Synthesizer V (Studio 1, 2)		Japanese* (SynthV, V6)
ROSA	CeVIO AI, Synthesizer V (Studio 1)	Sister of CUL.	Japanese
CUL	Vocaloid (3)	Unfortunate name.	Japanese
Lily	Vocaloid (2, 3)	Developed by Yamaha and Avex Inc., published by Internet Co. She fell off.	Japanese
kokone	Vocaloid (3)		Japanese
Chika	Vocaloid (3)		Japanese

KAMITSUBAKI STUDIO

The label consists of 'Virtual Isotope Phenomenon', the vocal synth characters, and 'Virtual Witch Phenomenon', the corresponding VTubers. Ordered by release date.

Character	Programs	Notes	Languages
KAFU	CeVIO AI	Voice from VTuber KAF. A Synthesizer V AI voicebank was planned, but was postponed in 2024 and canceled in 2025.	Japanese
SEKAI	CeVIO AI, VOICEPEAK	Voice from VTuber Isekaijoucho.	Japanese
RIME	CeVIO AI, VOICEPEAK	Voice from VTuber RIM.	Japanese
COKO	CeVIO AI, VOICEPEAK	Voice from VTuber KOKO.	Japanese
HARU	CeVIO AI, VOICEPEAK	Voice from VTuber Harusaruhi.	Japanese

TOKYO6 ENTERTAINMENT

Voicebanks are distributed by AHS.

Character	Programs	Notes	Languages
Koharu Rikka	Synthesizer V (Studio 1, 2 "Plus"), CeVIO AI, VoiSona, VOICEPEAK	The trio attend the same high school. Rikka has Synth V Standard and AI voicebanks (and a "Plus" for Studio 2).	Japanese* (SynthV)
Hanakuma Chifuyu	Synthesizer V (Studio 1), CeVIO AI, VoiSona, VOICEPEAK	Teto won me over but i'm waiting for the SV2	Japanese* (SynthV)
Natsuki Karin	Synthesizer V (Studio 1), CeVIO AI, VoiSona, VOICEPEAK	All 3 are confirmed to receive an upgrade in February 2026. Most known for being on SICK -やんでるEP- by ゆよゆっぺ, the track 'Datte' having a few million YouTube views.	Japanese* (SynthV)

SSS LLC. (Zunko)

Character	Programs	Notes	Languages
Tohoku Zunko	Voiceroid (+, +EX), Vocaloid (3, 4), Voidol, NEUTRINO, CeVIO AI, VoiSona, VOICEPEAK, VOICEVOX	She has a wikipedia page for her family. The three are named after the region.	Japanese
Tohoku Kiritan	UTAU, Voiceroid (+EX), Voidol, NEUTRINO, CeVIO AI, VoiSona, VOICEPEAK, Seiren Voice, VOICEVOX	Surname usually written either Tohoku, Touhoku, or Tōhoku, start pronounced similar to Touhou.	Japanese
Tohoku Itako	UTAU, Voiceroid (2), NEUTRINO, CeVIO AI, VoiSona, Seiren Voice, VOICEPEAK, VOICEVOX	The oldest of the three.	Japanese
Zundamon	UTAU, VOICEVOX, NEUTRINO, Seiren Voice, VOICEPEAK, CeVIO AI, VoiSona, Paravo, Voiceger	The creature-est. Themed after zunda-mochi. Certified genderfucky, and guinea pig for new platforms.	Japanese*
Shikoku Metan	UTAU, VOICEVOX, NEUTRINO, CeVIO AI, VoiSona	All characters are part of the anime musical 'Zunda Horizon'.	Japanese
Kyuushuu Sora	UTAU, VOICEVOX		Japanese
Chuugoku Usagi	UTAU, VOICEVOX		Japanese
Ooedo Chanko	UTAU, NEUTRINO, VOICEPEAK		Japanese
Chuubu Tsurugi	UTAU, VOICEVOX		Japanese
Kansai Shinobi	UTAU		Japanese
Hokkaido Meron	UTAU	Official website illustration shows she does have at least one melon.	Japanese
Okinawa Awamo	UTAU		Japanese
Ankomon	VOICEVOX	Huh? What? Since when?	Japanese

GPT-SoVITS is an open source project that got packaged up, renamed, and shipped with Zundamon, with a corresponding lecture video featuring said Zundamon, speaking in English, in a very suspicious tone describing it. The ethical matter of this kind of program being freely available is a Pandora's box that developers tend to open for fun.

First-party (Yamaha, Dreamtonics, etc)

A majority of Yamaha's voicebanks are either developed for other groups, or are talking heads optionally in silhouette. Few have defined characters. Dreamtonics' voicebanks have minimal cover art.

Character	Programs	Manager	Notes	Languages
asa	Vocaloid (Mobile, 6)	Yamaha	Mystery!	Japanese* (V6)
Po-uta	Vocaloid (6)	Yamaha	Porter Robinson. Has strict terms.	English* (V6)
Nurse Robot_Type T	UTAU, CoeFont, COEIROINK, VOICEVOX, Vocaloid (6), VoiSona	Yamaha	Originally an UTAUloid.	Japanese* (V6)
Kasukabe Tsumugi	Vocaloid (β, 6), VOICEVOX	Yamaha (Kasukabe Tsukushi)	Designed and voiced by the VTuber Kasukabe Tsukushi. More popular than her.	Japanese* (V6)
Mai	Synthesizer V (Studio 1, 2)	Dreamtonics	Included with Synthesizer V Studio.	Japanese* (SynthV)
Eleanor Forte	Synthesizer V (R1, Studio 1, 2 "Plus")	Dreamtonics	ENG-F1. Has a 'Plus' voicebank trained on the Standard files.	English* (SynthV)
Hǎiyī	UTAU, Synthesizer V (R1, Studio 1, 2 "Plus")	Dreamtonics	Private UTAU voicebank, derived to Synth V R1. Fun! Both Studio VBs in 2025.	Mandarin Chinese* (SynthV)
Yì Xī	Synthesizer V (Studio 1, 2)	Dreamtonics	Meat girl. ^q^	Mandarin Chinese* (SynthV)
Chis-A	VoiSona	Techno-Speech Ltd.	Main character of VoiSona.	Japanese
Utane Uta	UTAU	飴屋P?...	Included with UTAU. Derives from AquesTalk's Josei 1.	Japanese

Gynoid

Character	Programs	Notes	Languages
flower	Vocaloid (3, 4), own talk software, CeVIO AI, VoiSona, A.I.VOICE	Product as v flower or Ci flower. Every flower looks different.	Japanese
Meika Hime	Vocaloid (5), own talk software, A.I.VOICE (2, 1)	unspecified gender. Maybe enby! Maybe vagueposting. Sibling of Mikoto.	Japanese
Meika Mikoto	Vocaloid (5), own talk software, A.I.VOICE (2, 1)	unspecified gender. Maybe enby! Maybe vagueposting. Sibling of Hime.	Japanese
Xin Hua	Vocaloid (3, 4)		Mandarin Chinese, Japanese

Eclipsed Sounds

Character	Programs	Notes	Languages
SOLARIA	Synthesizer V (Studio 1, 2)	Themed after the sun. These four are Starry Court.	English* (SynthV)
ASTERIAN	Synthesizer V (Studio 1, 2)	Themed after the moon.	English* (SynthV)
SAROS	Synthesizer V (Studio 1, 2)	Nonbinary. Themed after stars.	English, Spanish* (SynthV)
NYL	Synthesizer V (Studio 1, 2)	Agender. Themed after void.	English* (SynthV)
HXVOC	Synthesizer V (Studio 2)	Mechanical arms. Adept at scream vocals.	English* (SynthV)
GALENAIA	Synthesizer V (Studio 2)	This set is Tone Chroma, and has worldbuilding.	Spanish* (SynthV)
REMMANT	Synthesizer V (Studio 2)	Old man. Dressed in more blue than KAITO.	English* (SynthV)

Other groups

Character	Programs	Manager	Notes	Languages
Kasane Teto	UTAU, Renoid, TALQu, Synthesizer V (Studio 1, 2), VOICEPEAK	TWINDRILL	Synthesizer V and VOICEPEAK distributed by AHS.	Japanese* (SynthV)
Akita Neru	Not really	Crypton Future Media	Derivative character. Adopted by CFM on 1st April 2008, and appears in Project Diva.	Japanese, usually
AVANNA	Vocaloid (3)	Zero-G Ltd.	Appears on two Porter Robinson songs. Also voices Yameii Online.	English
Adachi Rei	UTAU, A.I.VOICE (1), DiffSinger, Vocaloid (5)	Mechanical Girl LLC.	Robot girl with a synthetic voice. Exists in real life. VOCALOID5 in development.	Japanese* (Manual XLS)
Tsukomo Shion	UTAU	(missile_39)	Synthesis by the same author as Adachi Rei. Has a thousand-mile stare.	Japanese
IA	Vocaloid (3, 6), CeVIO Creative Studio, CeVIO AI, VoiSona	1st PLACE (IA PROJECT)	The first ARIA sister. Stylized as IA -ARIA ON THE PLANETES-	Japanese, English
OИE	CeVIO Creative Studio, CeVIO AI, VoiSona	1st PLACE (IA PROJECT)	The other ARIA sister. Stlyized as OИE -ARIA ON THE PLANETES-	Japanese
Luo Tianyi	Vocaloid (3, 4, 5), ACE Studio, X Studio	Vsinger (VOCALOID CHINA)	The first Chinese Vocaloid. X Studio is by Microsoft China, unrelated to ACE Studio.	Mandarin Chinese* (ACE)
Yuezheng Ling	Vocaloid (3, 5), ACE Studio	Vsinger (VOCALOID CHINA)	Very few characters are on Vocaloid 5. It's the CeVIO of Vocaloid.	Mandarin Chinese* (ACE)
Aoki Lapis	Vocaloid (3), CoeAvatar	i-style Project	CoeAvatar is unrelated to both CoeFont and COEIROINK. She has NFTs	Japanese
Rana	Vocaloid (3, 4)	We've Inc.	V3 uniquely distributed, with V4 mostly unchanged but regular sale.	Japanese
LUMi	Vocaloid (4)	Akatsuki Virtual Artists	Included for a page link. Your move.	Japanese
#kzn	CeVIO AI, VoiSona	(Kizuna AI)	Another VTuber voicebank, this time for Kizuna AI.	Japanese
Ui	VoiSona	(Shigure Ui)	SOMETHING'S WRONG	Japanese
Fukase	Vocaloid (4)	TOKYO FANTASY	Voiced by Fukase Satoshi of the band managed by that company.	Japanese, English
Namine Ritsu	UTAU, VOICEVOX, ACE Studio, and a whole buncha shit	Probably? Uhhhh...	A VIPPERloid like Kasane Teto, with weird canon details. 6 years old, 25 tons. Sure.	Japanese* (ACE)
Yokune Ruko	UTAU, TALQu, CoeFont, COEIROINK, DiffSinger, ACE Studio	Long Sleeper	Another VIPPERloid, a time-traveling 197cm 12-year-old, with split masc/fem voices like Rin/Len.	Japanese* (ACE)
BeMeebEth	Talkbox	Enad Global 7	i- what? huh- I- I don't think this counts?	???

Trivia

• Most of the program names listed are uppercase. This might be related to some Japanese input methods being based on western QWERTY layouts, and transcribing lowercase inputs to kana or kanji as typed/selected, but keeping capital letters as they are.
• Despite the common mentions of AI, generated imagery or backing instrumentals are not looked kindly upon. In voicebanks, it is purely a technological advancement, with usually lower storage cost and higher fidelity at the cost of compute.
• Many early characters have the kanji 音ne in their name, meaning sound; Hatsune Miku, Kagamine Rin and Len, Megurine Luka, Kasane Teto, Momone Momo, the Macne series, Utane Uta, and many more UTAUloids.
• There is a third ARIA sister named HIPPI. The only sources are a few illustrations and official 1st PLACE social media.
• If you're getting into vocal synth, if you don't have fluent Japanese your best bet is UTAU or Synthesizer V. Vocaloid has a lot of big names, but is like double the price of Synth V Studio. It does come with Vocalo Changer supporting Vocaloid:AI voicebanks though, whereas Dreamtonics sells their own separately.
• There are many VTuber/vocal synth connections, from the whole split cast of KAMITSUBAKI STUDIO, to Kizuna AI, Shigure Ui, and even Chihiro Ishiguro as Yuzuki Yukari Μμ, a parallel universe Yukari.
• Vocaloid 4 had a cross-synthesis feature allowing blending between voicebanks, whether different Appends or fully distinct voices. This didn't carry over to later versions, and the closest thing since is Synth V's Vocal Modes. Most featuring songs used it like that, with fewer between different characters; the most common of the latter being hacked cross-synthesis between Kagamine Rin and flower to voice Akita Neru.

• The screenshot of Synthesizer V has a full description.
• Battle for Dream Island is also Vocaloid.