Dreamtonics Unveils Synthesizer V Studio 2, The Next Evolution in Vocal Synthesis 

AI-Powered Synthetic Vocal Instrument available for pre-order now.

Dreamtonics, the leading music and voice technology company based in Tokyo, has an upcoming release of Synthesizer V Studio 2—the AI-powered virtual instrument that allows songwriters to generate and sculpt rich vocal tracks by simply sketching out a melody, writing lyrics, choosing a voice, and customizing expressions. Synthesizer V Studio 2 is available now for pre-order and will officially launch March 21. This latest version of Synthesizer V is faster and creates more powerful, realistic vocal tracks than ever before.

To create a vocal track using Synthesizer V, users type their lyrics, use the piano roll interface to input their desired melody, and select the virtual singer they want to perform it. Synthesizer V brought users powerful voice sculpting tools for creating vocal tracks full of character. Now, Synthesizer V Studio 2 takes the evolution of voice synthesis a step further—making it more natural and human-like than ever before. Thanks to improved algorithm design and enhanced multi-threading support, Synthesizer V Studio 2 renders up to 300% faster than its predecessor. This speed boost is achieved without requiring a dedicated GPU or acceleration hardware, allowing for seamless offline use.

Even the most talented human singers aren’t perfect, so Synthesizer V Studio 2 allows users to randomize timing and pitch in varying degrees. With AI-assisted editing, take fluid control over the vocal register, and even the mouth-opening parameter which significantly affects a singer’s pronunciation and tone. 

Along with these milestone updates to the editing interface and synthesizing technology, Synthesizer V Studio 2 will introduce new vocal packs to the platform’s growing library.

“In testing, the vocals generated by the Synthesizer V actually received the same naturalness reading as real human vocals—a very exciting milestone for voice synthesis,” explains Dreamtonics founder and CEO Kanru Hua. “While J-Pop artists have used voice synthesis tools like this for some time now, most Western have yet to discover it. Dreamtonics is proud to finally unveil the Synthesizer V Studio 2 and introduce endless inspiration and fun to more people’s music creation process.”

Synthesizer V Studio 2 is available now for pre-order and will officially launch March 21.

About Dreamtonics

Dreamtonics is a Tokyo-based startup specializing in electronic music and voice technology. We build and provide the best music software to meet your creative needs. For corporate customers, we also provide services such as technology licensing and artificial voice creation. Dreamtonics develops and sells its flagship Synthesizer V software as well as the Vocoflex plug-in directly at https://www.dreamtonics.com. 

Japan's Leading Singer-Songwriter Yumi Matsutoya Transcends Time with Help From Dreamtonics

Matsutoya leaned on Dreamtonics’ Synthesizer V to create her "Chrono Recording System,” the secret power behind her new release.

Japanese music icon Yumi Matsutoya's 40th original album is a musical message to the future. In her latest collection of songs, Matsutoya confronts an eternal theme—“What is time?"—head-on. She explores this question via the newly introduced cutting-edge "Chrono Recording System,” an original technology created specifically for this album.

This system uses Japanese startup Dreamtonic’s voice synthesis software Synthesizer V to synthesize the voice of Yumi Arai, the voice that resounded on Matsutoya’s first hits, and weave it together with the vocals of Yumi Matsutoya today, creating a new "voice" that transcends time. It delivers a new dimension of musical experience to listeners, as if Yumi of the past and present were singing in the same space. 

Half a century after her debut, Yumi Matsutoya continues to expand the possibilities of music. Yumi Matsutoya's story of "time" enters a new phase by embracing technology that suited her unique artistic vision.

“As we began working on the new album, I learned about the existence of a software called Synthesizer V developed by Dreamtonics,” explains Masataka Matsutoya, Yumi’s producer. “We were convinced that we could make an interesting album by successfully coexisting the voices we created with current voices, so we named Synthesizer V and our production process the Chrono Recording System. It's like recording sound beyond time. Anyone who listens to it can hear the old Yumi, yet the results are strikingly new.” Matsutoya reflects on the project’s creative and technological origins more in an eloquent statement, accessible in full here.

"Dreamtonics is honored to participate in this amazing project by Masataka Matsutoya with the Chrono Recording System," said Kanru Hua, CEO of Dreamtonics. "Our efforts to push the boundaries of vocal synthesis reflect Japan's approach to integrating advanced technology with culture and the arts.”

About Synthesizer V

"Synthesizer V" is a singing voice synthesis software developed by Dreamtonics Inc. that is equipped with a powerful voice processing engine and allows you to easily create high-quality, natural singing voices. Simply draw a melody and record lyrics to easily create your own original song.

The Synthesizer V Studio Pro editor for the Synthesizer V series features a vocal style function that allows you to change the tone of your voice to suit the song or scene, an AI retake function that allows you to adjust the pitch and tone of your voice with the touch of a button, a rap vocals function that reproduces rap-specific expressions, and a multilingual singing function that allows you to sing in English, Chinese, Cantonese, Spanish, and more. It can handle any musical style and make you sing like a real singer down to the last detail.

About Yumi Matsutoya

Yumi Matsutoya is Japan's leading singer-songwriter, lyricist, and composer. Commonly known as Yumin, Matsutoya was born January 19, 1954 in Tokyo. In 1972, while enrolled at Tama Art University, she debuted under her maiden name, Yumi Arai, with the single "I Don't Need an Answer". The following year, in 1973, she released her first album, "Hikoukigumo".

With highly fashionable melodies and unique realistic lyrics that set her apart from previous folk songs, she became a pioneer among female singer-songwriters. As well as being an artist who has produced innovative stage design, she has also provided many songs to other artists under her real name as well as under the name Karuho Kureta.

Her representative works include "Graduation Photo", "I Want to Protect You", "Refrain is Screaming", "Hello, my friend", "Haru yo, Koi", and many others. Currently, over 400 songs are available for download. On July 5, 2022, she celebrated her 50th anniversary since her debut. In the same year, she became the first artist in history to reach No. 1 on the album charts in the 60s. In 2023, this record was registered in the Guinness Book of World Records. She continues to be active as one of Japan's leading female artists in both name and reality. She has released 39 original albums to date, with total sales of over 30 million copies.

2013: Awarded the Purple Ribbon Medal and the Tokiko Iwatani Award
2018: Awarded the Kikuchi Kan Award
2022: Selected as a Person of Cultural Merit

JAPANESE ORIGINAL 

【日本を代表するシンガーソングライター・松任谷由実、最新アルバムで“時間”に挑む──新技術「Chrono Recording System」を導入】

オリジナル40作品目となるオリジナルアルバムは、ユーミンからの未来への音楽のメッセージ

松任谷由実が、最新アルバムにおいて自身の永遠のテーマである“時間とは何か？”に真正面から向き合う。
その鍵となるのが、新たに導入した最先端技術「Chrono Recording System」だ。今回のアルバムの為に命名されたオリジナルの技術である。
このシステムは、音声合成ソフト「Synthesizer V」を用いて、荒井由実時代の声と現在の松任谷由実のヴォーカルを合成し、時間を超越した新たな“声”を創り出す革新的な技術。まるで過去と現在のユーミンが同じ空間で歌うような、新次元の音楽体験をリスナーに届ける。
デビューから半世紀を迎えた今も、音楽の可能性を広げ続ける松任谷由実。ユーミンが紡ぐ“時間”の物語は、新たなフェーズへと突入する。

▶︎松任谷由実プロフィール

日本を代表するシンガーソングライター、作詞家、作曲家。通称ユーミン。

1954年1月19日、東京都出身。

72年、多摩美術大学在籍中にシングル「返事はいらない」で旧姓・荒井由実としてデビュー。

翌、73年、ファースト・アルバム「ひこうき雲」をリリース。

それまでのフォークソングとは一線を画する、ファッション性の高いメロディと独自の写実的な歌詞で、女性シンガー・ソングライターの草分け的な存在に。

革新的なステージを生み出してきたアーティストであると同時に、本名だけでなく呉田軽穂名義で他のアーティストにも多数の楽曲を提供。

自身の代表作には「卒業写真」「守ってあげたい」「リフレインが叫んでる」「Hello,my friend」「春よ、来い」他多数。現在、400曲を超える楽曲を配信中。2022年7月5日に、デビュー50周年を迎えた。

同年、史上初6年代でアルバム1位を獲得。2023年この記録がギネス登録された。名実共に日本を代表する女性アーティストとして活躍を続けている。これまでに39枚のオリジナルアルバムをリリースし、総売上枚数は3,000万枚以上。

2013年　紫綬褒章、岩谷時子賞受賞

2018年　菊池寛賞受賞

2022年　文化功労者に選出

▶︎本プロジェクトについての、松任谷正隆（ユーミンプロデューサー）からのメッセージ

“我々の求めているもの”

あれはほんの４－５年前のことでしょうか。スタッフが倉庫から未発表曲の入ったマルチテープを持ってきたことから始まりました。５０年も続けていれば未発表曲もそれなりにあります。その曲はどうやら７０年代の終わりか、８０年代初めのものらしいことが、スタジオのデータとかミュージシャンの声から分かりました。ところが作曲した由実さんも、編曲した僕自身もほぼ記憶にない。確かに由実さんらしい曲だし、僕らしい音なので、それは間違いないのだけれど、こんな曲あったっけ・・・なんてみんなで顔を見合わせたのを覚えています。

聴いているうちに、この７０年代だか８０年代の音が妙に新鮮で、現代では絶対に再現出来ないことが肌で感じられてきました。しかも「ラララ」で仮歌を歌っている由実さんの声もずいぶん若くて高い。このオケは使いたくてもキーが高くて今では無理、再び倉庫行きか、なんて諦めかけていた頃、某国立大学に、声をサンプリングしてメロディにする研究をするチームがあることを知りました。AIなどという言葉が今みたいに普通ではない時代だったので（たった数年前のことなのに！）、それがどういうことなのか理解出来ず、でもどうなるのかやってみたい、という気持ちから、昔の由実さんの声をサンプリングして新しいメロディに作り替えられないか、という打診をし、やってみよう、という返事をもらったのです。

試行錯誤の末に出来上がったものは、まだまだ僕がイメージしたものとはほど遠く、似ていなくもない、程度のものだったでしょうか。でもこれを部分的に使って、昔の自分に会いに行く、というテーマの作品にしました。Call me backという曲です。そう、これが全ての始まりでした。

それからほんの数年後、Dreamtonics社が開発する“Synthesizer V”というソフトウェアの存在を知りました。あの頃某国立大学が挑んでいた研究は、この短い時間でのテクノロジーの発達ゆえか、それとも技術者の才能ゆえか、天文学的な発達を遂げていました。誰が聴いても昔の由実さんがそこにありました。

僕はもやもやしながらも、これは使える。と、どこかで思ったのです。

技術の発達のスピードは凄まじいものがあります。そしてそれを受け取る我々の方も、そのスピードにある程度慣らされてしまいます。AIがディープラーニングをし、考え、あっという間にポロンとアウトプットしていく。こんな夢みたいなことは今や常識。リポート作成も、作文も作曲も、AIに任せればなんでも出来るし、それなりの形にしてしまう。いや、それなりどころではない。傑作が生まれるのも時間の問題でしょう。今はそんな時代。そして誰もがそれを受け入れている時代。

そんな中で、今一度”Synthesizer V”の意義について考えました。もしこれを普通に使ったら、由実さんは歌うのを諦めて、イージーにAIで済まそうとしている、などと言われるでしょう。ついに声の出なくなった由実さんはAIに頼った、みたいな。

それはないな・・・と思いました。この究極的なテクノロジーは、作品作りの初めから生かさないと意味も意義もない、と。

そして、当然のことながら、これまで通りの由実さんの歌がメインにならないとアルバムとしての価値はない、と。

こうして辿り着いたのがワームホールという考え方でした。実際にあるかどうかも分からないワームホール。でも、もしあるとすれば過去と今を行き来出来ると言われます。この考えを心のどこかに置きながら曲を作り、音を作り、そして詞を作れば、

”Synthesizer V”との共存は出来るはず。

作った声と今の声とをうまく共存させて面白いアルバムが作れるはず、という確証を持ち、Synthesizer Vと我々の制作プロセスを「Chrono Recording System」と名付けました。時間を超えて音を記録するイメージです。

考えてみれば７０年代後半から８０年代というのは、生楽器の中に少しずつ、シンセサイザーが楽器として忍び込んでいった時代でした。そして気がつくとテクノサウンドあたりからはシンセサイザーが表舞台に立っていった。

もしもそれをこのAIテクノロジーで例えるなら、Synthesizer Vをはじめとするボーカルシンセサイザーなどが当てはまるのかもしれません。

その後のテクノサウンドはどうなっていったか、と言えば、それは形を変えながら静かに今の音楽にまで染みこんでいった、と言えるでしょう。まるでウイルスのように。

そこには変わらず進化を求める音楽そのものの姿があります。

誰にでもインスタントに音楽が作れる時代。

それだからこそ、最新のテクノロジーと共存するためには、その原点となる発想と共存出来なければ我々には意味がない、というのが僕の、少なくともたった今の結論です。

松任谷正隆

「Dreamtonics は、松任谷正隆 氏によるこの素晴らしいプロジェクトに“Chrono Recording System”参加できることを光栄に思います」と Dreamtonics の CEO、Kanru Hua 氏は述べています。 「音楽におけるAIの限界を押し広げるという私たちの取り組みは、文化と芸術に先進テクノロジーを統合するという日本のアプローチを反映しています。

Synthesizer Vについて

「Synthesizer V」は強力な音声処理エンジンを搭載し、ハイクオリティで自然な歌声を簡単に作ることができるDreamtonics株式会社が開発した歌声合成ソフトウェアです。メロディーを描き歌詞を吹き込むだけで、簡単にオリジナルソングを制作できます。

Synthesizer Vシリーズのエディター「Synthesizer V Studio Pro」では、楽曲やシーンに合わせて声色を変化させられる「ボーカルスタイル機能」、ボタン一つで歌声のピッチや声色を調整できる「AIリテイク機能」、ラップ特有の表現を再現する「ラップ歌唱機能」、さらに英語、中国語、広東語、スペイン語などで歌唱できる「多言語歌唱機能」も搭載。

どんな音楽スタイルにも対応し、細部まで本物の歌手のように歌わせることができます。 

Dreamtonics（ドリームトニクス）について

Dreamtonics株式会社は2019年に設立された東京を活動拠点とするベンチャー企業です。
経験豊かなエンジニア達による小規模でマルチリンガルなチームが、電子音楽と音声技術に特化した製品開発を行っています。
「ユーザーがよりスムーズで快適に操作ができる音楽制作ソフトを創りたい」という想いのもと、お客様の創造性を支える高品質なソフトフェアを構築・提供してまいります。

Dreamtonics Launches Two New Voices for Synthesizer V

Empowering creators to experiment with different vocal textures and tones in their music

Dreamtonics has launched two new voices for Synthesizer V, the company’s flagship voice synthesis instrument that allows songwriters to generate and sculpt rich, realistic vocals in seconds. Dreamtonics users can now channel the powerful operatic female tones of Felicia or the crisp sensitive sound of Riku in their music.

Synthesizer V combines an intuitive and flexible user interface with a powerful singing synthesis engine and cutting-edge technologies. Users can easily create realistic-sounding vocal covers or original songs by simply sketching out a melody and filling in the lyrics. 

Dreamtonics continues building a collection of voices, and the Riku and Felicia vocal packs further expand the library to cover new genres and sounds. AI Felicia’s powerfully classic and self-confident voice is an ideal choice for opera, classical, and even metal music. Meanwhile, AI Riku’s warm whispery vocals are a perfect match for low-tempo, emotional pop or soul. 

Composer, songwriter, and producer Nick Trepka wrote and recorded his demo “Show Me” using the Synthesizer V and the Felicia voice: “It sounded extremely natural and emotive straight away,” says Trepka. “I realized during this project that a lot of my feelings toward AI were about just not understanding what that interface would look like between the technology and the producer or writer. So to get an idea of how I would actually use this tool—and to see it just as a tool—was very enlightening and gave me another perspective on AI in general.”

“For some time, J-Pop artists have used tools like Synthesizer V to broaden their creative possibilities and introduce new voices or characters in their music,” says Kanru Hua, founder and CEO of Dreamtonics. “Voice synthesis is a powerful creative tool that many Western creators have yet to discover. Dreamtonics hopes to introduce them to these technologies and inject fun and a new source of inspiration into their music creation process.”  

The addition of Riku and Felicia voice packs closely follows on the curtails of another big announcement from Dreamtonics. Earlier this year, the company launched a second voice synthesis tool, the Vocoflex—a plug-in that allows singers to transform their voices with minimal latency. Using Vocoflex, users morph cutting-edge technology that reduces latency, the Vocoflex plug-in enables artists to morph multiple voices together to create backing vocals, record vocal ideas and demos, and experiment with voice extrapolation.

All Dreamtonics voice models are fairly trained in partnership with professional singers who are fairly compensated for their work.

About Dreamtonics

Dreamtonics is a Tokyo-based startup specializing in electronic music and voice technology. We build and provide the best music software to meet your creative needs. For corporate customers, we also provide services such as technology licensing and artificial voice creation. Dreamtonics develops and sells its flagship Synthesizer V software as well as the Vocoflex plug-in directly at https://www.dreamtonics.com. 

Trailblazing Tokyo-based music tech start-up Dreamtonics, is excited to announce the full release of Vocoflex, its real-time, AI-powered voice creation and transformation plugin. Equipping creators with three bundles combining Vocoflex, their flagship Synthesizer V Studio Pro, and a variety of realistic-sounding voice databases, Dreamtonics provides state-of-the-art AI-powered voice synthesis tools to the community while prioritizing their ethical development and use. 

“Singing voice conversion (SVC) technology has been around for a few years now. As a technical person, I am genuinely excited by the technical advances, but at the same time feeling disappointed and betrayed that more often than not, it’s only used to create (often ethically questionable) covers, and fails to produce anything original or make a lasting, positive influence on modern-day culture,” admits Kanru Hua, CEO of Dreamtonics. “This untapped potential is why soon after releasing Synthesizer V, we decided to move toward the SVC space.”

While Synthesizer V originated from Vocaloid culture in Japan, it has gained mainstream adoption. In a similar way, Dreamtonics counts on its next product Vocoflex to bring ethical SVC to the creative masses. 

Using some clever statistical tricks to map multiple voice characteristics onto a 2D space, the Dreamtonics team found a way to interpolate between multiple models to create entirely new voices. Reducing the latency of the rendering unlocked real-time voice conversion. Like simultaneously DJing and singing a karaoke duet, a single performer can tap into several voices during one live performance using Vocoflex. For a more tactile experience, Vocoflex even allows users to connect and map their MIDI controller’s buttons, knobs, or sliders to adjust their voice. 

While Vocoflex and all associated bundles are designed for creative applications, Dreamtonics understands the potential risks and ethical implications of its use beyond these intended purposes. The voice morphing tool allows users to train their own AI voice models with as little as 10 seconds of source audio and operate the model on their own local computer—drastically reducing the time it takes to render new voices and effects. To prevent unauthorized usage of such a powerful tool, Vocoflex requires ID verification through Dreamtonics’ KYC-service partner and incorporates an advanced tamper-proof audio watermarking feature. Undetectable to the ear, this watermark embeds a user-unique license ID into the voice, enabling Dreamtonics to identify both the use of Vocoflex and the creator of the audio sample, deterring users from importing voice samples without the singer or users consent—a practice prohibited by their usage terms.

“Dreamtronics adheres to ethical AI usage, never blurring any moral and legal boundaries, and encourages users to use Vocoflex to expand their creative possibilities with the artist’s, actor’s, vocalist’s or user’s full knowledge and transparency,” says Kanru Hua, CEO of Dreamtonics. “Singing Voice Conversion deserves a revolution, a release of creativity, a wave of inspiration that will change the course of music and vocal production, and we are proud to be standing at the forefront.”

About Dreamtonics

Dreamtonics is a Tokyo-based startup specializing in electronic music and voice technology. We build and provide the best music software to meet your creativity needs. For corporate customers, we also provide services such as technology licensing and artificial voice creation. Dreamtonics develops and sells Vocoflex software directly at https://www.dreamtonics.com. Vocoflex is a registered trademark of Dreamtonics.