Dreamtonics Co., Ltd.

Dreamtonics Co., Ltd. (ドリームトニクス) is a compact, multi-lingual team of experienced engineers and music lovers from Tokyo, Japan and are responsible for the development of the Synthesizer V and Synthesizer V Studio voice synthesis software.

According to their official website, rather than building their product on top of conventional patterns, Dreamtonics began with a realization that music software could be made much better if given a deeper thought about how users would actually use the software.

Dreamtonics notes that independence, patience and dedication are what it takes to make a difference. As they are a small team, Dreamtonics's goal is to tackle problems that large corporates can't efficiently solve and iterate rapidly on ideas and develop them into usable products.

They noted that while many startups place product launch and growth in the top priority, they are under the belief that "things" work the other way around. Dreamtonics states that they prefer taking reasonable risks and building quality software over rushing to the finish line. This philosophy combined with the latest software engineering practices is what has guided them towards a long-term success: a line up of high quality products everyone likes.^[1]

History[]

Synthesizer V[]

Dreamtonics was first formed in February 2019 by software engineer Kanru Hua. Dreamtonics released their first version of Synthesizer V on August 19, 2018 as a Technical Preview and the full Production Release, released on December 24 in the same year. Together in collaboration with AH-Software Co. Ltd., Dreamtonics Co., Ltd. would release the upgraded version of Synthesizer V known as Synthesizer V Studio on July 10, 2020. AH-Software's store acted as a general storefront for the Japanese market and distributed not only their own vocals and usual partners, but also Saki, Dreamtonics's first new vocal for the Synthesizer V Studio software and later the first Synthesizer V AI voice database. They later assisted in distributing more Dreamtonics vocals (except Qing Su) as of February 2022.

On November 20, after the release of Synthesizer V Studio 1.4.0, Dreamtonics also opened their own Taobao store as part of their updated sales model for the Chinese market and pre-orders for Qing Su, their first Chinese AI voice database, were hosted there. Regarding overseas users, she would be available through other means, but the details were not yet specified.^[2] This was later revealed to be the official Dreamtonics international store, which was opened on February 4, 2022, along with the release of their new vocals Ryo and Kevin.^[3]

On June 13, 2022, Dreamtonics announced that they launched a new official store for the Chinese market built on WeChat's Mini Program. Users would be able to purchase the Synthesizer V Studio Pro editor and Dreamtonics' vocals through the application in a convenient manner, enjoying the automatic real-time distribution shopping experience. From June 13 to July 13, users were able to take advantage of unlimited 10% off coupons in the new store.^[4] It was later clarified that the decision to open this new shopping option was made due to Taobao's new restrictions on the sales of virtual goods as of April 2022, especially for restrictions on shipments without logistics since virtual goods would need to be delivered via email.^[5] Due to popular demand, the international store later supported payments via Paypal on September 16.^[6]

VOICEPEAK[]

On September 18, 2021, Dreamtonics revealed that they were working on a text-to-speech synthesizer that was described to be "ultra-realistic".^[7]

On February 17, 2022, this was revealed to be "VOICEPEAK" (also stylized as "voicepeak" or "VOICE PEAK"), which was developed in collaboration with AH-Software.^[8] According to AH-Software's product page, VOICEPEAK was equipped with the high-quality AI speech synthesis engine "Syllaflow", which was developed by Dreamtonics.^[9] A trial version of VOICEPEAK, along with one male and one female voice, was released on the same day, with the commercial version set to release for Windows, MacOS, and Linux on March 11 with four females and three males.^[10]

On August 11, Dreamtonics teased that new Chinese speech voices were expected to debut the next day, but did not state the engine.^[11] On August 12, this was confirmed to be VOICEPEAK and four voices were shown: an adult female, an adult male, a middle-aged or elderly male, and a young female. They were shown to speak with different moods and tones. A release date had not been announced, but more demos were to be expected.^[12]

For more information about VOICEPEAK and its compatible voice databases, see Vocal Synthesizer Wiki.

Synthesizer V AI Gold Series[]

On June 17, 2022, Dreamtonics announced a new series of voice databases for Synthesizer V Studio dubbed the Synthesizer V AI Gold Series. Described as "a culmination of arts and artificial intelligence", the Synthesizer V AI Gold Series defines itself as the ultimate sound quality for synthesized vocals, adhering to the highest-ever standard of production. Dreamtonics plans to collaborate with top-tier vocalists, producers and seasoned staff in China, pushing the specifications to the limits, with the sole goal of creating the perfect voice synthesizer for serious music production. The first voice database launched under the Synthesizer V AI Gold Series, Weina, voiced and directed by Chinese actress and professional singer-songwriter Weina Hu, was announced the same day to be produced in collaboration with Ready Steady Sound! and Sound & Vision Media Studio to be released in July 2022.

It was noted that the Gold Series had no impact on the functionalities of Synthesizer V voice libraries nor the editor itself.^[13]

Key people[]

Kanru Hua (华侃如; Huá Kǎnrú, written in Japanese as フアカンル Fua Kanru) is a software engineer born in Shandong, China but currently living in Tokyo, Japan. He is the founder and Representative Director of Dreamtonics and is the creator of the Synthesizer V and Synthesizer V Studio voice synthesis applications. He is a graduate of University of Illinois Urbana-Champaign.

In an interview with vocaloidnews.net (VNN), it was revealed that Kanru first thought of the idea for Synthesizer V in 2015 using inspiration from previous work on the Sinsy voice synthesis engine and the UTAU resampling program Moresampler. He released the first generation of Synthesizer V in December 2018.^[14]

LinkedIn
SoundCloud (@kanru-hua)
Twitter (@khuasw)
YouTube (@kanruhua504)

Tomohide Ogata (尾形友秀; Ogata Tomohide) was appointed Director of Dreamtonics by Kanru Hua on June 30, 2022, as part of the deal where Kanru became the new President and Chief Technology Officer (CTO) of AH-Software Co. Ltd..^[15]