Mai

Mai
Character information
Gender	Female
Pronouns	She/Her
Technical information
Type	Synthesizer V AI
Language	Japanese
Release date	November 10, 2022
Company	Dreamtonics Co., Ltd.

Mai is a Japanese vocal developed and distributed by Dreamtonics Co., Ltd., and released as an AI voice database for Synthesizer V Studio in November 2022.

Her voice provider is Honoka Kitta.

Concept

Like previous Dreamtonics vocals before her, Mai was intended to be treated as an official voice database or an indispensable "reference-level" type of singing voice, representing Dreamtonics's brand quality.

Mai was designed to have "crisp pop singing vocals" suitable for J-Pop, Dance, and Idol styles of music. The characteristics of her voice is retained throughout her range, allowing her to keep "the vibe of the song" undisturbed whenever she changes keys.

Etymology

No official information was released regarding why the name "Mai" was chosen or what the name may mean.

Appearance

Like previous Dreamtonics vocals, rather than having an official human-like avatar, Mai is represented by an abstract symbol, the letters M and A, which are drawn from the first two letters of her name. The letters are light yellow in color with hints of magenta. The top of the M's arches are flat rather than pointed. The "A" is shorter than the "M" and is more of a box-shape rather than pointed. Characterization is left to the song producers themselves rather than the product, so Mai is open to any form of visual interpretation, allowing the producer to decide what they would like her to look like.

History

On October 27, 2022, Dreamtonics announced a new feminine Japanese voice database known as Mai and released one demo for her debut with a brief description of her voice database. The editor in the demo's PV also revealed that Mai had at least two Vocal Modes: "Emotional" and "Soft". A release date had yet to be announced at the time.

On November 10, Synthesizer V Studio 1.8.0b1 was officially released, which introduced some new features such as Diffusion Probabilistic Models (DPM), MIDI and Metronome support, and Note-level cross-lingual synthesis. In addition, it was announced that Mai was released as a free vocal for all Synthesizer V Studio Pro users, with Dreamtonics cautioning that the 1.8.0b1 editor and later editions were necessary to use her voice database as she would not work with older versions. There was no expiration for her free distribution. Through an interview with DTM Station, Kanru Hua explained that Synthesizer V Studio Basic and Lite versions of certain voice databases were released so users could experience it for free with limited functions. On the other hand, upon purchasing Synthesizer V Studio Pro, there weren't options like this for full voice databases, leading to the free distribution of Mai so users could experience the fun and wonders of AI singing voice synthesis.

Marketing

Like previous Dreamtonics vocals, Mai was treated as an official or standard vocal for the engine, where she could potentially be found in demonstrations of Synthesizer V Studio and its AI capabilities. This also meant that she would be among the first vocals to be equipped with the latest engine updates. Mai was the focal voice of marketing Synthesizer V Studio 1.8.0, which introduced Diffusion Probabilistic Models (DPM), MIDI keyboard and Metronome support, and Note-level cross-lingual synthesis. She was featured in the introduction video for the 1.8.0 update, specifically the sections that featured MIDI keyboard and Metronome support and the Note-level cross-lingual synthesis function (with the YouTube version featuring her in English and the bilibili version featuring her in Mandarin Chinese).

On November 10, 2022, Mai was released as a free vocal for all Synthesizer V Studio Pro users, a first for the Dreamtonics full voice database line-up. Through an interview with DTM Station, Kanru Hua explained that Synthesizer V Studio Basic and Lite versions of certain voice databases were released so users could experience it for free with limited functions. On the other hand, upon purchasing Synthesizer V Studio Pro, there weren't options like this for full voice databases, leading to the free distribution of Mai so users could experience the fun and wonders of AI singing voice synthesis.

Voicebanks

• Mai AI (Synthesizer V Studio), November 10, 2022

Reputation

Reaction

As a vocalist without an official character, this allowed producers and fans to create their own for Mai, resulting in a variety of designs. On November 2, 2022, Mai was featured in a DTM Station article written by Ken Fujimoto, where she was praised for having a smooth and intuitive voice, noting that Synthesizer V had evolved to a level where the voice could no longer be distinguished from live human singing. She was said to have a very natural falsetto in her high range and her breathing was noted to be realistic. Dreamtonics noted that Mai was warmly received in the Japanese market, particularly after Ken Fujimoto's article was published.

Impact

As a Dreamtonics product to demonstrate the capabilities of Synthesizer V Studio (specifically Synthesizer V AI), Mai was considered to be one of the default or reference vocals used for tech demos, allowing for producers to compare and understand the differences per update. She had a professional feel and made for a good starting AI voice database, which was especially praised for sounding realistic and helped gauge interest in this type of voice database for Synthesizer V as a whole.

Achievements

• First full Synthesizer V AI voice database to be released for free.

External links

Articles

• Synthesizer V Wiki
• VocaDB