Mai 2

Mai	SynthV Studio	SynthV Studio 2	|	Originals	|	Gallery

Mai 2
Product Information
Company	Dreamtonics Co., Ltd.
Release Date(s)	March 21, 2025
Status	Released
System Requirements	Windows, MacOS
Base Language(s)	Japanese
Type	Synthesizer V Studio 2
Licensing	Proprietary
Affiliations	AH-Software Co. Ltd.
Product Page	Digital copies: AHS Store AHS Store (Starter Pack) AHS Store (Starter Pack; user discount) Dreamtonics (International) Dreamtonics (Intl.) (Upgrade) Dreamtonics (Intl.) (Bundle Set) Dreamtonics (Mainland China) Dreamtonics (Mainland China) Dreamtonics (China) (Upgrade) Dreamtonics (China) (Upgrade)

This article is about the Synthesizer V Studio 2 software known as a voice database. If you are looking for the Synthesizer V concept then click here.

History

On January 23, 2025, Dreamtonics Co., Ltd. kicked off its participation in the annual NAMM Show, held at the Anaheim Convention Center until the 25th. For people who were unable to attend NAMM 2025 in person, Dreamtonics prepared an exclusive preview video where Kanru Hua showed off a preliminary build of Synthesizer V Studio 2. On January 24, a press release conducted by DTM STATION was released, confirming Mai 2 among other announced voice databases.

On February 13, Dreamtonics opened pre-orders for Synthesizer V Studio 2 Pro on its international store, with release date set to March 21. Buyers of SVS2 Pro would be allowed to select for free (upon release) either Mai 2 or one of two brand-new voice databases, Liam or Mo Xu. Otherwise, she would need to be purchased separately if not chosen as the complimentary voice database.

On March 21, Mai 2 was released alongside Synthesizer V Studio 2 and according to her product page, she was completely re-recorded to add more Vocal Modes. This version of Mai consists of six Vocal Modes: "Breathy", "Downer", "Emotional", "Powerful", "Rap", and "Sweet".

On or around August 23, Mai 2, Liam, and Mo Xu were made available as separate purchases on AH-Software Co. Ltd.'s AHS Store.

Updates

Mai 2 v201b1 - June 18, 2025 

A closed-beta update for Mai 2 was issued one day after the release of Synthesizer V Studio 2 version 2.1.0. This update focused on enhancing her pronunciation and pitch accuracy, and was reported to make improvements to her Cross-lingual Singing Synthesis.

• To obtain this and other closed-beta updates, interested users needed to apply to join the Dreamtonics voice beta testing program by filling out the signup form given on the Dreamtonics Users Forum, which was opened on June 18 and closed on or around June 21. Users whose applications were approved were informed via email, and they received access to the beta updates for Dreamtonics voice databases currently owned by them or under a free trial.
• To install, open the Product Manager in Synthesizer V Studio 2 Pro and click "Update" for each Dreamtonics voice (including but not limited to Mai 2).
• User feedback is crucial for the Dreamtonics Team to identify and address any issues and to determine whether to release this beta version. The Team asks beta testers to use a feedback form linked on the same approval email message to provide feedback on version 201b1.

Mai 2 v201b2 - July 2, 2025 (withdrawn) 

Another closed-beta update for Mai 2 was issued to beta testers who had been accepted into the Dreamtonics voice beta testing program. This version claimed to include further improvements to sound quality and address some of the pitch issues reported by 201b1 beta users.

• Although this update was able to be installed during the first few hours upon issued, it was withdrawn by Dreamtonics the same day after beta testers reported problems in general with the 201b2 updates for several other Dreamtonics voice databases, ranging from quality degradation for some vocals to download failure for other vocals.
• The Dreamtonics Team "identified an issue causing file corruption on some voices when uploading version 201b2 to the server" and kindly asked testers "to refrain from further testing as we are working on version 201b3 which will become available later this week." 201b3 was issued the next day to remedy this.

Mai 2 v201b3 - July 3, 2025 

This closed-beta update for Mai 2 was issued to approved beta testers to fix the file-corruption issue plaguing the day prior's withdrawn 201b2 update that led to reports of quality degradation. This update includes the sound quality improvements and pitch issue fixes that were originally intended by 201b2.

• The feedback form originally supplied for 201b2 was repurposed for providing valuable feedback on 201b3.

Mai 2 v201b4 - July 11, 2025 

This closed-beta update for Mai 2 was issued to approved beta testers to resolve quality degradation issues reported between 201b1 and 201b3.

• The feedback form originally supplied for 201b2 and 201b3 was again repurposed for providing valuable feedback on 201b4.

Mai 2 v201 - July 23, 2025 

A free update for Mai 2 was released following the Synthesizer V Studio 2 Pro 2.1.1 update. This update focuses on enhancing the pronunciation and sound quality, becoming available after extensive beta testing sessions where participating users tried out her research prototype and offered valuable feedback.

• v201 beta testers recognized improved pitch accuracy, significantly better cross-lingual pronunciation, and the return of unique vocal timbres that sound closer to the original vocalist.
• How to Access the Update: This is a free voice update. To access v201 voice update, launch Synthesizer V Studio 2 Pro, open the Product Manager, and click the Update option under each voice item.
  • Please note that Synthesizer V Studio 2 Pro 2.1.0 or above is required to install this update.

Voice Database Information

Demonstrations

Demonstrations
Synthesizer V Studio 2 Pro "Mai 2" Sings in 3 Languages!! - English & Mandarin Chinese Cross-lingual Singing Synthesis	YouTube
Merry-Go-Round	YouTube bilibili

Voice Databases

Product Information

Optimum

Genre: Pop, Dance, J-Pop, Idol

Versions

Starter Pack Available?: Yes, if picked as complimentary  Trial Version Available?: Yes

Package details as noted:

This is the Synthesizer V Studio 2 version of Mai, a feminine Japanese vocal based on the singing style of Honoka Kitta. As an AI vocal, this enables her to sound realistic and human-like. Mai 2 was completely re-recorded to support more Vocal Modes compared to her original version.

Vocal traits as noted:

• Mai 2 has crisp, pop-style vocals suitable for a variety of pop-styled genres.
• Mai 2's core vocal character is consistent across all ranges, allowing for the feeling of the song to remain intact even through key shifts.
• Mai 2 is able to sing more realistically through changes in volume and breath, further enriching singing details, making each singing unique, and providing creators with more options. Through this mode, she can use AI Retakes to create multiple "takes" of a sung section to find an ideal vocal without the need for "laborious tuning". This feature is only available in the Synthesizer V Studio 2 Pro Editor.

Phonetic notes as noted:

• Phonetic format: Romaji
• Through Cross-lingual Singing Synthesis, Mai 2 can sing in not only Japanese but also in English, Mandarin Chinese, Cantonese Chinese, Spanish, and Korean. This feature is only available in the Synthesizer V Studio 2 Pro Editor.

Vocal Modes as noted (Synthesizer V Studio 2 Pro editor only):

• Mai 2 comes with six variations within the Vocal Mode function:
  • "Breathy"
  • "Downer"
  • "Emotional"
  • "Powerful"
  • "Rap"
  • "Sweet"
• Compared to the original Mai voice database released for Synthesizer V Studio, Mai 2 gained four Vocal Modes and lost or possibly renamed one. "Emotional" remained, while "Soft" was no longer named for Mai 2. "Breathy", "Downer", "Powerful", "Rap", and "Sweet"' were added to this version of Mai.

System requirements as noted:

• OS: Windows 11/10 (64-bit) / Mac OS X 10.13 or newer.
  • AH-Software Co. Ltd.'s AHS Store recommends instead macOS 11 or later for the latter.
• CPU: Intel Core i5 or newer / equivalent AMD Ryzen CPUs / Apple Silicon M1 or newer.
  • AHS Store recommends at least 4th generation for Intel Core i5 CPUs.
• Memory: 4GB or more.
• HDD: 1GB or more.
  • This is the space required when one voice database is installed.
  • Space is required according to the number of voice databases to be installed.
• Others: audio device, internet connection required, email address able to send and receive messages required. (You need to create an account at Dreamtonics to use the product.)
  • Please check the product page for the latest operating environment. Even if you do not have a DVD-ROM drive, you can install the software via the Internet. Even if the software meets the requirements for operation, we do not guarantee that it will work on all computers.

License agreements as noted:

• Dreamtonics Co., Ltd.'s End User License Agreement - Japanese
• Dreamtonics Co., Ltd.'s End User License Agreement - English
• Dreamtonics Co., Ltd.'s End User License Agreement - Simplified Chinese

Voice database sample

• Mai 2 Solfège:
  
  • Vocal Mode Solfèges:
    • "Breathy"
      
    • "Downer"
      
    • "Emotional"
      
    • "Powerful"
      
    • "Rap"
      
    • "Sweet"
      
• Vocal Mode Rap Sample:
  
  • "Rap"