SynthV Wiki
Ling Wan
SynthV Studio
SynthV Studio 2
|
Originals
|
Gallery

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

History[]

On May 16, 2024, Dreamtonics Co., Ltd. announced that they would be showcasing an early preview of a female Cantonese AI voice database at the Guangzhou International Music Instrument Exhibition from May 23 to May 26.[1]

On July 18, a poem dropped on bilibili[2] and on Weibo.[3] The poem could be translated to the following:

"To the south, to the south,
The melody will not cease until it reaches the southern sea, then hears a voice like a warbler.

Blue feathers, purple feathers,
The gentle Tang tone is haunting; when the song disappears, the tide has stopped."[4]

As such, it was acknowledged the voicebank would be Cantonese,[5][6] and possibly the one shown back in May at the Guangzhou International Music Instrument Exhibition. On the next day, on July 19, Ling Wan released on Chinese stores as well as a demo on bilibili.[7]

On November 14, Ling Wan, along with Mandarin Chinese vocals Xuan Yu, Cong Zheng, Lin Lai, Yun Quan, and Yi Xi, were added to AH-Software Co. Ltd.'s AHS Store,[8] thus allowing international customers to purchase her without resorting to proxy services (like ParcelUp, which are required for most users from outside mainland China to buy Taobao products).

Updates[]

Ling Wan AI v101 - circa November 20, 2024 
A free update for Ling Wan was released to fix some of her reported metallic resonance, allowing her to sing smoother and also handle faster notes better.

Retirement[]

Ling Wan was discontinued by Dreamtonics on March 21, 2025 with the release of Synthesizer V Studio 2 and Ling Wan 2. As of March 23, several Japanese online stores like the AHS Store, DLsite, and SONICWIRE still sell the original Ling Wan voice database, but stock may be limited.

Usage on Synthesizer V Studio 2[]

Ling Wan can be imported into (and used on) Synthesizer V Studio 2 Pro by simply registering her SVS1 activation code into the My Dreamtonics website.

Voice Database Information[]

Demonstrations[]

Demonstrations

后顾之友 (Hau6 Gu3 Zi1 Jau5) - Cantonese Chinese Favicon-bbbilibili
Dreamtonics Recommended Songs Playlist[9]

初恋 (Hatsukoi) - Cantonese Chinese Favicon-bbbilibili
不怕庆祝 (Bùpà Qìngzhù) - Mandarin Chinese Favicon-bbbilibili
士多啤梨苹果橙 (Si6 Do1 Be1 Lei4 Ping4 Gwo2 Caang2 - Cantonese Chinese Favicon-bbbilibili

Voice Databases[]

Product Information
Optimum
Genre: Pop, Folk  Range: A3 ~ A4

Versions
Lite Version/FLT Available?: No  Starter Pack Available?: Yes (with SVS2)  Trial Version Available?: No  Web Version Available?: No

Package details as noted:
Ling Wan is a feminine Cantonese Chinese voice database. As expected of an AI voice database, this enables her to sing with a more human-like, natural, and realistic voice.

Vocal traits as noted:
  • Ling Wan's voice was described as soft voice.
  • With Diffusion Probabilistic Models (DPM), Ling Wan can 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 Pro and Synthesizer V Studio 2 Pro editors.

Phonetic notes as noted:
  • Phoneme format: X-SAMPA
  • Through Cross-lingual Singing Synthesis, Ling Wan can sing in not only Cantonese Chinese but also in Mandarin Chinese, English, Japanese, and Spanish. Cross-lingual Singing Synthesis is only available in the Synthesizer V Studio Pro and Synthesizer V Studio 2 Pro editors.

Vocal Modes as noted (Synthesizer V Studio Pro and Synthesizer V Studio 2 Pro editors only):
  • Ling Wan comes with six variations within the Vocal Mode function:
    • "Firm"
    • "Gentle"
    • "Lively"
    • "Powerful"
    • "Soft"
    • "Steady"

System requirements as noted:
  • OS: Microsoft Windows 11 / 10 (64 bit) and up; macOS 10.13 (High Sierra) and up; Ubuntu 20.04 (64 bit) and up.[10]
  • CPU: Intel Core i5 or higher, or equivalent AMD processor; Apple Silicon M1 or higher.
    • For high-quality editing of AI audio: Intel Core series 4th generation i5 or higher is recommended, or AMD Athlon X4 845 or higher, including Ryzen series.
  • Memory: 2GB or more.
  • HDD: 1 GB or more.
  • Display resolution: 1280 x 800 or higher resolution.
  • Others: audio device, internet connection.

License agreements as noted:

Voice database sample

References[]

  1. https://t.bilibili.com/932057724907159569
  2. https://x.com/LenKiMo/status/1813915937726414939
  3. https://weibo.com/7752303641/Oo8ian0es
  4. https://x.com/LenKiMo/status/1813915942977728655
  5. https://x.com/LenKiMo/status/1813915945485967462
  6. https://x.com/LenKiMo/status/1813915948019269689
  7. https://www.bilibili.com/read/cv36195749/
  8. https://x.com/ahsoft/status/1856895025285890449
  9. https://space.bilibili.com/593592382/favlist?fid=1655788882 - These songs were featured in an official bilibili playlist featuring demos and recommended songs. Certain users were invited to create songs using earlier versions of the voice database and release the songs in sequence after the product's release as a complement to official demo tracks. It should also be noted that certain songs may not be involved with the early invitation and were added based on the company's preference. Only songs that feature Ling Wan as a main vocalist would be added to this demo table.
  10. AH-Software Co. Ltd.'s Dreamtonics-branded Synthesizer V voice database specifications page, archived December 8, 2024

Navigation[]