This article is about the retired Synthesizer V Studio software known as a voice database. If you are looking for the Synthesizer V concept then click here.
History[]
On February 27, 2023, Dreamtonics posted a poem on bilibili along with an announcement that new songs and other news were expected for February 28 at 17:00 GMT+8.[1][2] Details were not specified but the first part of the poem seemed to describe the beauty of song and pronunciation in music across any language.[3][4] The second part described the role of melodies and pitches in music, emphasizing the importance of rhythm.[5][6] On February 28, a technical demo announcing the future support for the Cantonese dialect and rap was uploaded, showing a new male AI voice database singing in the new supported language respectively. The new male vocal was confirmed to be entirely trained on Cantonese songs and was noted to be the first Cantonese voice library in the history of commercial singing voice synthesis software.[7] On March 15, after receiving feedback in improving the song to be more in line with Cantonese songwriting habits, Dreamtonics replaced the bilibili version of the debut video, which implemented corrections made to the male vocal's and Feng Yi's demos.[8][9] On September 26, Dreamtonics announced that they would be showcasing a "soon-to-be-released" dedicated Cantonese Chinese AI voice database at the Music China event in Shanghai, which ran from October 11 to 14. This vocal was noted to have outstanding mixed Mandarin and Cantonese singing with proficient and smooth Cross-lingual Singing Synthesis across the four available languages for Synthesizer V Studio.[10] It was unknown if this voice database was the same one shown in February or if it was a new vocalist.
On October 3, 2023, Dreamtonics Co., Ltd. posted a thread on Twitter announcing four new voice databases in development for Synthesizer V Studio that were to be "coming up", providing no information apart from teasers.[11] The last of four voice databases to be teased with a demo song within the thread was Wei Shu, described as a "Cantonese male voice with a soft, whispery, slightly nasal voice ideal for the low to middle range" as well as "a powerful sound that maintains softness" in the middle to high range, suitable "for ballads and high-tempo electro-pop tunes" like the linked demo song "Kissing Someone Next".[12]
Wei Shu was released on October 26, 2023.
Updates[]
Retirement[]
Wei Shu was discontinued by Dreamtonics on March 21, 2025 with the release of Synthesizer V Studio 2 and Wei Shu 2.
Voice Database Information[]
Demonstrations[]
| Demonstrations | |
|---|---|
|
| |
| 好心吻下个 (Hou2 Sam1 Man5 Haa6 Go3) ft. Cong Zheng - Mandarin Chinese Cross-lingual Singing Synthesis |  YouTube  bilibili
|
| Dreamtonics Recommended Songs Playlist[15] | |
|---|---|
|
| |
| 兜兜转转 (Dau1 Dau1 Zyun2 Zyun2) - "Soft" Vocal Mode | bilibili
|
| Shall We Talk ft. Ao Tian - English Cross-lingual Singing Synthesis | bilibili
|
| 单车 (Daan1 Ce1) | bilibili
|
Voice Databases[]
- Wei Shu's voice was described as soft, whispery, and slightly nasal in the low to middle range, and as powerful while maintaining softness in the middle to high range.
- He was noted to be suitable for ballads and high-tempo electro-pop tunes.
- With Diffusion Probabilistic Models (DPM), Wei Shu 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, he 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 Editor.
- Phoneme format: X-SAMPA
- Through Cross-lingual Singing Synthesis, Wei Shu can sing in not only Cantonese Chinese but also in Mandarin Chinese, English, and Japanese. Since the release of his v101b1 update on December 18, 2023, he can also sing in Spanish with this feature. Cross-lingual Singing Synthesis is only available in the Synthesizer V Studio Pro Editor.
- Wei Shu comes with four variations:
- "Bright"
- "Powerful"
- "Soft"
- "Subdued"
- 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
- Wei Shu AI Solfège:
- Vocal Mode Solfèges:
- "Bright":
- "Powerful":
- "Soft":
- "Subdued":
- "Bright":
- Vocal Mode Solfèges:
References[]
- ↑ https://t.bilibili.com/767295924844101665
- ↑ https://x.com/LenKiMo/status/1630132094893719552 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132100216287233 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132108072218624 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132104104415233 - Translation by @LenKimo
- ↑ https://x.com/LenKiMo/status/1630132111452811264 - Translation by @LenKimo
- ↑ https://www.youtube.com/watch?v=mcJU0Wq-u7w
- ↑ http://www.bilibili.com/video/BV1zs4y1f7QJ - "Dreamtonics 已于 3 月 15 日将 Synthesizer V AI 粤语歌声合成技术预览的测试曲目更换为更加符合粤语歌曲创作习惯的版本，感谢各位创作者的关心与鞭策。未来 Dreamtonics 将陆续发布更多关于粤语歌声合成与跨语言合成的信息，敬请期待。"
- ↑ https://t.bilibili.com/773207552189005831
- ↑ https://t.bilibili.com/845594879243321396
- ↑ https://x.com/dreamtonics_en/status/1709116086644310260
- ↑ https://x.com/dreamtonics_en/status/1709116095171637371
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0b2-update/
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0-update/
- ↑ 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 Wei Shu as a main vocalist would be added to this demo table.
- ↑ https://img.alicdn.com/imgextra/i4/54187543/O1CN01w2L83b25akRYbNTh7_!!54187543.png - Wei Shu initially did not have a range listed upon release. This was added to his Taobao product page as of March 15, 2024