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 January 29, 2024, Dreamtonics Co., Ltd. posted a poem on bilibili along with an invitation for listeners to listen to new songs expected for January 30 at 17:00 GMT+8.[1] Details were not specified but the first part of the poem seemed to describe the sound of snapping fingers, the clapping of hands and the calling of toes kicking along. The second part described the role of drum beats and melody changes and the bodies' response to the rhythm. The third part described the lyrics as freely written, and that the sparks of dreams are sparked by the collision of lips and teeth. On January 30, a technical demo was released announcing the development of a new female Mandarin Chinese vocalist, specialized for Rap. The vocal was described as energetic and dynamic, full of the young generation's strong personal advocates; the biting is stable and clear, and maintains an excellent sense of unity even in Cross-lingual Singing Synthesis and rapping; and combines firm biting with the female singer's unique agility in fast-paced rap music, giving the listener an uninhibited impression of freedom. This gives the listener the impression of freedom from constraints. The voice database was announced to be released in the near future as well as additional information about the product, also announced to be released in the future.[2]
On February 2, her name was revealed to be Yi Xi;[3] her technical demo video was also updated to reflect the new name. Sometime on or before March 5, the demo video's thumbnail was updated to reveal a darkened version of her final icon design.
She was released to mainland Chinese customers on Dreamtonics' Taobao store on March 15. On November 14, she, along with Xuan Yu, Cong Zheng, Lin Lai, Yun Quan, and Cantonese Chinese vocal Ling Wan, were added to AH-Software Co. Ltd.'s AHS Store,[4] 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[]
Retirement[]
Yi Xi was discontinued by Dreamtonics on March 21, 2025 with the release of Synthesizer V Studio 2 and Yi Xi 2. As of March 23, several Japanese online stores like the AHS Store, DLsite, and SONICWIRE still sell the original Yi Xi voice database, but stock may be limited.
Usage on Synthesizer V Studio 2[]
Yi Xi 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 | |
|---|---|
|
| |
| 人间布洛芬 (Rénjiān Ibuprofen) |  bilibili
|
| Dreamtonics Recommended Songs Playlist[6] | |
|---|---|
|
| |
| 爱我的请举手 (Ài Wǒ De Qǐng Jǔ Shǒu) | bilibili
|
Voice Databases[]
- With Diffusion Probabilistic Models (DPM), Yi Xi 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.
- Phoneme format: X-SAMPA
- Through Cross-lingual Singing Synthesis, Yi Xi can sing in not only Mandarin Chinese but also in English, Japanese, and Cantonese Chinese. Since the release of her v101 update on April 4, 2024, she can also sing in Spanish with this feature. Cross-lingual Singing Synthesis is only available in the Synthesizer V Studio Pro and Synthesizer V Studio 2 Pro editors.
- Yi Xi comes with five variations within the Vocal Mode function:
- "Soft"
- "Languid"
- "Relaxed"
- "Cool"
- "Firm"
- It should be noted that the Vocal Modes were uniquely calibrated for diverse rap performances and work best in Yi Xi's Rap Mode.
- OS: Microsoft Windows 11 / 10 (64 bit) and up; macOS 10.13 (High Sierra) and up; Ubuntu 20.04 (64 bit) and up.[7]
- 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.
- 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
- Yi Xi AI Solfège:
- Vocal Mode Solfèges:
- "Soft":
- "Languid":
- "Relaxed":
- "Cool":
- "Firm":
- "Soft":
- Vocal Mode Solfèges:
- Yi Xi Rap Example:
References[]
- ↑ https://t.bilibili.com/891983356406792208
- ↑ https://www.bilibili.com/video/BV1i2421L76E/
- ↑ https://t.bilibili.com/892351654161023105
- ↑ https://x.com/ahsoft/status/1856895025285890449
- ↑ 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 Yi Xi as a main vocalist would be added to this demo table.
- ↑ AH-Software Co. Ltd.'s Dreamtonics-branded Synthesizer V voice database specifications page, archived December 8, 2024