This article is slowly being improved for the benefit of all visitors. Please bear with us while improvements are being made. We apologise for the inconvenience this may cause in the meantime.
(What's Being worked on: expand upon sales discontinuation by including the initial news that first broke out in either June or early July.)
This article is about the discontinued Synthesizer V Studio 2 software known as a voice database. If you are looking for the Synthesizer V character then click here.
History[]
Pre-Synthesizer V[]
On December 1, 2017, ST MEDiA Co., Ltd. published their first album: I Love Moonlight. The album was a compilation of all of UNI's promotional demo songs in addition to four songs made exclusively for it. A limited edition version was also produced and came with a special LED light stand based off of the album's cover art. A five-day preorder sale was held prior to the album's release and allowed customers to purchase the normal version at a 10% discount for either.
On January 26, 2024, ST MEDiA announced the hosting of a contest as part of the SeeU Library Renewal Limited 400 project broadcast to be launched with the goal of creating a masculine derivative for UNI, to be known as "YUNO" (유노).[3]
2025[]
On February 14, 2025, in celebration of UNI's 8th anniversary as a VOCALOID, ST MEDiA announced the release of a new Korean voice database for UNI, to be developed for the then-upcoming Synthesizer V Studio 2 software, and it was planned to be released on March 21, the same day the new engine was expected to release.[4] UNI was announced to be equipped with the latest AI voice synthesis technology in the upgraded Synthesizer V version 2, enabling her to sing with more natural voice expression and providing a wide range of timbres for rich vocal expressions. With the use of Synthesizer V Studio 2's Cross-lingual Singing Synthesis feature, UNI was announced to be available in multiple languages, including English and Japanese, in addition to Korean. Though not specified, Cross-lingual Singing Synthesis would allow UNI to perform in additional languages such as Mandarin Chinese, Cantonese Chinese, and Spanish. Due to "various reasons" at the time, ST MEDiA was unable to disclose more information at the time, though they noted that they were working hard and would be releasing sample voices and demonstrations of Synthesizer V 2 AI UNI, a pre-order schedule, and additional information in the near future.[4]
ST MEDiA was able to disclose the voice database release formats. UNI would be available as digital download editions and a special Limited Edition Launch Package. Pre-orders of the digital download version and of the Limited Edition Launch Package would begin on March 14. The digital version would be available for general sale starting on March 21. The voice database's price for both digital and the Limited Edition Launch Package was still undetermined. It was noted that those who purchase the digital version would receive their serial code and installation files on March 21. The Limited Edition packages for the launch were expected to take a period of production time after pre-orders are completed and would be shipped out sequentially after production is complete. ST MEDiA would keep consumers updated on the production progress of the Limited edition packages through the official Shop page on Character Planet, the official ST MEDiA Official X (formerly Twitter) Account as well as the official ST MEDiA YouTube Channel.
Compared to other Synthesizer V 2 voice databases, ST MEDiA apologized for a lack of further information about the release of UNI's voice database and for the fact that they could only disclose basic information such as the release date and release format. ST MEDiA noted that in the future, they would be able to share a deeper story with fans through a live broadcast that was unable to be shared at the current time on the official ST MEDiA YouTube channel. ST MEDiA asked fans for their understanding of the current situation by simply stating that "there were various circumstances." With the launch date set for March 21, ST MEDiA was confident that they would be able to provide more comprehensive information in the coming days and would do their best to do so. ST MEDiA announced that they would be releasing sample voices from the UNI voice database soon, understanding that fans would be most curious and understanding that they may be concerned about the lack of information that is able to be shared so close to the launch date. It was noted that development on the core UNI voice database was well underway and was being finalized. ST MEDiA noted that there were "many other things" that were needed to get ready (noting demonstrations especially) and were working on them as best as they could. ST MEDiA stated that they would share more information as it becomes available and thanked fans for their support and suggested to "stay tuned."[5]
Sales suspension[]
WIP: need the news that went public in June or early July for context
On July 22, it was officially announced that following an order of Seoul's court, the sales for UNI's Synthesizer V 2 voice database would be stopped on July 23 at midnight Korean time, and that ST MEDiA would be seeking another voice provider for UNI.[1][2] The official Character Planet website also informed that the third batch of pre-ordered packages would be shipped on July 23.[6][7]
Updates[]
- 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 | |
|---|---|
|
| |
| 필요조건◎Stranded (Piryojogeon◎Stranded) |  YouTube
|
| 필요조건◎Stranded (Piryojogeon◎Stranded) comparison ft. UNI (VOCALOID4) | YouTube
|
| 미완성인 우리의 노래를 (Miwanseongin Uriui Noraereul) | YouTube
|
| Longing Stars - English Cross-lingual Singing Synthesis | YouTube
|
| 목성은 사랑을 한다 (Mokseongeun Sarangeul Handa) | YouTube
|
| 악천후에도 지지 않아! (Akcheonhuedo Jiji Ana!) | YouTube
|
Voice Databases[]
With Diffusion Probabilistic Models (DPM), UNI would be 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.
It is to note that this voice database has no retrocompatibility with Synthesizer V Studio editor.- Phoneme format: X-SAMPA
- Through Cross-lingual Singing Synthesis, UNI is expected to sing in not only Korean but also in Japanese, English, Mandarin Chinese, Cantonese Chinese, and Spanish. This feature is only available in the Synthesizer V Studio 2 Pro Editor.
- UNI comes with sixteen[5][9] variations in the Vocal Mode function:
- "Normal": A vocal mode that highlights UNI's character traits.
- "N_Bright": A brighter sounding vocal mode compared to Normal.
- "N_peaceful": A more comfortable and soft feeling vocal mode compared to Normal.
- "Bold": A vocal mode for expressing a lively and confident singing style in fast-tempo songs.
- "Bold_dynamic": A vocal mode suitable for expressing bold and strong feelings in rock, metal, and similar genres.
- "Charming": A vocal mode with a slight nasal quality, good for expressing a simple and nonchalant feeling.
- "Delicate": A Default-series vocal tone that expresses delicate, soft, and restrained feelings in middle and high ranges.
- "Emotive_dynamic": A vocal mode with dark qualities in pronunciation and tone, suitable for serious ballad-like genres.
- "Mature": A Whisper-series vocal tone that sounds more calm and mature than Whisper.
- "Moody": A Default-series vocal tone specialized for comfortable ballads and medium-tempo genres.
- "Playful": A vocal mode specialized for playful expressions with strong nasal sounds and unique pronunciation.
- "Resonant": A vocal tone with compressed resonance, suitable for modern rock or appealing ballads.
- "Resonant_dynamic": A vocal mode created to express the high range of Resonant more dramatically.
- "Soulful": Produces a more compressed sound compared to Moody, a vocal mode for expressing songs with groove like R&B or Soul genres.
- "Tempting": A vocal mode that expresses refreshing tone and charming vocal techniques.
- "Whisper": A Normal-series vocal tone but with more breath mixed in, creating a whispering-like vocal tone.
- 유니(UNI) Synthesizer V Studio 2 보이스뱅크 및 캐릭터 라이선스의 상업/비상업적 사용에 대한 안내 via Wayback Machine
Guidelines for Commercial/Non-Commercial Use of UNI Synthesizer V Studio 2 Voicebank and Character License (in Korean; scroll down to the bottom of the page then expand the section)
- UNI Solfège:
- Vocal Mode Solfèges:
- "Normal":
- "N_Bright":
- "N_peaceful":
- "Bold":
- "Bold_dynamic":
- "Charming":
- "Delicate":
- "Emotive_dynamic":
- "Mature":
- "Moody":
- "Playful":
- "Resonant":
- "Resonant_dynamic":
- "Soulful":
- "Tempting":
- "Whisper":
- "Normal":
- Vocal Mode Solfèges:
References[]
- ↑ 1.0 1.1 https://x.com/STMEDiA_info/status/1947644614649008283
- ↑ 2.0 2.1 https://docs.google.com/document/d/1UeKZq2EbS1kL30OhGBT5k4VqUDaxxFXrNJyS3MbrmjM/edit?tab=t.0 (in Korean; English translation by Infoholic)
- ↑ https://www.youtube.com?watch?v=_6YvdyyfHZU&t=2125
- ↑ 4.0 4.1 https://x.com/STMEDiA_info/status/1890336583599173796
- ↑ 5.0 5.1 https://characterplanet.net/ via Wayback Machine (February 15, 2025)
- ↑ https://characterplanet.net/ via archive.today (July 22, 2025)
- ↑ https://characterplanet.net/ via Wayback Machine (July 23, 2025)
- ↑ https://dreamtonics.com/synthesizer-v-voice-201-update/
- ↑ https://www.youtube.com/watch?v=YAZ6JvFaqP8