JUN (Synthesizer V Studio)

JUN	SynthV Studio	SynthV Studio 2	|	Originals	|	Gallery

JUN (Synthesizer V Studio)
Product Information
Company	AUDIOLOGIE Co., Ltd.
Release Date(s)	April 20, 2023
Status	Released
System Requirements	Windows, MacOS, Linux
Base Language(s)	English
Type	Synthesizer V Studio (AI)
Licensing	Proprietary
Affiliations	Dreamtonics Co., Ltd.
Product Page	Digital copies: AHS AUDIOLOGIE AUDIOLOGIE (Mainland China) SONICWIRE Physical copies: AUDIOLOGIE (Limited stock) AUDIOLOGIE (Mainland China) (Limited stock)

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

History

2022

On December 11, 2022, AUDIOLOGIE posted an original song, "1NTROSPECTION", in celebration of the first anniversary of ANRI, their first vocalist. In the description, they announced that a new voice database would be announced within the first quarter of 2023 and a silhouette of a new character was seen in the PV, labelled as "ANRI + ? = Smth NEW". It was noted that AUDIOLOGIE was working on two projects, one of which was cited to be releasing early next year, but it was unknown if this was in reference to the new vocalist. The vocalist was said to be a perfect complement to ANRI. It was also noted that the COVID-19 pandemic had hurt the rollout schedule, but the available budgets allowed for the company to allocate funds for upcoming projects. Aria was cited to be leading the development of both projects.

2023

On February 11, 2023, JUN was revealed to be a male English voice database and made his debut with his first original song "Burn So Bright". Information about his character was made available on AUDIOLOGIE's website. He was illustrated by Allenkung1 and his concepts were designed by Chisacha and 7Mora. His voice provider was revealed to be Lavy. JUN was confirmed to have seven Vocal Modes and was made available to pre-order upon debut, with an expected release date in April 2023 as digital and limited physical copies. His Taobao pre-orders were to begin on February 14.

On February 18, through JUN's second demo, "Outta My Head", AUDIOLOGIE confirmed the seven Vocal Modes: "Dark", "Chest", "Soul", "Power", "Light", "Tsubaki", and "Soft". On February 25, through his third demo, AUDIOLOGIE clarified in the description that his release date was scheduled for late April. On April 1, according to the description of one of JUN's demos, the "Tsubaki" Vocal Mode was noted to have data that was designed specifically to improve Japanese Cross-lingual Singing Synthesis though he was not officially considered a Japanese bilingual vocalist.

On April 18, in response to a fan, AUDIOLOGIE confirmed that there would be a special collector's edition of ANRI and JUN's duet pack, which was expected to be distributed at a discounted price and would have a brand new cover illustration by Allenkung1. Physical copies of JUN were also being prepared for shipment while digital pre-orders were being fulfilled. The pre-order discount was announced to be ending on April 20 with all pre-orders to be fulfilled by that date.

On June 14, a special "ANRI & JUN Special Duet Edition Box" was released in commemoration of ANRI's 2nd birthday celebration. The hardcover box featured a plastic postcard of ANRI's birthday illustration featuring open slots for ANRI and JUN's digital activation code. It was noted that the box did not contain ANRI or JUN's software and was an add-on merchandise box with an activation code holder intended to be paired with digital purchases or previous physical DVD purchases. The bundle included two clear acrylic standees and an acrylic PVC postcard (activation code holder) featuring ANRI and JUN with an illustration by Allenkung1 and "K.".

Updates

JUN AI v101b1 - June 21, 2023 

A free update for JUN was released following the Synthesizer V Studio 1.9.0 update. This implemented the new rap feature available for the English and Mandarin languages. Cantonese Chinese was added to the Cross-lingual Singing Synthesis feature as well as general improvements to the overall function, resulting in more accurate pronunciation that sounds closer to a native speaker when singing foreign words. For JUN specifically, there were corrections for his phonemes and hard consonants.

JUN AI v101 - July 6, 2023 

Final version update compatible for Synthesizer V Studio 1.9.0 which enables JUN to use the rap feature (English and Mandarin Chinese only), allows for Cantonese Chinese Cross-lingual Singing Synthesis, and corrects his phonemes and hard consonants if the beta version was not installed previously. This update also improved JUN's stability in his high pitch.

JUN AI v102b1 - August 2, 2023 

A free update for JUN was released following the Synthesizer V Studio 1.10.0b1 update. This enhanced pitch generation by utilizing Reinforcement Learning from Human Feedback (RLHF), translating to fewer off-key errors, making better use of vibrato, and creating more expressive transitions between notes. This also allowed for the use of the new "Enhancement" slider in the AI Retakes panel, which controlled the level of changes introduced by RLHF. For Synthesizer V Studio Pro users, feedback submission was enabled, allowing users to consensually share their preferred takes with only Dreamtonics for research and development purposes, where models trained with this feedback would be deployed in future voice database updates. Users may also opt out of this feature if undesired.

JUN AI v102b2 - September 28, 2023 

A free update for JUN was released following the Synthesizer V Studio 1.10.0b2 update, which was the second beta version following version 1.10.0b1 that introduced enhancements to voice databases and integrated the latest user feedback via Reinforcement Learning from Human Feedback (RLHF). Regarding the editor, numerous reported issues were addressed for a more fluid experience. A new generation of pitch models were trained using the extensive feedback from users over the past month, and the new models offered greater accuracy in voice timbre reproduction, as well as a reduction in mispronunciations. Dreamtonics also focused on issues from the previous beta release that made Vocal Modes seem less distinct on certain vocals, ensuring clearer differentiation in the 1.10.0b2 update. The latest update also introduced a new feature in the Note Properties Panel that allowed for even division of a note into multiple syllables, proving to be a useful tool for songs with faster tempos.

JUN AI v102 - October 19, 2023 

Final version update compatible for Synthesizer V Studio 1.10.0 which enables JUN to use Reinforcement Learning from Human Feedback (RLHF) as well as other enhancements (as listed in v102b1 and v102b2's notes) if the beta version was not installed previously.

JUN AI v103 - October 26, 2023 

A free update for JUN was released that added support for the Japanese language to the rap feature.

JUN AI v104b1 - December 18, 2023 

A free update for JUN was released following the Synthesizer V Studio 1.11.0b2 update. This implemented support for the Spanish language in the Cross-lingual Singing Synthesis feature.

JUN AI v104 - April 4, 2024 

Final version update compatible for Synthesizer V Studio 1.11.0 which enables JUN to sing in Spanish through Cross-lingual Singing Synthesis if the beta version was not installed previously.

JUN AI v105 - May 18, 2024 

An update featuring updated EULA embedded in the voice database, notably the addition of Japanese version, and added clause on not to use rendered voice into other synthesis program.

Voice Database Information

Demonstrations

Demonstrations
Burn So Bright	NicoNico YouTube bilibili SoundCloud
Outta My Head - "Dark", "Chest", "Soul", & "Power" Vocal Modes	NicoNico YouTube bilibili SoundCloud
Plastic Love (RnB Remix) - Japanese Cross-lingual Singing Synthesis; "Soul" Vocal Mode	NicoNico YouTube bilibili SoundCloud
I've Been a Fool - "Chest" Vocal Mode	NicoNico YouTube bilibili SoundCloud
Walk This Way ft. ANRI	NicoNico YouTube bilibili SoundCloud
Memories - "Dark" Vocal Mode	NicoNico YouTube bilibili SoundCloud
Starry Eyes	NicoNico YouTube bilibili
日もすがら音楽と (Hi mo Sugaru Ongaku to) - Japanese Cross-lingual Singing Synthesis; "Power" & "Tsubaki" Vocal Modes	NicoNico YouTube bilibili SoundCloud
Just Be Friends (Screamo Remix)	NicoNico YouTube SoundCloud
GQ	YouTube bilibili
长大 (Zhǎngdà) - Mandarin Chinese Cross-lingual Singing Synthesis	bilibili
Heart of Gold	NicoNico YouTube bilibili SoundCloud
Fake Love, Broccoli & Caroline ft. ANRI	NicoNico YouTube bilibili SoundCloud

Voice Databases

Product Information

Optimum

  Range: Varies depending on Vocal Modes

Versions

  Lite Version/FLT Available?: No  Starter Pack Available?: No  Web Version Available?: No

Package details as noted:

JUN is a masculine English voice database based on the singing style of the CV Lavy. As expected of an AI voice database, JUN is capable of singing with a more human-like and realistic voice. According to AUDIOLOGIE, his voice is described to have a powerful tone with a melodic timbre.

Vocal traits as noted:

With Diffusion Probabilistic Models (DPM), JUN 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.

Phonetic notes as noted:

• Phoneme format: ARPABET
• Through Cross-lingual Singing Synthesis, JUN can sing in not only English but also in Japanese and Mandarin Chinese. Since the release of his v101b1 update on June 21, 2023, he can also sing in Cantonese Chinese with this feature; since his v104b1 update on December 18, he can also sing in Spanish with this feature. Cross-lingual Singing Synthesis is only available in the Synthesizer V Studio Pro Editor.
  • It should be noted that JUN's default language is set to English. He was confirmed to also be trained with Japanese songs to further optimize his Cross-lingual Singing Synthesis capabilities, especially through the "Tsubaki" Vocal Mode.

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

• JUN comes with seven variations:
  • "Dark": A mature and slightly breathy tone. Effective range noted to be B2 ~ G#4.
  • "Chest": Works with energizing lower-ranged songs. Effective range noted to be F2 ~ A3.
  • "Soul": An expressive mode that would also change JUN's pronunciation. Effective range noted to be G3 ~ E4.
  • "Power": The strongest tone that contained all belt samples. Ideally used for higher-ranged and high-energy types of songs. Effective range noted to be F3 ~ A4.
  • "Light": A bright and lightweight tone. Effective range noted to be B2 ~ E4.
  • "Tsubaki": A bright tone of voice with data primarily used to improve JUN's Japanese pronunciation and accent. It was designed specifically for English to Japanese Cross-lingual Singing Synthesis. Effective range noted to be C3 ~ G4.
    • "Tsubaki" was named after the "Camellia japonica" flower.
    • According to Aria, it was recommended to use "Tsubaki" with "Power" or "Light" to retain his accent in Japanese. For the other softer modes ("Dark", "Soft", and "Soul"), the accent's improvement is less defined.
  • "Soft": A breathy tone. Effective range noted to be A2 ~ F4.
• With the use of his Vocal Modes, JUN would be able to handle "hard-driving up-tempo" songs, slow ballads, and everything in between, noting him to be a flexible voice.

License agreements as noted:

• AUDIOLOGIE's Commercial Use Guidelines - English

Voice database sample

• JUN Solfège:
  
  • Vocal Mode Solfèges:
    • "Dark":
      
    • "Chest":
      
    • "Soul":
      
    • "Power":
      
    • "Light":
      
    • "Tsubaki" (ENG):
      
    • "Tsubaki" (JPN):
      
    • "Soft":