SynthV Wiki
Advertisement
This project is currently in production.

According to official sources, this project was announced to currently be in production or is in its conceptual stages.
Please read the page for more information.

For miki's voice provider, see Miki Furukawa.
miki
SynthV Studio
VOCALOID2
VOCALOID4
|
Originals
|
Gallery

miki is an upcoming Japanese vocal to be developed and distributed by AH-Software Co. Ltd. and is expected to release as an AI voice database for Synthesizer V Studio in December 2024. She was initially released under the moniker SF-A2 codename: miki (SF-A2 開発コード miki) as one of AH-Software's three debut voicebanks for the VOCALOID2 engine (along with Hiyama Kiyoteru and Kaai Yuki) in December 2009; she was updated for VOCALOID4 in June 2015.[1]

Her voice is provided by the Japanese female singer-songwriter, Miki Furukawa.

Concept[]

Etymology[]

"miki" comes from her provider's name "Miki Furukawa". Regarding her original name on VOCALOID, "SF-A2 codename: miki" (often shortened to just "SF-A2 miki"): in Japanese, 'codename' or 'development code' translates as 'kaihatsu koudo' (開発コード); the meaning of the "SF-A2" part of her old name has never been stated.

Appearance[]

INFORMATION PENDING

Relations[]

  • Utatane Piko - Originally, miki and Piko were developed as a pair, but due to complications, they were split between two companies.[2]

History[]

In spite of being one of AH-Software Co. Ltd.'s first three singing vocals, miki's direction was very different from that of Hiyama Kiyoteru and Kaai Yuki. Much of her planning and development for VOCALOID2 was handled by HEARTFAST, while the rest of her planning was carried out by AHS (together with the overall planning of its other two debut vocals, which began in 2007). She was originally meant to be the partner vocal of Utatane Piko and was made with a different company, but due to problems, she was separated from her "brother" vocal,[2] who ended up being owned by Ki/oon Music Inc. (a subsidiary of Sony Music Entertainment Japan). She, Kiyoteru, and Yuki were released the same day on December 4, 2009; SF-A2 codename: miki (as her voicebank was officially dubbed), whose creation was a joint effort by both AH-Software and Yamaha Corporation, was released as part of an "artist edition series".

miki and many other AH-Software vocals were announced to be receiving updates for VOCALOID4 on November 20, 2014's livestream, after their silhouettes were revealed on a poster two weeks earlier without providing any further context.[3] On May 14, 2015, AHS confirmed that miki would only have a Natural voicebank and would release on June 18, 2015; it was possible to buy SF-A2 miki V4 Natural either as a standalone product or as a Starter Pack bundled with the VOCALOID4 Editor.[4]

2023[]

Synthesizer V AI miki & Hiyama Kiyoteru announcement
AH-Software Co. Ltd. livestream, December 1, 2023

On December 1, 2023's AHS livestream, it was announced that both miki and Kiyoteru would be receiving AI voice databases for Synthesizer V Studio for their joint 15th anniversary in 2024.[5]

2024[]

On October 31, 2024, during AH-Software official live broadcast No. 207, it was announced that both miki and Kiyoteru would be delayed until 2025 because they wanted to refine their voicebanks and ensure that it meets the highest quality standards, making sure that the final product is the best possible and lives up to fans' expectations.[6]

Voice Database Information[]

Voice Databases[]

Product Information
Versions
  Lite Version/FLT Available?: TBA  Starter Pack Available?: TBA  Web Version Available?: No

Package details as noted:
miki is expected to be a feminine Japanese voice database based on the singing style of Miki Furukawa. As expected of an AI voice database, miki will be capable of singing with a more human-like and realistic voice.

Vocal traits as noted:
With Diffusion Probabilistic Models (DPM), miki will 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 will be able to 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: Romaji
  • Through Cross-lingual Singing Synthesis, miki is expected to sing in not only Japanese but also in English, Mandarin Chinese, Cantonese Chinese, and Spanish. This feature is only available in the Synthesizer V Studio Pro Editor.

Voice Libraries[]

Additional Information[]

Marketing[]

miki, along with Hiyama Kiyoteru and Kaai Yuki, was introduced to expand the selection of VOCALOIDs, giving producers more choices.[7]

Until May 2011, all AH-Software VOCALOIDs were banned from KARENT.

Reputation[]

Miki's character status
Achievements
  • One of the first three AH-Software VOCALOID2 voicebanks to be released.
  • One of the two first female AH-Software VOCALOIDs.
  • First VOCALOID of the Artist Edition series to be released.

References[]

External links[]

Navigation[]


Advertisement