SynthV Wiki
Advertisement
Tsurumaki Maki
SynthV Studio
VOICEROID
CeVIO AI
VoiSona Talk
VOICEPEAK
|
Originals
|
Gallery
Japanese
English

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[]

2020[]

On December 25, 2020, AH-Software Co. Ltd.'s YouTube channel published a video announcing Tsurumaki Maki's CeVIO AI and Synthesizer V AI voice databases, which featured official illustrations by Umetani Atarō for her CeVIO AI design and Ohmi Chiko for her Synthesizer V AI design. She was announced to have both Japanese and English banks for both engines.[1] It was also announced via livestream that Manami Tanaka was the voice provider instead of Tomoe Tamiyasu, Maki's voice actress for her VOICEROID voicebanks. This was due to a communication error between AH-Software and Tomoe Tamiyasu's management company. The agency would not allow the original voice actress to keep the role, so AH-Software needed to find a new voice provider for Maki. The original voice actress was allegedly not notified of the change in providers during the production of the new banks.[2][3][4] AH-Software later released a letter during a press release regarding the situation and asked for support of the new voice provider.[5]

2021[]

On March 30, 2021, reference sheets for Maki were revealed.[6] On May 12, Maki was confirmed to be releasing on June 18. For Synthesizer V Studio, the Japanese and English voice databases were to be available as separate physical packages for both Standard and AI.[7] The lite editions of her voice databases were released on June 3.[8] Maki's full voice databases were released on June 18 as intended.

2022[]

On March 25, 2022, after the implementation of Vocal Modes via Synthesizer V Studio Version 1.6.0., AH-Software announced that other AI voice libraries, such as Tsurumaki Maki, were planned to receive them.[9] On June 30, it was announced that Maki Japanese AI would be receiving a standalone physical package, which was expected to release on July 21, with pre-orders beginning on July 1.[10][11]

On July 21, Tsurumaki Maki Japanese AI was one of the AI voice databases to receive an update for HDVM compatibility (a feature introduced in Synthesizer V Studio Pro 1.7.0, also released the same day); this same update also integrated her Vocal Modes.[12] For both of her voice databases, Maki was given five Vocal Modes to choose from, including: Adult, Breathy, Power_Pop, Twangy, and Whisper.[13]

However, some users complained about unstable voice-quality results when re-rendering in 1.7.0 projects saved under earlier versions of the editor that made use of her voice database (after updating it to v111). On July 22, Dreamtonics explained that by default, the AI Retakes feature favors "rich timbre and expressions over smooth and stable vocalization", resulting in inconsistent behavior relative to previous versions;[14] as a workaround to stabilize the voice output, both Dreamtonics and AH-Software offered these steps below:[15][16]

  • Empty the selection.
  • Open AI Retakes panel, go to Timbre tab.
  • Under Takes -> Global Settings, reduce Expressiveness.

Responding to requests from users, both Dreamtonics and AHS made available for download that same day rolled-back versions of Tsurumaki Maki AI (as well as other affected AI voice databases distributed by them) by logging in to their respective websites.[17][18]

Updates[]

AI - Full Version[]

Tsurumaki Maki AI v107 - December 23, 2021[19] 
A free update for Tsurumaki Maki AI was released following the Synthesizer V Studio 1.5.0 update. This enables her to support Cross-lingual Singing Synthesis.
Tsurumaki Maki AI v111 - July 21, 2022[20] 
A free update for Tsurumaki Maki AI was released following the Synthesizer V Studio 1.7.0 update. This enables her to use the new High Dynamics Voice Models and AI Retakes features. It also added data for the Vocal Modes feature from the 1.6.0 update, giving Maki five new Vocal Modes: "Adult", "Breathy", "Power_Pop", "Twangy", and "Whisper".
Tsurumaki Maki AI v108 - July 25, 2022[21] 
A free downgrade for Tsurumaki Maki AI that removes HDVM compatibility, but retains the Vocal Modes introduced in v111.
Tsurumaki Maki AI v114b1 - November 10, 2022[22] 
A free update for Tsurumaki Maki AI was released following the Synthesizer V Studio 1.8.0b1 update. This enables her to use the new Diffusion Probabilistic Models (DPM) feature.
Tsurumaki Maki AI v114 - November 24, 2022[23][24] 
Final version update compatible for Synthesizer V Studio 1.8.0 which enables Tsurumaki Maki AI to use the new Diffusion Probabilistic Models (DPM) feature if the beta version was not installed previously.
Tsurumaki Maki AI v115b1 - June 21, 2023[25][26] 
A free update for Tsurumaki Maki 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.
Tsurumaki Maki AI v115 - July 6, 2023[27][28] 
Final version update compatible for Synthesizer V Studio 1.9.0 which enables Tsurumaki Maki AI to use the rap feature (English and Mandarin Chinese only) and allows for Cantonese Chinese Cross-lingual Singing Synthesis if the beta versions were not installed previously.
Tsurumaki Maki AI v116b1 - August 2, 2023[29][30][31][32] 
A free update for Tsurumaki Maki AI 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.
Tsurumaki Maki AI v116b2 - September 28, 2023[33][34][35] 
A free update for Tsurumaki Maki AI 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.
Tsurumaki Maki AI v116 - October 19, 2023[36][37] 
Final version update compatible for Synthesizer V Studio 1.10.0 which enables Tsurumaki Maki AI to use Reinforcement Learning from Human Feedback (RLHF) as well as other enhancements (as listed in v116b1 and v116b2's notes) if the beta version was not installed previously.
Tsurumaki Maki AI v117 - October 26, 2023[38] 
A free update for Tsurumaki Maki AI was released that added support for the Japanese language to the rap feature.
Tsurumaki Maki AI v118 - April 4, 2024[39][40] 
A free update for Tsurumaki Maki AI was released following the Synthesizer V Studio 1.11.0 update. This implemented support for the Spanish language in the Cross-lingual Singing Synthesis feature.

AI Lite[]

Tsurumaki Maki AI Lite v101 - June 18, 2021[41][42] 
A free update for Tsurumaki Maki AI Lite was released to coincide with the Synthesizer V Studio 1.3.0 update.

Voice Database Information[]

Demonstrations[]

Synthesizer V Studio Standard[]

Demonstrations

FLASH BACK LYRICS - Short Version Favicon-ytYouTube
『Synthesizer V 匊巻マキ』デモ゜ング詊聎版 ("Synthesizer V Tsurumaki Maki" Demo Song Audition Version)[43] Favicon-ytYouTube
䜕者でもない私から (Nanimono Demo Nai Watashi Kara) - Short Version Favicon-ytYouTube
ゞングル・ベル (Jingle Bells) Favicon-ytYouTube
時を巻き戻さないで (Toki o Makimodosanaide) Favicon-ytYouTube Favicon-bbbilibili
FLASH BACK LYRICS - Full Version Favicon-ytYouTube Favicon-bbbilibili
䜕者でもない私から (Nanimono Demo Nai Watashi Kara) - Full Version Favicon-ytYouTube Favicon-bbbilibili
ハルカれ゚ンダヌ (Harukaze Ender) Favicon-nnNicoNico Favicon-ytYouTube Favicon-bbbilibili
りツロむ (Utsuroi) Favicon-nnNicoNico Favicon-ytYouTube
謎ゲヌでRTAを走るな (Nazo Gee de RTA o Hashiru na) Favicon-ytYouTube Favicon-bbbilibili
トラブルトラブル (Troubles! Troubles!!) Favicon-nnNicoNico Favicon-ytYouTube

Synthesizer V AI[]

Demonstrations

ハルノ寂寞 (Haru no Sekibaku) Favicon-ytYouTube
時を巻き戻さないで (Toki o Makimodosanaide) Favicon-ytYouTube Favicon-bbbilibili
FLASH BACK LYRICS - Full Version Favicon-ytYouTube Favicon-bbbilibili
ハルカれ゚ンダヌ (Harukaze Ender) Favicon-nnNicoNico Favicon-ytYouTube Favicon-bbbilibili
りツロむ (Utsuroi) Favicon-nnNicoNico Favicon-ytYouTube
倧矩名分 (Taigimeibun) Favicon-nnNicoNico Favicon-ytYouTube Favicon-bbbilibili
サむバヌノォむス・ゲヌミングガヌル (Cyber Voice Gaming Girl) Favicon-ytYouTube Favicon-bbbilibili
侖界侭 笑顔になれ (Sekaijuu Egao ni Nare!) Favicon-ytYouTube Favicon-bbbilibili
トラブルトラブル (Troubles! Troubles!!) Favicon-nnNicoNico Favicon-ytYouTube

Voice Databases[]

Product Information
Optimum
  Genre: Band Music, Rock, & Pop  Range: C4 ~ G5  Pitch Group: C#4, F4, A#4, C5 (falsetto)[44]

Versions
  Lite Version/FLT Available?: Yes (Lite)  Starter Pack Available?: Yes  Web Version Available?: No

Package details as noted:
Maki is a feminine Japanese voice database voiced by Manami Tanaka. She is noted to have a fast attack and articulation, as well as a clear, energetic, and cute voice.[45] According to AH-Software, this voice database is suitable for band music, rock songs with fast and good-paced tempos, as well as bright and pop-like idol songs. The voice database would make a compatible back vocal.

Phonetic notes as noted:
  • Phoneme format: Romaji
  • Additional voice files are included with Maki's CeVIO AI Talk Voice or Synthesizer V AI voice database. There are over 2000 audio files to use for a wide variety of genres.

Software issues as noted:
  • As Maki's Synthesizer V voice databases were voiced by Manami Tanaka instead of Tomoe Tamiyasu, she may not sound the same as her VOICEROID voicebanks.
    • As an alternative, her CeVIO AI talk voicebank could be used in collaboration with the Synthesizer V voice databases as these share the same voice actress.
  • As the Lite voice databases are generally restricted to monopitch (one pitch) only, Maki's range is noted to be F4 in this version.

System requirements as noted:

Hardware Requirements:

  • CPU:
    • Intel Core series 4th generation i5 (i5-4xxx) or higher
    • AMD Athlon X4 845, Ryzen series or higher
  • RAM: 2GB or higher
  • Disk Space: 1 GB or higher (for installing one voice database)
    • The amount of space required depends on the number of voice databases installed.
  • Display: 1280 x 800 or higher

Software Requirements:

  • Operating System:
    • Windows 10/8.1
    • Mac OS X: 10.11 or higher
    • Linux Ubuntu 16.4 or higher

Other:

  • DVD-ROM Drive (physical edition only)
  • Sound card
  • Internet connection is necessary for activation and obtaining updaters.

License agreements as noted:
  • AH-Software's End User License Agreement - Japanese
  • AH-Software's End User License Agreement - English
  • Regarding the Lite version:
    • AH-Software does not accept technical inquiries regarding free software nor do they guarantee or support the operation of all free software.
    • AH-Software is not liable for any damages (including loss of data) caused by using free software. Users are cautioned to use the free software at their own risk.
    • The program may not be transferred, sold, lent, distributed or rented without AH-Software's permission, regardless of whether it is paid or free of charge.
    • Reverse engineering, including modification, decompilation, and disassembly, of their program for any purpose is prohibited.
    • Tsurumaki Maki Standard Lite may not be used commercially in any way
    • When using the Lite version of this voice database, "This work uses the Lite version" must be mentioned on any uploads.

Voice database sample

Product Information
Optimum
  Genre: Band Music, Rock, & Pop  Range: A3 ~ D#5

Versions
  Lite Version/FLT Available?: Yes (Lite)  Starter Pack Available?: Yes  Web Version Available?: No

Package details as noted:
Maki is a feminine Japanese voice database based on the singing style of Manami Tanaka. She is noted to have a fast attack and articulation, as well as a clear, energetic, and cute voice. According to AH-Software, this voice database is suitable for band music, rock songs with fast and good-paced tempos, as well as bright and pop-like idol songs. The voice database would make a compatible back vocal. As AI voice database, Maki is able to sing with a more human-like and realistic voice.

Vocal traits as noted:
  • As per the Synthesizer V Studio 1.7.0 update launched on July 21, 2022, through High Dynamics Voice Models (HDVM), which later migrated to Diffusion Probabilistic Models (DPM) per the 1.8.0b1 update on November 10,[47] AI voice databases may use AI Retakes to create multiple "takes" of a sung section with variations in pitch, dynamics, and timbre. This replicates the randomness of human vocalists, adds a more realistic feel, and allows users to find an ideal vocal without the need for "laborious tuning." This feature is only available in the Synthesizer V Studio Pro Editor.[48][49]
    • This does not apply to the Lite version.

Phonetic notes as noted:
  • Phoneme format: Romaji
  • Additional voice files are included with Maki's CeVIO AI Talk Voice or Synthesizer V AI voice database. There are over 2000 audio files to use for a wide variety of genres.
  • On December 23, 2021, with the announcement of Synthesizer V Studio 1.5.0, all AI voice databases would be able to use cross-lingual singing synthesis. This allows Maki's Japanese AI to be able to sing in not only Japanese but also in English and Mandarin Chinese using this new feature.[51] Since the release of her v115b1 update on June 21, 2023, she can also sing in Cantonese Chinese with this feature; since her v118 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 Editor.
    • This does not apply to the Lite version, thus restricting the voice database to Japanese only.

Vocal Modes as noted (Synthesizer V Studio Pro Editor only):
  • As of July 21, 2022, the paid version of Tsurumaki Maki AI became compatible with the Vocal Mode function introduced in Synthesizer V Studio 1.6.0. Her v111 update included five variations:
    • "Adult"
    • "Breathy"
    • "Power_Pop"
    • "Twangy"
    • "Whisper"

Software issues as noted:
  • As Maki's Synthesizer V voice databases were voiced by Manami Tanaka instead of Tomoe Tamiyasu, she may not sound the same as her VOICEROID voicebanks.
    • As an alternative, her CeVIO AI talk voicebank could be used in collaboration with the Synthesizer V voice databases as these share the same voice actress.

System requirements as noted:

Hardware Requirements:

  • CPU:
    • Intel Core series 4th generation i5 (i5-4xxx) or higher
    • AMD Athlon X4 845, Ryzen series or higher
  • RAM: 2GB or higher
  • Disk Space: 1 GB or higher (for installing one voice database)
    • The amount of space required depends on the number of voice databases installed.
  • Display: 1280 x 800 or higher

Software Requirements:

  • Operating System:
    • Windows 10/8.1
    • Mac OS X: 10.11 or higher
    • Linux Ubuntu 16.4 or higher

Other:

  • DVD-ROM Drive (physical edition only)
  • Sound card
  • Internet connection is necessary for activation and obtaining updaters.

License agreements as noted:
  • AH-Software's End User License Agreement - Japanese
  • AH-Software's End User License Agreement - English
  • Regarding the Lite version:
    • AH-Software does not accept technical inquiries regarding free software nor do they guarantee or support the operation of all free software.
    • AH-Software is not liable for any damages (including loss of data) caused by using free software. Users are cautioned to use the free software at their own risk.
    • The program may not be transferred, sold, lent, distributed or rented without AH-Software's permission, regardless of whether it is paid or free of charge.
    • Reverse engineering, including modification, decompilation, and disassembly, of their program for any purpose is prohibited.
    • Tsurumaki Maki AI Lite may not be used commercially in any way
    • When using the Lite version of this voice database, "This work uses the Lite version" must be mentioned on any uploads.

Voice database sample

References[]

  1. ↑ https://www.youtube.com/watch?v=EmqBPc-ps4A
  2. ↑ https://www.youtube.com/watch?v=JMCKyH7Btls
  3. ↑ https://twitter.com/tammy_now/status/1342495702471962625
  4. ↑ https://twitter.com/Rylitah/status/1342616819874586624 - Livestream summary by @Rylitah
  5. ↑ https://www.ah-soft.com/images/products/maki/seiyuu.jpg
  6. ↑ https://twitter.com/maki_gyungyun/status/1377099522464096259
  7. ↑ https://twitter.com/maki_gyungyun/status/1392677212273340421
  8. ↑ https://twitter.com/maki_gyungyun/status/1400350915647860741
  9. ↑ https://twitter.com/ahsoft/status/1507273221976260609
  10. ↑ https://www.youtube.com/watch?v=zJVmg0cIZrM
  11. ↑ https://twitter.com/ahsoft/status/1542711016860962816
  12. ↑ https://twitter.com/dreamtonics_en/status/1550050403613835264
  13. ↑ https://www.dtmstation.com/wp-content/uploads/2022/07/Snap1-1.png
  14. ↑ https://twitter.com/dreamtonics_en/status/1550520904291012609
  15. ↑ https://twitter.com/dreamtonics_en/status/1550520905868009472
  16. ↑ https://twitter.com/ahsoft/status/1550385484027035649
  17. ↑ https://twitter.com/dreamtonics_en/status/1550520907159851009
  18. ↑ https://twitter.com/ahsoft/status/1550385686389616640
  19. ↑ https://dreamtonics.com/en/cross-lingual-support-for-synthesizer-v-ai/
  20. ↑ https://dreamtonics.com/en/synthesizer-v-studio-1-7-0-update-ai-retakes-feature/
  21. ↑ https://twitter.com/ahsoft/status/1551774834983866368
  22. ↑ https://dreamtonics.com/en/synthesizer-v-studio-1-8-0b1-update/
  23. ↑ https://dreamtonics.com/en/synthesizer-v-studio-1-8-0-final-update/
  24. ↑ https://twitter.com/ahsoft/status/1595674717200916481/
  25. ↑ https://dreamtonics.com/synthesizer-v-studio-1-9-0-final-update/
  26. ↑ https://twitter.com/dreamtonics_en/status/1671427830629154816
  27. ↑ https://www.bilibili.com/read/cv24826703/
  28. ↑ https://twitter.com/ahsoft/status/1676865674898206720
  29. ↑ https://twitter.com/dreamtonics_en/status/1686648078571655168
  30. ↑ https://t.bilibili.com/825177687051993121
  31. ↑ https://dreamtonics.com/synthesizer-v-studio-1-10-0b1-update-enhancing-pitch-generation-with-user-feedback/
  32. ↑ https://twitter.com/ahsoft/status/1686653272474738689
  33. ↑ https://twitter.com/dreamtonics_en/status/1707304150059639108
  34. ↑ https://dreamtonics.com/synthesizer-v-studio-1-10-0b2-update/
  35. ↑ https://twitter.com/ahsoft/status/1707304906535956719
  36. ↑ https://dreamtonics.com/synthesizer-v-studio-1-10-0-final-update/
  37. ↑ https://twitter.com/ahsoft/status/1714919114182181140
  38. ↑ https://twitter.com/ahsoft/status/1717451110305366047
  39. ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0-update/
  40. ↑ https://twitter.com/ahsoft/status/1775800933538320621/photo/4
  41. ↑ https://twitter.com/ahsoft/status/1405724076769910792
  42. ↑ https://twitter.com/ahsoft/status/1405725227305213955
  43. ↑ informal title
  44. ↑ https://www.ah-soft.com/synth-v/maki/index.html
  45. ↑ https://dreamtonics.com/en/synthesizerv/
  46. ↑ https://twitter.com/maki_gyungyun/status/1537730091786305537
  47. ↑ https://dreamtonics.com/en/synthesizer-v-studio-1-8-0-final-update/
  48. ↑ https://twitter.com/dreamtonics_en/status/1550048543624564736
  49. ↑ https://twitter.com/dreamtonics_en/status/1550048543624564736
  50. ↑ https://twitter.com/maki_gyungyun/status/1537730091786305537
  51. ↑ https://twitter.com/dreamtonics_en/status/1473941453810577410

Navigation[]

Advertisement