SynthV Wiki
Advertisement
Mo Chen
SynthV Studio
|
Originals
|
Gallery

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

History[]

On November 5, 2021, during the Q/A section of Qing Su's livestream, when asked about producing a masculine Mandarin Chinese voice database, Dreamtonics confirmed that it was being considered, but no information could be provided.[1]

2022[]

On March 23, 2022, Dreamtonics posted a poem on the official bilibili account, then noted that an announcement would be made on March 25 at 17:00 in China.[2] On March 25, MAN-M2, a new Mandarin Chinese masculine AI voice database, was revealed through his first demo. It was also announced in the description that Dreamtonics was launching a contest to select a name for him from March 25 to April 1. His name was to be two to three Chinese characters long and should reflect his vocal characteristics. Users were to share the video, follow the official Dreamtonics bilibili account, and comment with the name they've created. The selected name would be revealed on April 3 and the selected participant would also be presented with a set of Synthesizer V Studio Pro and MAN-M2's library.[3]

On April 1, Dreamtonics announced that the name contest officially closed and noted that there were 1,268 comments in total at the time. They remarked that the names that were submitted were varied, from traditional to more modern takes with much expectations and wishes put into each one. The winning name was still expected to be announced on April 3 and the product's pre-order period would be scheduled simultaneously.[4]

On April 3, the winning name was announced to be "Mo Chen" (默辰), which was submitted by Shan Shu (善树). Mo Chen was then confirmed to be made available for pre-order on Dreamtonics's taobao shop and would release on April 15. During the pre-order period, Mo Chen was discounted for 479 yuan while his starter pack was discounted for 899 yuan. Regarding a lite version, Mo Chen would not be having one. Instead, it was noted that people could fully understand his performance and style through the test and demo tracks provided by Dreamtonics's cooperation with professional creators prior to purchasing. In addition, a raffle was launched for five users to potentially win a copy of Synthesizer V Studio Pro and Mo Chen's voice database. Participants had to follow Dreamtonics's account and forward the announcement post. Winners were selected on his release date. For users who already bought Mo Chen, they were entitled to a full refund of their purchase.[5]

Mo Chen was released a week early on April 9 and was made available on the Dreamtonics international store.[6][7] On June 13, Dreamtonics announced that they launched a new official store for the Chinese market built on WeChat's Mini Program. Users would be able to purchase the Synthesizer V Studio Pro editor and Dreamtonics' vocals through the application in a convenient manner, enjoying the automatic real-time distribution shopping experience. From June 13 to July 13, users were able to take advantage of unlimited 10% off coupons in the new store.[8] It was later clarified that the decision to open this new shopping option was made due to Taobao's new restrictions on the sales of virtual goods as of April 2022, especially for restrictions on shipments without logistics since virtual goods would need to be delivered via email.[9]

On July 21, Mo Chen 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).[10] 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 his voice database (after updating it to v103). 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;[11] as a workaround to stabilize the voice output, they offered these steps below:[12]

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

Responding to requests from users, Dreamtonics made available for download that same day rolled-back versions of Mo Chen (as well as other affected AI voice databases) by logging in to their store download website.[13]

On October 7, it was announced that AH-Software Co. Ltd. would begin distributing digital versions of Mo Chen, Qing Su, An Xiao, and Feng Yi, as well as Yuma and Natalie, the newest Dreamtonics vocals.[14]

Updates[]

Mo Chen AI v103 - July 21, 2022[15] 
A free update for Mo Chen was released following the Synthesizer V Studio 1.7.0 update. This enables him to use the new High Dynamics Voice Models and AI Retakes features.
Mo Chen AI v104b1 - November 10, 2022[16] 
A free update for Mo Chen was released following the Synthesizer V Studio 1.8.0b1 update. This enables him to use the new Diffusion Probabilistic Models (DPM) feature.
Mo Chen AI v104 - November 24, 2022[17][18] 
Final version update compatible for Synthesizer V Studio 1.8.0 which enables Mo Chen to use the new Diffusion Probabilistic Models (DPM) feature if the beta version was not installed previously.
Mo Chen AI v105b - February 6, 2023[19][20] 
A free update for Mo Chen was released following the Synthesizer V Studio 1.8.1b1 update. This improved the neural vocoder for male vocals in general, which results in an enhanced sound quality in the bass range.
Mo Chen AI v105 - February 16, 2023[21][22] 
Final version update compatible for Synthesizer V Studio 1.8.1 which improves the neural vocoder for all male vocals, including Mo Chen, resulting in an enhanced sound quality in the bass range.
Mo Chen AI v106b1 - April 18, 2023[23][24] 
A free update for Mo Chen was released following the Synthesizer V Studio 1.9.0b1 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.
Mo Chen AI v106b2 - May 23, 2023[25][26] 
A free update for Mo Chen was released following the Synthesizer V Studio 1.9.0b2 update. This version of the vocal allowed for compatibility with the engine's second beta, which focused on rectifying several design issues identified by the user base in the 1.9.0b1 post-release survey.
Mo Chen AI v106 - June 21 2023[27][28] 
Final version update compatible for Synthesizer V Studio 1.9.0 which enables Mo Chen 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.
Mo Chen AI v107b1 - August 2, 2023[29][30][31][32] 
A free update for Mo Chen 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.
Mo Chen AI v107b2 - September 28, 2023[33][34][35] 
A free update for Mo Chen 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.
Mo Chen AI v107 - October 19, 2023[36][37] 
Final version update compatible for Synthesizer V Studio 1.10.0 which enables Mo Chen to use Reinforcement Learning from Human Feedback (RLHF) as well as other enhancements (as listed in v107b1 and v107b2's notes) if the beta version was not installed previously.
Mo Chen AI v108 - October 26, 2023[38] 
A free update for Mo Chen was released that added support for the Japanese language to the rap feature.
Mo Chen AI v109b1 - December 18, 2023[39] 
A free update for Mo Chen 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.
Mo Chen AI v109 - April 4, 2024[40][41] 
Final version update compatible for Synthesizer V Studio 1.11.0 which enables Mo Chen to sing in Spanish through Cross-lingual Singing Synthesis if the beta version was not installed previously.

Voice Database Information[]

Demonstrations[]

Demonstrations

这感觉 (Zhè Gǎnjué) ft. Qing Su Favicon-ytYouTube Favicon-bbbilibili
给你给我 (Gěi Nǐ Gěi Wǒ) Favicon-bbbilibili
悬溺 (Xuán Nì) Favicon-bbbilibili
匿名的好友 (Nìmíng de Hǎoyǒu) Favicon-bbbilibili
Susan说 (Susan Shuō) Favicon-bbbilibili
水星记 (Shuǐxīng Jì) Favicon-bbbilibili

Voice Databases[]

Product Information
Optimum
  Genre: C-Pop  Range: D#3 ~ D#4[42]

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

Package details as noted:
Mo Chen is a masculine Mandarin Chinese voice database. As expected of an AI voice database, this enables him to sing with a more human-like and realistic voice. He was also marketed to showcase the new functionality and experience of Synthesizer V Studio 1.6.0, as it was noted that through the new Vocal Mode, creators would experience a new vocal range and powerful dynamic effects.

Vocal traits as noted:
  • On his product page, it was mentioned that Mo Chen's vocal range was designed to fit the characteristics of C-Pop style.
  • According to Dreamtonics, his mature and stable voice presents a unique tone that stands out in his mid-bass range.
  • He was advertised to have clear and accurate pronunciation, making him ideal for testing out original lyrics.
  • 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,[43] 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, adding 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.[44][45]

Phonetic notes as noted:
  • Phonetic format: X-SAMPA
  • Through Cross-lingual Singing Synthesis, Mo Chen is able to sing in not only Mandarin Chinese but also in English and Japanese. Since the release of his v106b1 update on April 18, 2023, he can also sing in Cantonese Chinese with this feature; since his v109b1 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.

Vocal Modes as noted (Synthesizer V Studio Pro Editor only):
  • Mo Chen comes with three variations:
    • "Open"
    • "Soft"
    • "Clear"
  • These were advertised to provide great coverage for other genres such as pop, folk, and blues.

System requirements as noted:
  • OS: Microsoft Windows 11 / 10 / 8.1 (64 bit) and up; macOS 10.11 (El Capitan) and up; Ubuntu 18.04 (64 bit) and up
  • CPU: Intel Core i5 or higher, or equivalent AMD processor.
    • 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

License agreements as noted:

Voice database sample


References[]

  1. https://www.bilibili.com/video/BV11f4y1u7Sw
  2. https://t.bilibili.com/640827185283727369
  3. https://t.bilibili.com/641498050565505064
  4. https://t.bilibili.com/644073824077217832
  5. https://t.bilibili.com/644865158914506789
  6. https://www.bilibili.com/read/cv16052860
  7. https://twitter.com/dreamtonics_en/status/1512718709864820736
  8. https://t.bilibili.com/671200609838301200
  9. https://www.bilibili.com/read/cv17082866
  10. https://twitter.com/dreamtonics_en/status/1550050403613835264
  11. https://twitter.com/dreamtonics_en/status/1550520904291012609
  12. https://twitter.com/dreamtonics_en/status/1550520905868009472
  13. https://twitter.com/dreamtonics_en/status/1550520907159851009
  14. https://www.ah-soft.com/press/ah-soft/20221007.html
  15. https://dreamtonics.com/en/synthesizer-v-studio-1-7-0-update-ai-retakes-feature/
  16. https://dreamtonics.com/en/synthesizer-v-studio-1-8-0b1-update/
  17. https://dreamtonics.com/en/synthesizer-v-studio-1-8-0-final-update/
  18. https://twitter.com/ahsoft/status/1595674717200916481/
  19. https://dreamtonics.com/en/synthesizer-v-studio-1-8-1b1-update/
  20. https://twitter.com/dreamtonics_en/status/1622505781265563648
  21. https://dreamtonics.com/synthesizer-v-studio-1-8-1-final-update/
  22. https://twitter.com/dreamtonics_en/status/1626100512675500033
  23. https://dreamtonics.com/synthesizer-v-studio-1-9-0b1-update-rap-cantonese-and-more/
  24. https://twitter.com/dreamtonics_en/status/1648235081608343552
  25. https://dreamtonics.com/synthesizer-v-studio-1-9-0b2-update/
  26. https://twitter.com/dreamtonics_en/status/1660888307482656771
  27. https://dreamtonics.com/synthesizer-v-studio-1-9-0-final-update/
  28. https://twitter.com/dreamtonics_en/status/1671427830629154816
  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/photo/1
  38. https://twitter.com/ahsoft/status/1717451110305366047
  39. https://dreamtonics.com/synthesizer-v-studio-1-11-0b2-update/
  40. https://dreamtonics.com/synthesizer-v-studio-1-11-0-update/
  41. https://twitter.com/ahsoft/status/1775800933538320621/photo/4
  42. https://img.alicdn.com/imgextra/i2/54187543/O1CN01M4nloo25akRXXXuMT_!!54187543.png - Mo Chen initially did not have a range listed upon release. This was added to his Taobao product page as of March 15, 2024
  43. https://dreamtonics.com/en/synthesizer-v-studio-1-8-0-final-update/
  44. https://twitter.com/dreamtonics_en/status/1550048543624564736
  45. https://twitter.com/dreamtonics_en/status/1550048543624564736

Navigation[]

Advertisement