An Xiao (Synthesizer V Studio)

An Xiao	SynthV Studio	|	Originals	|	Gallery

An Xiao (Synthesizer V Studio)
Product Information
Company	Dreamtonics Co., Ltd.
Release Date(s)	May 4, 2022
Status	Released
System Requirements	Windows, MacOS, Linux
Base Language(s)	Mandarin Chinese
Type	Synthesizer V Studio (AI)
Licensing	Proprietary
Affiliations	AH-Software Co. Ltd.
Product Page	Digital copies: AHS Store AHS Store (Starter Pack) AHS Store (Starter Pack; user discount) animate GAMES DLsite DMM GAMES Dreamtonics (International) Dreamtonics (Intl.) (Bundle Set) Dreamtonics (Mainland China) Dreamtonics (Mainland China) (Bundle Set) Dwango JP Store SONICWIRE Vector PC Shop

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 May 4, 2022, An Xiao was suddenly introduced with one demo on bilibili and was released simultaneously on the official Dreamtonics taobao shop and International Store. From then until May 19, he was sold at a discounted price of 479 yuan as a standalone and 899 yuan as a bundle pack with the Synthesizer V Studio editor on taobao.

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. 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.

On July 21, An Xiao 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). 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; as a workaround to stabilize the voice output, they offered these steps below:

• 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 An Xiao (as well as other affected AI voice databases) by logging in to their store download website.

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

Updates

An Xiao AI v101 - May 26, 2022 

A free update for An Xiao was released. No details were provided regarding any changes.

An Xiao AI v103 - July 21, 2022 

A free update for An Xiao 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.

An Xiao AI v104b1 - November 10, 2022 

A free update for An Xiao was released following the Synthesizer V Studio 1.8.0b1 update. This enables him to use the new Diffusion Probabilistic Models (DPM) feature.

An Xiao AI v104 - November 24, 2022 

Final version update compatible for Synthesizer V Studio 1.8.0 which enables An Xiao to use the new Diffusion Probabilistic Models (DPM) feature if the beta version was not installed previously.

An Xiao AI v105b - February 6, 2023 

A free update for An Xiao 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.

An Xiao AI v105 - February 16, 2023 

Final version update compatible for Synthesizer V Studio 1.8.1 which improves the neural vocoder for all male vocals, including An Xiao, resulting in an enhanced sound quality in the bass range.

An Xiao AI v106b1 - April 18, 2023 

A free update for An Xiao 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.

An Xiao AI v106b2 - May 23, 2023 

A free update for An Xiao 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.

An Xiao AI v106 - June 21 2023 

Final version update compatible for Synthesizer V Studio 1.9.0 which enables An Xiao 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.

An Xiao AI v107b1 - August 2, 2023 

A free update for An Xiao 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.

An Xiao AI v107b2 - September 28, 2023 

A free update for An Xiao 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.

An Xiao AI v107 - October 19, 2023 

Final version update compatible for Synthesizer V Studio 1.10.0 which enables An Xiao 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.

An Xiao AI v108 - October 26, 2023 

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

An Xiao AI v109b1 - December 18, 2023 

A free update for An Xiao 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.

An Xiao AI v109 - April 4, 2024 

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

Voice Database Information

Demonstrations

Demonstrations
远方有星辰 (Yuǎnfāng Yǒu Xīngchén)	YouTube bilibili
远方有星辰 (Yuǎnfāng Yǒu Xīngchén - 2023 Version ft. Mo Chen, Xuan Yu, and D-Lin	bilibili
远方有星辰 (Yuǎnfāng Yǒu Xīngchén - 2024 Version	bilibili

Dreamtonics Recommended Songs Playlist
伯虎说 (Bó Hǔ Shuō) ft. Cheng Xiao & Feng Yi	bilibili

Voice Databases

Product Information

Optimum

  Range: C#3 ~ D#4

Versions

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

Package details as noted:

An Xiao 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 noted to have "a full and bright voice with no lack of passion". Like Mo Chen before him, he was marketed to promote the new functionality and experience of Synthesizer V Studio 1.6.0's Vocal Mode.

Vocal traits as noted:

• According to Dreamtonics, he has a flexible range that would provide high-quality results in his tenor and bass tones.
• He was advertised to be capable of "bringing an impressive level of emotion and expression".
• 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, 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.

Phonetic notes as noted:

• Phonetic format: X-SAMPA
• Through Cross-lingual Singing Synthesis, An Xiao 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):

• An Xiao comes with five variations:
  • "Airy"
  • "Chest"
  • "Open"
  • "Power"
  • "Soft"

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:

• Dreamtonics Co., Ltd.'s End User License Agreement - Japanese
• Dreamtonics Co., Ltd.'s End User License Agreement - English
• Dreamtonics Co., Ltd.'s End User License Agreement - Simplified Chinese

Voice database sample

• An Xiao AI Solfège:
  File:An Xiao AI Solfege.ogg
  • Vocal Mode Solfèges:
    • "Airy":
      File:An Xiao AI Airy.ogg
    • "Chest":
      File:An Xiao AI Chest.ogg
    • "Open":
      File:An Xiao AI Open.ogg
    • "Power":
      File:An Xiao AI Power.ogg
    • "Soft":
      File:An Xiao AI Soft.ogg