Xia Yu Yao AI《遙YAO》Crowdfund Campaign and Development Updates

Adding to this, not every company is obligated to show off crosslingual in demonstration. Seika, Ryo, Mo Chen, An Xiao, and Feng Yi did not. Karin did, but they mistakingly used her Japanese when trying to demonstrate Mandarin and didn’t replay it with Mandarin settings and continued on with the stream, so she ended up not having a proper Mandarin demonstration.

The entire point of crosslingual is to make these vocals an option for those languages. Dreamtonics, when introducing the function, said that it is supposed to make the voice fluent in all 3 languages. This benefits everyone who wanted the voice in a specific language but either don’t want to force tune it via phonemes (for tuners), as well as voice providers/companies who were not comfortable producing a voicebank in languages they were not familiar with.

I want to strongly point out that “fluent” does not mean “without accents”. That is something I really disliked when people were putting down “non-native language voicebanks” (Macne Nana English, Meiko English, Luo Tianyi Japanese, etc) and to be honest, when talking about people in real life (especially the latter is rude. People work very hard to learn as much as they can just to communicate in a language they are not native in). It was never promised that the vocals will sing “like a native”, just that they can sing in those languages fluidly and to make it possible for them to do it without having to record those specific languages. I don’t expect Kevin to have “accent-less” Chinese or Japanese. He sounds like an English vocal singing Japanese and Chinese in an American accent. Karin sounds and is a Japanese vocal singing in English and Chinese with a Japanese accent. And in OP’s case, An Xiao sounds like a Chinese vocal singing in English and Japanese with a Chinese accent. And unless they have more data in the other languages aside from default to improve the vocal even further (like Xingchen, and from what was announced, Weina), the accents /might/ be more prominent the less data it has. And to be honest, some people find accents very charming and just want the vocal to be able to sing it in the language they want, accent or not.

Honestly, considering how often I’ve seen comments asking for Utatane Piko English and Gackpoid English/Chinese all those years ago on Vocaloid Wiki and other places, this feature is basically an answer to this kind of request. It even happened for SOLARIA when one of the FAQ was about her getting a Japanese voice database and Eclipsed Sounds said that they couldn’t because Emma Rowley didn’t know the language well enough to produce a quality bank.

For Yuyao, it wouldn’t be unreasonable to expect a Taiwanese accent across all three languages.

Long story short, you buy a vocal built for a specific language and that’s what you get. They’re going to be accented in the other languages. They’re not always going to be “perfect”. If you’re not willing to work with the accent, the vocal probably isn’t for you unfortunately.


Yuyao is finally (re)confirmed to be SynthV AI hahaha

They also opened pre-orders for her digital version if anyone is interested in that.

By the way, here is an example of Mi Yang, the voice actress for Xia Yuyao, speaking as her in a mobile game as a crossover feature. Please keep in mind that this video was posted in March 2015, not very long since she released as an UTAU, so it might not paint an accurate idea of how Yuyao would sound now as a Synthesizer V AI singing vocal. Mi Yang seems to keep herself private, so we don’t really know what her experience is like now compared to back then. She was, however, confirmed to be an aspiring voice actress at the time of Yuyao’s audition back in 2014, so really, who knows? .w./

Unfortunately, I don’t know if there’s any examples of Mi Yang singing as Yuyao as that would be more helpful to figure out how that might sound in Synthesizer V AI (even if it’s an old clip or not).


First recordings have been completed and delivered for data processing. More recordings are expected for this month.


It looks like the second recordings have been completed, and they expect to only need one more session after this.

It’s hard to say what that means as far as progress for the project as a whole, but it is interesting to see that three recording sessions can provide enough samples to create an AI voice.

They also mentioned in today’s tweet that they are planning to make a lite version!


All of the sound samples have been recorded and were sent to Dreamtonics for processing as of last week! Unfortunately, Mi Yang and the recording engineers caught COVID a few days ago, but have recovered now.

Also some progress on the merchandise: the design drafts were sent to the manufacturers and started production.

This was just brought up to me, but it looks like her box was also updated!


Beta testing applications are open until November 25!

Approved beta testers will be expected to provide raw samples (at least 2 minutes long) and feedback about any issues with the voice database. The testing period will run from December 1 to December 10.

I think from this tweet, it can be interpreted that she might not release on time for the expected November period. ^^; They haven’t officially said they’re moving the date, but I think it’s also fair to keep it in mind. Beta testing/demos don’t usually come after the voice releases after all.


I’ve noticed that Dreamtonics has never acknowledged Xia Yu Yao? Like yes, they haven’t done a genbu 2 electric boogaloo, but they said that official business collaboration would be announced on their website/social media, and from what i see (which is nothing), they haven’t?

It’s interesting to see a somewhat strained relationship from the outset…

Yuyao will be delayed a little longer since the Synthesizer V Studio 1.8.0 update went up and introduced Diffusion Probabilistic Models (DPM). As VOICEMITH wants her to be equiped with the newest update to present better singing quality, the beta test version is now being delayed to mid-December, with the final version to be expected in early January 2023.


This is good to hear. I’m excited for her release but I definitely think it’s a positive sign that they’re able/willing to take the extra time to deliver a stronger product.


Choosing the beta testers will take time as more than 300 people applied! Estimated dates remain the same: beta tests in mid-December and an official release for early January 2023.

Also check out her boxes!


Crowdfund backers will begin receiving their goods, INCLUDING the physical boxed copy of Xia Yuyao, soon as VOICEMITH began distributing them on the 29th! Reminder to those who pledged for the voice database, you won’t receive them until the production is finished!



Got a new update today from Xia Yuyao’s Twitter! Some major takeaways:

  • The sampling in the high range is based on the characteristics of Mi Yang. Mi Yang is best at being a soft voice in the middle range, so the AI voice database would replicate that well. In UTAU, the upper range is a very strong voice, which isn’t present in the Synthesizer V version. That said, for a stronger sound in the Synth V version, it’s recommended to adjust Vocal Mode(s) and the tension parameters.
  • The pitch above C5 is the falsetto range.
  • It was reminded that the recordings were in Mandarin Chinese. Mi Yang was noted that she isn’t good at Japanese and English songs. That said, Yuyao’s Japanese and English may not meet the standards of these languages’ articulation and pronunciation. It’s important to keep in mind that Yuyao’s accent will be Taiwanese.
  • After the beta testers’ reviews, Voicemith let Dreamtonics know about the opinions. Voicemith will begin making revisions based on the reviews.
  • Judging by the image, Yuyao seems to have five vocal modes: Dark, Soft, Solid, Whisper, Sweet

Voicesmith has uploaded a short demonstration comparing Xia Yu Yao’s default voice and five vocal modes (Soft, Whisper, Solid, Sweet, and Dark) using two different phrases:


Additionally, the latest video shows various short covers of original songs that were made with prior versions of Xia Yu Yao.

The video also shows the various Parameter and Vocal Mode settings used for each part.


For everyone who supported the digital download or physical box pledges, it sounds like they’ll be able to download and use the voice database early? I’m not sure if I’m interpreting this correctly.

Also, there will be 2 original songs, mobile wallpapers, and desktop wallpapers distributed. The methods are different depending on if you supported physical or digital. Physical supporters will be able to get these via the QR code on the music download card. Digital supporters will get these via email.


New demo! A cover by Mouzhize of " 雨林"!

EDIT: It seems that the beta testers are allowed to start posting content. There’s a bunch of songs available already! The one I just showed and this one are currently the only ones VOICEMITH shared on Twitter, but feel free to look for more (or if you were selected for beta and wanted to share it yourself) and add them to the thread .w./

“星路” (Galaxy Stairway) cover by NiSei

EDIT2: One of the beta testers volunteered to keep track of beta tests posted on YouTube via this playlist. (Won’t post it as an embed; this forum would only post the first video of the list)

EDIT3: Looks like the official webpage for Yuyao was updated to include the SynthV design. She also has a new ToU page for both her UTAU and SynthV libraries


Voicemith’s store page indicates that the preorder period will be from Jan 19 to Feb 12, and there will be a preorder discount.

The discount looks to be 25%, at a price of US$59.90 compared to the full price of US$79.

Taiwan only:

International purchasing with PayPal:


Relevant link and email addresses for Voicemith have also been added here: [Guide] How to Purchase, Download, and Install Synthesizer V Studio and Voice Databases - claire の #18

(edit: pre-order details were placeholders and have been updated accordingly)


An official English demo by CircusP has just premiered on YouTube! This should give international buyers a better idea of Xia Yu Yao’s cross-lingual capabilities.


Details about Yuyao’s final release!

The physical boxes for the crowdfund version and the general release are different. The crowdfund version comes with a mobile phone holder. Sponsors also receive 10 original songs featuring her voice (2 brand new and 8 self-covers) and downloadable wallpapers. Other than that, the content is not different.

Sponsors get the voice database early on January 18. The pre-order period for the general public will be open on January 19 and will run with a discount for the digital version (physical will not be having a discount). The voice database will be officially released on January 30!


Forgot to have this updated, but there’s details about her pre-order.

  1. Because of the cash flow system of Taiwanese stores unable to support overseas credit cards, overseas customers have to use payment methods provided by Paypal to buy her. The link for this product is here

  2. Based on past experiences, there were a lot of issues with shipping overseas (such as delayed receipts, expensive shipping fees, damaged packaging, etc). Because of that, the physical edition will only be available for purchase in Taiwan.

This wasn’t mentioned in the tweet, but there is also an official distributor via Taobao, so you can use Taobao proxies (like ParcelUp) for that. It’s hosted by VC Palace Group, a very reliable shop known for hosting Chinese voice synthesis (VOCALOID especially) doujinshi goods.

  1. There’s no CD in the physical copies. The voice still has to be obtained via downloading (QR code)