Synthesizer V - Singing voice synth for Win/Linux/Mac (Free & Payware)

VST, AU, AAX, CLAP, etc. Plugin Virtual Instruments Discussion
Post Reply New Topic
RELATED
PRODUCTS

Post

Ran the SVS Pro updater and sure enough, SOLARIA was prompting to update to ver. 101 with the corrected EULA.

Good News! AUDIOLOGIE's ANRI AI also has an update (ver. 104), and that EULA has been fixed!

Old ANRI license txt
Article 2: User license
1. When the user uses this product, AUDIOLOGIE endows the user with nonexclusive rights which cannot be transferred or sub-licensed.
2. Natural person users can use the synthesized voice generated by or role copyright image included in this product under non-commercial or commercial situations for activities, creation, work spreading, publication, etc.
3. If the natural person users apply the synthesized voice generated by or role copyright image included in this product for commercial purpose, and the situation involves more than USD 5,000, Or if the user is Corporation or legal entity, the obligation to notify AUDIOLOGIE will occur. AUDIOLOGIE will sign additional User License Agreement with such users according to the users’ use purpose (licensing fees might be produced according to the agreement situations).
A. Use in commercial multimedia video works, including but not limited to advertising image, network video, animation, film, TV series, television program, and game, as well as all of the above situations can be deemed to use the synthesized voice generated by or role copyright image included in this product during expression and communication behaviors.
B. Use in commercial music products sold by the legal person, including but not limited to CD, DVD, disc, audio tape, MD, hard disk, flash memory, IC memory card, and other recording contents (hereinafter referred to as commercial music products) produced by the legal person or third party under its entrustment; all of the above situations can be deemed to download and use the contents published or provided after using the synthesized voice of this product.
C. Use in commercial advertisement, including but not limited to character’s name, brand name, package, publicity material, credits titles of video works, and sound source implanted in any machine of the legal person’s product; the products and functions expressed under this agreement are recorded in the tag type or advertisement behaviors which can be recognized by consumers.
D. Commercial derivative products, including but not limited to the use of the synthesized voice generated by or role copyright image included in this product on the package of related products including surrounding life, clothing decoration, cosmetics and skin care products, stationery, toy articles, food, 3C electronic products and publications.
E. When using behaviors beyond the scope listed under this agreement appear, application should be submitted to AUDIOLOGIE for use license.
F. When submitting the application for use license, please inquire through the contact information recorded in various official channels.
4. When the legal person and organizational users use the synthesized voice generated by or role copyright image included in this product, they are obliged to inform AUDIOLOGIE.
5. When the users provide the third party with the authorization for synthesized voice or role copyright image generated by this product based on the purpose or shapes in various terms, they should inform the third party of consulting AUDIOLOGIE.
New ANRI license txt
Article 2: User license
1. When the user uses this product, AUDIOLOGIE endows the user with nonexclusive rights which cannot be transferred or sub-licensed.
2. Natural person users can use the synthesized voice generated by or role copyright image included in this product under non-commercial or commercial situations for activities, creation, work spreading, publication, etc.
3. If the natural person users apply the role copyright image included in this product for commercial purpose, and the situation involves more than USD 5,000, Or if the user is Corporation or legal entity, the obligation to notify AUDIOLOGIE will occur. AUDIOLOGIE will sign additional User License Agreement with such users according to the users’ use purpose of the role copyright image (licensing fees might be produced according to the agreement situations).
A. Use in commercial multimedia video works, including but not limited to advertising image, network video, animation, film, TV series, television program, and game, as well as all of the above situations can be deemed to use the synthesized voice generated by or role copyright image included in this product during expression and communication behaviors.
B. Use in commercial music products sold by the legal person, including but not limited to CD, DVD, disc, audio tape, MD, hard disk, flash memory, IC memory card, and other recording contents (hereinafter referred to as commercial music products) produced by the legal person or third party under its entrustment; all of the above situations can be deemed to download and use the contents published or provided after using the synthesized voice of this product.
C. Use in commercial advertisement, including but not limited to character’s name, brand name, package, publicity material, credits titles of video works, and sound source implanted in any machine of the legal person’s product; the products and functions expressed under this agreement are recorded in the tag type or advertisement behaviors which can be recognized by consumers.
D. Commercial derivative products, including but not limited to the use of the synthesized voice generated by or role copyright image included in this product on the package of related products including surrounding life, clothing decoration, cosmetics and skin care products, stationery, toy articles, food, 3C electronic products and publications.
E. When using behaviors beyond the scope listed under this agreement appear, application should be submitted to AUDIOLOGIE for use license.
F. When submitting the application for use license, please inquire through the contact information recorded in various official channels.
4. When the legal person and organizational users use the synthesized voice generated by or role copyright image included in this product, they are obliged to inform AUDIOLOGIE.
5. When the users provide the third party with the authorization for synthesized voice or role copyright image generated by this product based on the purpose or shapes in various terms, they should inform the third party of consulting AUDIOLOGIE.
From the AUDIOLOGIE website:
https://audiologie.us/pages/about-us
All voice databases sold by AUDIOLOGIE are free for commercial usage, but commercial use of character image likeness requires permission from AUDIOLOGIE. For commercial usage of character designs, please email info[at]audiologie.us.
For fan-made derivative work, “commercial usage” is allowed if the production units and sales units of our characters’ likeness falls below a maximum production quantity of 100. Please note that Lite versions of Synthesizer V voice databases cannot be used commercially.
And now some Sad News: Eleanor AI's license is still the same.

Post

Good news re: Anri. I pre-ordered and was pretty annoyed that the license didn't match what was available on their website.
Softsynth addict and electronic music enthusiast.
"Destruction is the work of an afternoon. Creation is the work of a lifetime."

Post

That's great news Pelicanomicon.
The smallest minority on earth is the individual.
~A.Rand

Post

There's a sort of irony to companies not reading their own EULAs :wink:

(I kid, all you companies please make more voices)

If Cross-Lang hadn't happened I wouldn't bother to post this next news, but now that all AI voices are "English" voices...:

AHS is flexing again by releasing Kyomachi Seika's Standard and AI Lite vbs a week ahead of commercial launch. IIRC Dreamtonics took a while to mirror Tsurumaki Maki to their free downloads, so here is the link. Lite AIs can't use Cross-Lang, but at least you can test the sound:
  • https://www.ah-soft.com/trial/synth-v.html
  • Check the プログラム使用許諾に同意する usage agreement box at the bottom to reveal the downloads. All the zip file names are clearly written in English, click the appropriate ダウンロード download button.
I might get this eventually. The demo gave me a feeling that it would respond well to raised Gender for a more mature sound and the Lite bank seems to confirm it. It's breathy below C4 and clear above C5. By Tone Shifting up you can push the breathiness out of the lower registers and make it sound more powerful.
https://www.youtube.com/watch?v=j1AQJ6nenRI
Last edited by Pelicanomicon on Thu Jan 27, 2022 4:23 pm, edited 2 times in total.

Post

New Quadimension Muxin English demo, "Lovely" (Billie Eilish, Khalid). Tuned by Muxin's voice provider YuukaNeko
https://www.bilibili.com/video/BV1eF411n7UH

YuukaNeko also did a Muxin Chinese AI demo, "Solar Storm", that shows more of the voice's range.
https://www.bilibili.com/video/BV19P4y1E74n

Didn't note it earlier, but it looks like the Standard-derived AI voices will be marketed as "Plus"--Cangquiong Plus, Muxin Plus, etc. Muxin and Minus are the two Quadimension voices not sold on AniCute, hope that will change when the Plus upgrades come out.

Tips on pronouncing the Synth V Chinese voice names:
https://twitter.com/rice_deity/status/1 ... 1950528514

Post

Ms Muxin has a very sensual alto! In the Chinese 'Solar Storm', I think that those initial lowest notes sound a bit fake, or processed, though.

Maybe the voice could use a bit more 'tuning' when it comes to pronouncing end consonants such as 'T' and 'D' – she sings 'night' like 'nigh…' and 'hide' like 'hi…'. OTOH, she shares this deficiency with many live singers – not everyone can pronounce end consonants like Madeleine Peyroux…

Whatever nitpicks, Muxin sounds like a keeper. Any idea when she might be available?
If it were easy, anybody could do it!

Post

Spitfire31 wrote: Sun Jan 23, 2022 8:14 pm Maybe the voice could use a bit more 'tuning' when it comes to pronouncing end consonants such as 'T' and 'D' – she sings 'night' like 'nigh…' and 'hide' like 'hi…'.
It seems to be consistent with YuukaNeko's real-life singing style when he sings in English:
https://www.bilibili.com/video/BV1Tx411T7Be
But yea, probably something that could be made more distinct with tuning or mixing.
Spitfire31 wrote: Sun Jan 23, 2022 8:14 pm Any idea when she might be available?
Sadly no, it's just demos for now and Quadimension has four additional characters (Chiyu, Haiyi, Shian, Minus) to convert to AI so it might be a while. I'm honestly surprised that the current examples sound as good as they do given the different recording methods.

For those new to Synthesizer V, Muxin Standard is one of only two male voices available right now and sold only in China
https://www.youtube.com/watch?v=ooQjBEeOWeQ

The other is VOLOR/VirVox's Genbu Standard (Jpn)
https://www.youtube.com/watch?v=o1szm_J2jA0
If ppl are hoping for Genbu AI, there was a small drama about that last year. VirVox announced a crowdfund for it, but it turned out they did not have permission from Dreamtonics to develop. Dreamtonics had to issue a public statement:
https://twitter.com/dreamtonics_en/stat ... 4899956736

VirVox believed they had got the go ahead via 3rd party:
https://note.com/virvoxproject/n/n17f5051a2ea3

Post

Pelicanomicon wrote: Sun Jan 23, 2022 9:40 pmFor those new to Synthesizer V, Muxin Standard is one of only two male voices available right now and sold only in China
https://www.youtube.com/watch?v=ooQjBEeOWeQ
Oops! :oops: Mea culpa – I thought that Muxin was a lady alto…

Anyway, nice, expressive voice!
If it were easy, anybody could do it!

Post

Muxin's "character" is supposed to be quite young, so it's understandable :)

Post

Great stuff, thanks @Pelicanomicon!

I found this demo of five SV voicebanks doing a Spice Girls cover which is pretty impressive.
Even the rapped parts are very well done and the Chinese voicebanks do English so well!

https://www.youtube.com/watch?v=TotFdChJ7i0

Not surprised that Emvoice have slashed their prices!

Post

ZincT wrote: Mon Jan 24, 2022 11:04 am Not surprised that Emvoice have slashed their prices!
This! Am I glad that I kept my GAS under wraps after beta testing Lucy. That price level and you have to be connected. :hihi:

I wonder how long their server will remain on line. :roll:

SV Pro AI really is a quantum jump.
If it were easy, anybody could do it!

Post

Spitfire31 wrote: Mon Jan 24, 2022 11:26 am
ZincT wrote: Mon Jan 24, 2022 11:04 am Not surprised that Emvoice have slashed their prices!
This! Am I glad that I kept my GAS under wraps after beta testing Lucy. That price level and you have to be connected. :hihi:

I wonder how long their server will remain on line. :roll:

SV Pro AI really is a quantum jump.
Definitely! I came so close buying Emvoice so many times but the price and "online only" aspect kept my wallet in my pocket. Ironically, now, despite the price cut, I still won't bite.

I didn't even know you could do such convincing rap/talk in SV! :o

Post

ZincT wrote: Mon Jan 24, 2022 11:32 amI didn't even know you could do such convincing rap/talk in SV! :o
:) It's because the tuner is aman0_kei, one of the developers of SV Genbu Standard. He tweets a lot about various vocal synthesizers, sometimes in English. There are quite a lot of these synths coming out in Japan and China, but they're not pursuing a Western userbase like SV and VOCALOID are.

Post

Pelicanomicon wrote: Mon Jan 24, 2022 5:06 pm
ZincT wrote: Mon Jan 24, 2022 11:32 amI didn't even know you could do such convincing rap/talk in SV! :o
:) It's because the tuner is aman0_kei, one of the developers of SV Genbu Standard. He tweets a lot about various vocal synthesizers, sometimes in English. There are quite a lot of these synths coming out in Japan and China, but they're not pursuing a Western userbase like SV and VOCALOID are.
Thanks for your insight @Pelicanomicon. Do the makers of SV even realise how big this is going to be in the West? From where I am standing the future of SV looks very bright!

Post

Pelicanomicon wrote: Mon Jan 24, 2022 5:06 pm It's because the tuner :help: is aman0_kei, one of the developers of SV Genbu :help: Standard.
Would you mind explaining to a tyro what the "tuner's" position is in the process? Is he/she a developer or is this "tuning" user accessible in any way?

What is the "Genbu Standard", please?

Just wanting to familiarise myself with the buzzwords in this new and exciting field, you understand… 8)
If it were easy, anybody could do it!

Post Reply

Return to “Instruments”