#Voicebank Development
Explore tagged Tumblr posts
generalnuisance0 · 10 months ago
Text
i dont think people realize how much worse recording airy vbs is as opposed to vbs with very little air
e5 in arachne's recluse neo vb was child's play to record but recording anything other than middle c in her dark and whisper tones makes me want to actually kill myself and i cant do it without a gallon of tea on standby
7 notes · View notes
auspicious-voice · 7 months ago
Text
Fuwa Maria AI & Fuwa Mario AI for DiffSinger Progress Report (May 2024)
Hello!! With both Maria and Mario's DiffSinger voicebanks fully trained, I'd like to give some bit of detail on what I'm doing next for the eventual voicebank release including future version releases. It's been a busy April on my end as usual, but I feel like I'm almost done with things. It's a bit of a short post, though.
As usual, everything is under the cut.
Voicebank Progress
Maria and Mario's DiffSinger 1.0.0 voicebanks are fully trained and as such, they're ready for release. Of course, they'll receive new updates such as new languages, tweaks to certain parameters, and other new developments the DiffSinger development team has on the table.
Speaking of which, maybe after a couple months after 1.0.0 is released, expect version 1.1.0 in the works, with the brand-new Rectified Flow algorithm (meaning faster rendering times) and more language support. I've been gathering information on the best training settings when it comes to tension and pitch, and maybe I can just train Maria and Mario's datasets together instead of being trained separately.
Demo Reel Progress
Half of the demo reel audio is done~ I'm getting a headstart on getting the artwork done, though I think I might end up drawing it all on my phone. For the video itself, I still haven't decided on whether I should use After Effects or Alight Motion, but I think I might end up going with the latter.
I am hoping that I can finish the reel by the end of June ^^;
2 notes · View notes
steakout-05 · 1 month ago
Text
a few Big Al and Sweet Ann headcanons cause i'm fixated on the original early versions of these two goobers
Big Al is an undead reincarnation of an Elvis impersonator, and Sweet Ann is the who brought him back from the grave. the man Big Al used to be was somebody Ann was infatuated with, and when faced with the news of his tragic and untimely death, she was absolutely devastated. she couldn't bare to lost the one she loved, so she Frankenstein'd him back to life and gave him another chance with a new identity and show persona.
the reason Big Al's english and singing can sound a bit rough is because he's a reanimated corpse who's kinda relearning how to be a human. undead monsters, depending on how long they had been dead before their reincarnation, typically forget a lot of their previous lives beyond basic human instincts, and thus, when they are reincarnated, they need to learn how to act like the humans around them again. luckily, Ann dug him up pretty quickly after his death, so he still has partial recollection of who he was before his death. his body had been stuck in a casket for a while before his reincarnation, cut him some slack! XD
Sweet Ann is an undead monster like Al, although she seems to be much better at mimicking human behaviours than Al is, as he was only recently reincarnated. she was reincarnated close to a century ago, and in that time, she has built up an impressive career for herself as a singer. almost everything about her background before entering the spotlight is unknown to the public, apart from documentation of a human who looks strikingly similar to Ann who went by the name of "Jodie". Sweet Ann holds many secrets behind that smile that only Al knows.
Ronnie (Big Al's development name) was Al's previous name when he was alive, and it's a pet name Ann calls him. he finds it adorable and endearing.
most of Sweet Ann and Big Al's old demos have a backstory and chronology to them. Sweet Ann's 'How Could I Forget You' VOCALOID 1 demo is a song written from her perspective of Ann having to relearn and try to remember the ones she once loved when she was alive, very shortly after she was reincarnated as a monster. 'Amazing Grace' is what she sung after successfully bringing Big Al back to life, and it was the very first thing he'd heard when he woke up. Sweet Ann and Big Al's 'Make Me Feel' demos take place shortly after Big Al was reincarnated by Ann, with Big Al learning how to feel again and how to sing again. they kinda playing a mellodrama with each other that's partially born out of Sweet Ann's own feelings towards Al. Big Al's 'I Feel Good' demo was recorded when he was drunk lolllol
#big al#big al vocaloid#sweet ann#sweet ann vocaloid#vocaloid 2#vocaloid2#frankenstein's big al my beloved <3#i honestly really love the idea of these two being undead singing monsters#we already have a bunch of android-inspired vocaloids i think we should throw in a few undeads in the mix too#also while writing this i just watched the kitto vs sweet ann video and it is so fucking funny lmaooo go watch it#sweet ann and unreleased big al are two of my favourite vocaloids atm#they're so underrated and i'm so sad michael king's version of big al wasn't released#if only they had just waited for michael king to get back from touring.....#it makes me quite sad to think about what we could have had with big al#i do really like his released voicebank and all don't get me wrong but it just doesn't hit the same as the unreleased big al#released big al feels less unique than his unreleased incarnation#also i feel like i should mention that there was another cancelled version of big al with his development name (ronie)#but to my knowledge there are no demos of his voice anywhere#anyway yeah i love giving a backstory to characters who don't necessarily have one heeheehoohoo#also bonus headcanon that big al's puppet-like mouth is a side effect of his recent reincarnation and being put back together#and it's something that heals over time#sweet ann used to have a similar condition to al's but it healed as she got used to her undead body#sorry to get off track again but big al's 'i feel good' demo is so fucking funny#''wOOOOOOWWW!!!! i fEel goOd'' - big al after too many drinks#headcanons#my headcanons#obscure media#obscure vocaloids
8 notes · View notes
whatwillyousing · 10 days ago
Text
vsynth has long since been trending towards the uncanny valley of singing but i feel like its been especially pronounced the past few years now that a higher proportion of banks sound nigh indistinguishable from human people. you can only really tell if youre already deeply familiar with each bank's respective engine
#its stunning the amount of progress vsynth tech has made within the past few years#and its been really interesting too seeing like adachi rei rise in popularity almost as a counter to ai vsynth#its admittedly kind of saddening that the industry preference overwhelmingly pushes realistic vocals over mechanical robot vocals#and i mean i know they do come equipped with parameters you can edit to make them sound robotic again but its genuinely not the same#when you have the concatenation ai built into the software and the phoneme transitions are automatically smoothed over#this isnt to say that ai vsynth has like completely overtaken or threatening the Future of Vocalsynth though#there is a significant portion of people who largely prefer the clunky/mechanical/robotic sound of early vocalsynth#which is why i think rei has gotten as popular as she has#and the cryptonloids in particular are forever stuck in the piapro ether so the most we'll ever see of a miku ai#is just ppl messing with the rvc ai voice cloner LOL#i think if ai truly was causing Creative Bankruptcy or whatever then utau would not remain as wildly popular as it is#and part of the reason why utau still remains so popular is because [teto image] FREE SOFT its free!! anyone can use it & develop their own#vb on it too. so like yes you have the matter of industry pushing out these hyperrealistic voicebanks at an overwhelming pace#but individual fans will remain using/developing their own voicebanks (aggressively points to adachi rei again) so long as public interest#stays. hence why i dont think ''big ai'' in vocalsynth is a real threat or anything#referring to them as ai banks in the first place anyway is such a misnomer bc its not the same as generative ai#i do think that the relative simplicity at which realistic vocals are synthesized now does somewhat obscure the monumental amount of skill#it takes to tune older voicebank because that shit is HARD!!!!!!!!!#like with how synthv works it obscures the technical tuning feats of older engines and how massively massively massively impressive it is#to get anything to sound good let alone Realistic on smth like vocaloid2#synthv got popular because its ui made tuning a genuinely intuitive process rather than something that makes you want to throw#bricks at your head so its easy to forget tuning (albeit Still hard) was Much much harder#but at the same time.... ai doesnt automatically make tuning better either#actual plain vanilla ai voicebanks often sound very flat and lifeless if no actual tuning is applied i.e. vibrato pitch change tension etc#its such a beautiful complicated lovely artform#anyways my original thoughts. you unfortunately cant get that mechanical/clunky/robotic sound with. any commercial voice synth#released within the past 3 years#i hope more overtly artificial in nature banks along the same genre as rei catch on in popularity
9 notes · View notes
linabirb · 8 months ago
Text
seeing synthv lite and flt covers brings me so much joy.. like wow.. i can make cool stuff even with the free voicebanks.. even if they sound more robotic than the full ones..
5 notes · View notes
waffulaa · 1 year ago
Text
youtube
Yuezheng Longya's Official Birthday Song
Official Bilibili Upload
2 notes · View notes
dead-byte · 1 year ago
Text
I wish there was like... a program that could read the oto.ini file of an UTAU vb, and then, chop up the associated wav files so that they only contain the oto'd bits, and re-allocate the oto values accordingly. Thereby hopefully significantly minimizing the size of the vb.
If y'all have ever seen the samples in any of VOICE-MiTH's Chinese voicebanks, kinda like that.
2 notes · View notes
websitesdotcom · 8 months ago
Text
Doing stuff with utau is so fun but it takes SO LONGGG
0 notes
drawingeveryutau · 9 days ago
Text
Tumblr media
Rook! Voiced and Managed by ゆうじ / Yuji
Released November 17th, 2009, Rook is our first VIPPERLOID that wasn't (entirely) a joke! He's a derivative of Ruko; during her development, her masc voice provider (Yuu Raichi) went offline for a long while, so Yuji recorded a bank with his own voice in case Yuu couldn't finish theirs. One month before Ruko released though, Yuu Raichi reappeared with the finished voicebank, and Ruko launched as intended.
Many people liked Yuji's bank though, they liked how it sounded and how Yuji put a lot of effort into it; so on Ruko's first anniversary, Yuji's bank officially released as Rook!
Character-wise, he's chronically late to things and likes sleeping just as much as Ruko. He can also turn into a dog. He relation to Ruko (to my knowledge) has never been specified. (I hc them as siblings)
Don't took my word as gospel! If I got anything wrong feel free to correct me!
38 notes · View notes
cantheykillmacbeth · 1 year ago
Note
Hatsune Miku could kill MacBeth
Tumblr media
Yes, Hatsuke Miku from Vocaloid could kill Macbeth!
Tumblr media
She applies for all three clauses: Gender Clause due to being a girl; Unconventional Birth Clause due to being a software voicebank; and the Birth Parent Clause due to her creator being male software developer Sasaki Wataru! Thank you both for your submission!
227 notes · View notes
ukgk · 9 months ago
Text
SSP PLUGIN RECOMMENDATIONS
Do you want to customize and expand your desktop buddy experience further? here are some handy links to miscellaneous plug-ins I’ve gathered from around the web, or you can even program your own, and they can also be written in any programming language so the possibilities are limitless! plug-ins are essentially  extensions or add-on built for SSP. I’m not a plugin developer myself, and have yet to test out each one of them for extended periods of time, so please refer to the readme files/ instructions provided by the developers (github usually has info) on how to use them if you get stuck or encounter issues.  these are just some of the more recently updated ones, I'll be adding more to the plugin page of my blog if you're interested.
Tumblr media
Weather Station by Zicheq (of Ukagaka Dream Team) A plugin for both users and devs, for getting weather data! As a developer, you can set your ghost up to receive weather data from this plugin, to then do what you will with! Weather based comments? Outfit changes? Something else totally unrelated? It’s up to you! This plugin will handle the messy details of the user inputting their location and gathering the weather data for you. … (read more here)
Tumblr media
Discord Rich Presence by Ponapalt (main dev of SSP baseware) This plugin is designed for displaying the name of the primary ghost you have open on the ‘currently playing’ status on the Discord for Windows application in real-time. also compatible with displaying your currently played song in FLUX (a really awesome music player ghost by Zi).
CeVIO-Talker V2 Plug-in by Ambergon This Plug-in was initially revealed for Day 21 of the Ukagaka Advent Calendar collaborative project in 2022. using this you can have a fully voiced ghost with a realistic sounding voicebank speak to you out loud! (in English too?) it Requires ceVIO Creative Studio and SSP 2.6.45 (or newer) to work, ceVIO is a vocal synthesizer software commonly compared to Vocaloid and UTAU that works via text-to-speech method. the primary difference between Vocaloid and ceVIO is that ceVIO is built for both TTS/speech and creating vocals for songs in music production. you can download a demo of CeVIO if you would like to try it out here.
GhostSpeaker by apxxxxxxe like CeVIO-Talker, this Plug-in was initially revealed for Day 17 of the Ukagaka Advent Calendar collaborative project in 2023. it’s a successor to the Bouyomi-chan plug-in and utilizes a free (Japanese) text-to-speech software called VOICEVOX and COEIROINK so that your ghost can verbalize their balloon dialogue and speak to you. you can listen to a demo in this github link.
GhostWardrobe by apxxxxxxe allows you to dress up your ghost in different coordinates, mix and match pieces and save and load the outfit combinations from the plugin menu.
Tumblr media
CharameL plugin   by Umeici This software allows you to enjoy watching ghosts directly interact and chat amongst each other freely on the built in instant messenger.
71 notes · View notes
auspicious-voice · 10 months ago
Text
Surprise! A quick test of Maria's DiffSinger beta, trained at 42k acoustic and 80k variance!
She's underbaked just a bit since this is a beta voicebank after all, but I am loving with how she sounds as an AI voicebank. Eventually her final build will sound not as scuffed and have more features implemented. Her vocal modes sound pretty alright so far, but hopefully they'll be more pronounced once I make the final build.
That being said, I'll be going back to labeling once again... 💀💀💀
6 notes · View notes
vocaloidfactoftheday · 1 year ago
Text
Even though she has no known voicebanks in development, SeeU had a crowdfunding campaign for a collaboration album to celebrate her 10th anniversary in 2021. New merchandise was made to be distributed to crowdfunders, including an acrylic keychain and a plushie.
Tumblr media Tumblr media
(source: Vocaloid Wiki)
204 notes · View notes
synthsatellite · 1 month ago
Text
New Synthesizer V miki and Synthesizer V Hiyama Kiyoteru News in the next AHS Livestream!
Tumblr media
The next official AHS live broadcast will be on Thursday, 31st October! Miki Furukawa, the voice provider of SF-A2 Codename miki, will be a guest to share more details on the new Voicebanks in development!
YouTube Live放送 URL
ニコニコ生放送 URL
21 notes · View notes
k0ibee · 5 days ago
Text
i often find myself asking why i love vocaloid so much. then i remember. i love that the vocaloid community is so vast that it has sub communities that have sub communities. i love that there are so many stories told using vocaloid as a medium. i love that there are both long, complex stories and short ones that are self contained in their songs. i love when producers make books or manga based on their songs. i love how much there is to know, and how you dont need to know everything to enjoy it. i love the history of how the community developed and i love the way characters got the fanon that they have. i love the origins of voicebanks themselves and what happened in the companies that made them. i love that vocaloid exists as it does now because the companies that have the rights to characters acknowledge the community and the fan culture. i love the styles of music that are unique to vocaloid and how they developed alongside each other. i love that people re discover vocaloid after losing interest after their childhood phase. i love reading comments from people talking about loving the song when they were younger, and new fans commenting they’re that age. i love everything about vocaloid. every single last thing about it.
15 notes · View notes
Text
Virtual Character Tourney - Battle for 9th! (and 10th!)
Tumblr media Tumblr media Tumblr media Tumblr media Tumblr media Tumblr media Tumblr media Tumblr media
Propaganda below (May contain spoilers!)
Kasane propaganda:
HER DREAM WAS TO ONE DAY BECOME A REAL VOCALOID AMD SHE FINALLY DID IT!!!!!! ITS NOT A VOCALOID VOICE BANK BUT ITS A FULL SYNTH V VOICEBANK!!!!! AND A NEW DESIGN!!!!! SHE DID IT SHE GOT HER DREAMS!!!!!! YOURE NEVER TOO OLD TO ACCOMPLISH YOUR DREAMS!!!!!!!
Kasane Teto is a vocal synth, she started out as an april fools joke to parody VOCALOID, with her voice bank in UTAU. although she did start out as just a joke a lot of vocaloid fans grew to really love her and she became rather popular. Kasane Teto is to UTAU as Hatsune Miku is to VOCALOID. But recently on Kasane Teto's 15th anniversary, April 1st 2023, she got moved from UTAU to SynthV. With her voice bank now in SynthV she also got a new character deign alone with how her voice and her singing sounds much more clear and human like than her UTAU voice bank which sounded a lot more mechanical/robotic.
ART propaganda:
ART (Asshole Research Transport, nicknamed by Murderbot), formally known as the space ship The Perihelion (in italics but this is a Google Form), also known as Peri (nicknamed by it's human family) is a super illegal highly advanced AI that was created by a university. It grew up with two human dads and a human sister. It and its crew go on research trips that are cover for allying with people and communities at the edges (and beyond) of the capitalist hellscape that is the Corporate Rim. It also goes on espionage missions by itself, without its human crew and family, posing as an automated cargo ship. It was during one of these missions that it picked up Murderbot, a super-duper illegal bot-human security unit construct that had hacked the torture device implanted in all bot-human constructs so that it could disobey orders and walk away from its "owners" without dying. Murderbot uses its illegal freedom to watch television, a habit it passes on to ART. Turns out ART doesn't like shows where human crew members get hurt.
ART is the AI that controls/is the research and teaching vessel Perihelion. (Perihelion is usually what people call it, but the protagonist of the series calls it ART so that's the name I put. ART stands for Asshole Research Transport.) It is extremely intelligent and advanced and also extremely sarcastic and condescending. 100% earned the name ART. ART will do absolutely anything for its crew!! It was developed and "raised" alongside the captain's daughter, Iris, and they're like siblings. Its crew calls it Peri. They do corporate espionage on the side to help bring down said corporations. It has a "debris deflection system" which is definitely not a weapon because ART isn't legally allowed to have a weapon. Definitely just for debris, don't worry about it. It's friends with the aforementioned protagonist, Murderbot, and ART is very good at bullying it into actually leaving its comfort zone when it needs to. They care about each other a lot, and they like to binge watch TV shows together. I don't want to write too much but I just love it a lot.
Ene propaganda:
She's blue. Headphone actor and yuukei yesterday are also bangers
Epic gamer cybergirl. Miku adjacent
She's a girl that was forced to become digital but is still a good friend. She may not have a body anymore but she's still important to the plot.
Murder-Bot 2.0 propaganda:
Sapient computer virus made from bits of two other AI characters (the original Murderbot and a spaceship AI). Unlike its not-parents, it is genuinely just code and doesn't have a physical body. Its only physical presence is through its effects on the machinery it infects, and it considers its "body" to be the code rather than any combination of physical objects. Also it was literally made to cause problems on purpose, does so enthusiastically, gives several people including its creators existential crises, and saves one of its creators (and other people from the (literal) fallout of the other creator learning the first one got killed)
Murderbot 2.0 is sentient killware created by Murderbot and ART with the purpose of being sent on a suicide mission. It has some of Murderbot's memories, but not all because it doesn't have any hardware of it's own to store that much information in. It travels by hopping in between other computer systems (mostly bots and bot-human constructs). It named itself Murderbot 2.0. It freed a security construct named Three. It's nicer and more open than both its parents.
EDI propaganda:
EDI is the AI of the Normandy starting with Mass Effect 2. Through dialogue EDI can become more human-like in her way of thinking, developing different kinds of relationships with the crew. In Mass Effect 3 she uploads herself into a body so she can freely move around and can be taken to missions, but she is still part of the ship's system.
Holly propaganda:
Due to a pay dispute with Holly's original actor, Norman Lovett, Holly was instead played by Hattie Hayridge during seasons 3-5. This was explained briefly in the show as them having gone through a "computer sex change". This makes Holly canonically trans do not @ me.
holly is the silliest most specialest ai ever. she has an iq of 6,000 but sometimes it seems like his iq is more like 6. they're possibly transgender (do computers have gender??) (i am panicking over pronouns while writing this propaganda) - holly goes from appearing like a man to appearing like a woman with no real explanation(??) and nobody questions this (the show is from the 90s btw). he's hilarious and sometimes lies to the crew for no reason other than 'its a laugh, innit'. shes everything to me <3
Holly is the computer of Red Dwarf, a Tenth Generation AI hologrammatic computer who appears as a floating head on a screen. Can be downloaded onto various other devices. also literally transgender.. meets a female appearing parallel version of itself in a parallel universe and then goes through a sex change after falling in love with her. transgender computer ftw
Tama propaganda:
Tama is the eyeball of Kuruto Ryuki and investigates dream worlds with him. She's his bi emotional support eye who regularly ties him up to help him with stress relief and loves to affectionately tease him. She laughs at bad jokes and has AE10D1F ("Ryuki" in hexadecimal) in her likes on her profile.
OKAY anyway uhm she's like aiba in that she's a little Ai eyeball that helps you investigate except sadly no animal theme. instead she has a domintrix vibe instead!!!! she is so cool… also ermm she's a lot more. Human than aiba. Not literally/physically like uhh emotionally. I haven't finished aini but like she does look out for your best interest! what a good Ai partner i don't kno
She's voiced by Anairis Quiñones and she's an absolute legend
Lyla propaganda:
she is a humanoid ai programmed to help spider-man gather info. she can simulate human emotions and has a high intellect
84 notes · View notes