How to Sound Like an Anime Girl With This New AI Voice Changer

[@Noxis07]

I'm not gonna lie, that Gura voice was so unsettlingly spot on... I'm feeling all sorts of mixed emotions.

[@Itsappuru]

You can be your own waifu!

[@sneezyy.]

So many possibilities….

[@nekokoyoshi_enjoyer]

​@@Itsappuru You can just turn the voice changer on and off while you're speaking with yourself and there you have it, a conversation with your waifu just as how you've dreamt about all this time, which indeed would give a sort of unique/weird, mixed feelings

[@nekokoyoshi_enjoyer]

That said, I kinda wonder what Gura would sound like if the accent he used was totally different from her original accent, like let's say, a British accent (e.g. RP accent or Cockney accent). Would it sound like a posh version of Gura or would it just sound off?

[@sneezyy.]

@@Itsappuru finally, peak waifu

[@notsocody]

Now I can be a skinwalker like I've always wanted to. Thank you so much

[@victorfunnyman]

cod zombie time

[@froggycolouring]

Yes

[@staree_]

same bestie 💗🗣🗣❤️❤️💯

[@darthhunter69]

I love being a skinwalker

[@PumpKingGgNoRe]

Skinwalkest 🤤🤤🤤

[@unlegitdev]

That Markiplier voice is absolutely spot on wtf

[@TherronKeen]

Imagine how much training data is available of his voice lol Thousands and thousands of hours of KZbin vids

[@TheGoreforce]

imagine what this is like in 3 years. We won't be able to trust anything.

[@hbksss]

almost as if hes still with us😭

[@TherronKeen]

@@hbksss YOU GET THOSE DIRTY WORDS OUT OF YOUR MOUTH RIGHT NOW YOUNG MAN

[@Tensho_C]

​@@hbksssget tf outa here💀

[@backslash68]

chunk is the buffer size used in processing. The lower, the less latency, but if your cpu/graphics card is not fast enough, then some chunks will be left empty, hence the "choppy" sound. In other words, the lower chunk sizes can work without the sound being choppy, but in order for that to happen you need a monster graphics card.

[@AvgSurge]

Rtx 3050 Ti?

[@乾淨核能]

for example?

[@drejanzerss]

rtx 3070

[@AvgSurge]

@@drejanzerss just use Equalizer APO

[@mynameissongohanandamnotah17]

@@drejanzerss far more than that lol u need super computer

[@ShadowGirl-]

So I made some discoveries which could help some people. -Chunk: You should increase this if you experience any distortions or voice lag when gaming with this. This adds more graphics processing time, and if you set it longer it wont rush out bad audio. -Extra: This setting gives bonus CPU usage to help iron out the audio. I found that sometimes the changer would translate an F sound to an S sound, but adding a bit "extra" CPU to it (like the 8k setting or higher) fixes the problem. You don't want to max this out unless the only thing you're doing is using your voice, as maxing it out will use all or nearly all of your CPU. -Noise: I recommend using Sup2 option if you have an Air-Conditioner or other background noise. Sup1 didn't work as well and is probably for a different frequency range, so your millage may vary. When you start real time voice changing, you'll see some info in a box with millisecond timers. The thing to watch is the "res" time. If this time starts going up, from around 300ms it starts rising to a thousand then two thousand etc, this means the computer is unable to get the voice processing out in time, its being pushed back in priority you could say. The fix is to increase the Chunk, this will give it more time to process with the remainder of your resources, and switching it you should see the number start decreasing rapidly. If it doesn't just raise it even higher, and also again keep in mind that if you're doing something that is CPU intensive, you need to keep the Extra setting fairly low (like around 8k). I have a powerful computer (10 core i9 10900kf, with a reference 3080ti), and I found that if im going to play a "serious" game like GTAV or StarCitizen etc, its best to have the Chunk as high as 192, or 256, with the Extra set to 8192. If you're just on discord, or playing some very light game, you can crank the Extra up, and reduce the Chunk to maintain high quality audio but process it considerably faster. Hope this helps someone!! Good luck o/

[@jackhunter2633]

how do u get it to work while gaming or call? i rlyyyyy wanna prank my lil bro cause he mad thirsty for chicks rn hahahha

[@Doki_LP]

Thanks a lot for this! 👋

[@syriker1489]

Mine is in the 25K res lol

[@ShadowGirl-]

@@syriker1489 Yea really depends on what your hardware can do.

[@ShadowGirl-]

@@libertadiespressione C'è un ritardo di uno o due secondi a seconda delle impostazioni e dell'hardware.

[@remurina8696]

This is genuinely such an amazingly well put together tutorial video, no side-tracks, no random edits or cuts that confuses a complete newcomer as well as also including disclaimers and showing some potential issues with the program, this earns a sub!

[@theAIsearch]

Thank you so much!

[@buyvaccines]

sirno

[@TwistzWasTaken]

Is it a virus chat

[@remurina8696]

@@TwistzWasTaken its not, if your antivirus pops up or blocks it from running, just allow it through your firewall or turn off your antivirus

[@TwistzWasTaken]

@@remurina8696 thanks chat

[@RuisuTempest]

I dont even need an Ai to sound like an anime girl. Its a unique skill that i unlocked at the bathroom.

[@Willow_493]

lmfao genuinely thank you for that laugh i needed that XD

[@Pikachara]

Yeah we know rimuru

[@chocolachan7079]

My mom heard me when I was trying to say uwu in anime girl voice

[@Usieeeeee]

@@chocolachan7079 LOL

[@tricoolaz7188]

@@chocolachan7079just tell them your going through puberty a second time g XD

[@TheFlamingPike]

Your videos are really well done, the descriptions and explanations are top tier. This is a game changer for me since I'm a DM at a D&D game that we play on Discord and this will help me make the sessions even more entertaining and will help the players feel like they're interacting with unique characters instead of just me acting different voices. I may also mess around a bit while gaming online. Just a bit.😝

[@theAIsearch]

Thank you!

[@Keepmeuptillsunrise]

😝

[@m3gon1]

😝@@Keepmeuptillsunrise

[@aibi5532]

​@@theAIsearchany text to voice ai like this one but for text?

[@vonakakkola]

so basically you don't need anymore to be female in order to become a moe vtuber

[@miorosa318]

Or could just help us females with a bit more masc voices to actually sound more appealing to audiences because it sucks ;w;

[@farid-frederick]

Gigguk : "Always has been"

[@vonakakkola]

@@miorosa318 you're absolutely right for wanting more male vtubers, but in this moment what's more popular is the "cute anime female" trope, even among the female audience there are male vtubers (like Ryugon Daimonji, but he talks in japaneese) but they're very rare so sorry

[@stormierbody8419]

@@vonakakkolawell not only that but in Twitter male vtubers are just being berated off being a vtuber with others being all radical feminist towards them

[@ambulance-kun5284]

"Sometimes, it takes a real man to become best girl." -Gigguk

[@iRaphahell]

14:37 Jesus Christ! It sounds exactly like him

[@schneizevb]

buna rapha

[@arekusoo]

ikr

[@alexpinguin5978]

Salut Rafa :D

[@zlatevlad5887]

si tu vrei sa iti faci voce de fata anime fafa? te inteleg, si eu

[@maxwtw]

raphaeleeeee

[@theAIsearch]

Quick update for this video: If this discord is full, check out this video to fix it: kzbin.info/www/bejne/m2mmkpmqfZ6ios0 In the download table, I directed you to download the gpucuda version of the software if you have a dedicated graphics card. However, when I went to Hugging Face, I accidentally downloaded the directMLcuda. You should use the gpucuda version (if you have a dedicated graphics card)! Sorry for the confusion!

[@clumsymoe]

"onnxgpu" for NVIDIA GPU - "DirectML" for AMD GPU/INTEL GPU - "no cuda" for CPU only (no dedicated GPU)👍

[@temp5031]

the voice changer keeps picking up the pc audio even though when i speak without the voice changer it doesnt pick up the audio on my pc (help please)

[@ClydeCamilla]

o hmm well thanks also is it my mic problem that the ai voice is not quite saying the words right its just "mumble mumble" and other things i dont understand it saying. or smthng shud i use bluetooth headphones cuz thats what i use also is it okay if the file form http thing has no bat at the end

[@Itsappuru]

Would this work on intel core i3 2.20 ghz, 4 gigs ram and intel uhd gpu 2gb?

[@qee540]

This is not AI. Is just insert / injecting.

[@-weaponized6493]

"Nobody cared who i was until i put the voice changer on." - Bane Chan

[@ryouarozado1350]

Cat fishing went to a whole new level it's even anime.

[@theAIsearch]

🤣🤣🤣

[@Jish-ym6zc]

>:)

[@Graphik]

@@theAIsearchit aint really that funny

[@thecolorblue7427]

@@Graphik no but it really kind of is, imagine the potential to fuck with toxic players in game or whatever

[@ryouarozado1350]

@@thecolorblue7427 i would probably do that in call of duty.

[@norman157]

Markiplier's voice sounds way too real

[@flexxible6987]

Bruh, gura one is scary af

[@alejomakevids]

@@flexxible6987 No need for Gura anymore 🤯🤯

[@flexxible6987]

@Aka_Umash maybe tiktoker clown gon had an idea for this

[@southern-skies-angels77]

@Aka_Umash Someone will surely do.

[@heinloffman]

Chills

[@__________FRUIT]

Damn this is kinda scary but also fascinating. The fact this is real-time and it sounds so good just blows my mind.

[@igorthelight]

Almost real-time ;-)

[@TheUnderscore_]

@@igorthelight Real-time != the same instant, it just means without post-processing.

[@igorthelight]

@@TheUnderscore_ Fair point!

[@ibigfire]

The not actually instant is an important distinction though, it's hard to hold a conversation with that delay and you end up talking over and interrupting the other person a lot by accident. It also doesn't seem to handle laughter or whispering well at all. Still very cool tech though, for sure, for many uses.

[@JogosMofados]

Thanks for the introduction, I installed it and I'm having fun doing content with a true free voice changer. Glad I found your video, it helped a lot!

[@theAIsearch]

Thank you! Glad it helped!

[@beambie9145]

@@theAIsearch for some reason when the file it says http but without the bat next to it but it still says batch file. and when i open it, it immediately closes itself

[@KakashionFortnite]

when i click its not openingg@@theAIsearch

[@bottleofwater1961]

Now i can troll in over watch people be like " your voice is so cute" *enables markiplier* "you wanna say that again?"

[@Ikxi]

PERFECT

[@victorfunnyman]

you gotta make a video of that man it'd be fun

[@bottleofwater1961]

@victorfunnyman maybe if i can get it to actually connect to things like discord

[@hotstepper6303]

BRo I'll be waiting for a video 😂😂😂😂

[@louis450sr]

👊👊that was a good one

[@RyzenShanks]

Imagine a bug, glitched or an error happened in the middle of the stream and you don't know that your audience is hearing your original voice. :)

[@quazar-omega]

​@@micaheiber1419 what if the sanity check fails exactly when the process it is checking fails? Sanity checks all the way down

[@1aboveall]

going from a 9 year old girls voice to a 68 years old mans voice

[@CreEpeRneSs125]

With the way this voice changer works it isn't really possible for the original voice to leak through However accidently setting the wrong audio device somewhere definitely will, but still technically not at the fault of this program though

[@RyzenShanks]

@@CreEpeRneSs125 It's possible I already tried a few of them. The popular ones specially. It's very rare to happen but one time can kill your role play.

[@chloe-sunshine7]

@@quazar-omega This reminds me of the compiler trust paradox by Ken Thompson. It's very interesting, and very unsettling.

[@senhor6863]

Index is how the AI will match the original accent from the model, a higher index will make your voice have the same accent as the choosen model, but may generate artifacts and potentially take a little longer

[@orangesoupd]

> potentially take a little longer Not really. It's more like noise in SD

[@laxyboyz8969]

It would be so much fun reading novel out loud with this. Immersion +++

[@theAIsearch]

nice use case

[@groouber]

There's a pretty easy way to get the voice changer to work with discord with VB audio cable, it's just a quick download and works pretty well

[@theAIsearch]

Nice! Thanks for sharing

[@FunnyBloxYT]

Amazing!

[@LavaCreeperPeople]

nice

[@ffuwarin]

ok

[@Vivid_Merami]

This is honestly amazing, the ai is spot on and works perfectly for me. your tutorial is also perfect as well and was very easy to understand. i would love to see a video about how to get this to work on discord since i have had trouble doing the same thing with another voice changer before.

[@ichfae4936]

What voice changer did you use?

[@terrace15]

Did you happen to run into any issues with your audio being cut off near the end of sentences?

[@annihilatorex1363]

@@terrace15 some of the models dont work properly thats why they cut off im pretty sure

[@mycool8184]

I hope they have master chief, so when I go onto hell divers, I can be like "cortana drop me near the nearest hell diver"

[@ScarLunacyAlter]

To those not seeing the chart, Scoll down and when you see "(1) Usage with pre-built binaries" in BOLD Text. At the bottom there is a blue hyperlink text that says "Download from Hugging Face". Just before "(2) Usage after setting up the environment such as Docker or Anaconda" in BOLD text You are Welcome 🙂

[@ganeshk124]

thanks, really needed that

[@rickchaves]

Thank you for completing the video.

[@Nuinui_15]

Marry me tysm 😭

[@patchstep]

my best guess is that this is using some kind of FFT or equivalent audio processing before the AI processes it, which means that 1) the "CHUNK" setting would be equivalent to a "buffer size" (how many samples in the buffer currently being processed). this will add delay but increase performance for lower-end components. 2) the "EXTRA" setting would be equivalent to the FFT resolution, meaning how many frequencies it can process. this will increase the quality of your voice coming in, and thus the quality of the voice coming out.

[@unnameable57]

Hearing Hoshino Ai voice again give me all sorts of emotions

[@arys____]

The power you've just given me is incredible, and I'm sure I'll do amazing things. lmao

[@SqualingtonConstantine]

This is such cool technology. It's also great to see this being a public Github project and not some scummy trial bs.

[@vollyentertainmentinc.djvo8265]

sadly im still too sceptical to belive this. i wish i had your optimism.

[@suham5132]

@@vollyentertainmentinc.djvo8265 dw, this is open source project, github open source projects can always be trusted

[@conorebola9872]

bro you can literally download it and test it yourself..@@vollyentertainmentinc.djvo8265

[@dangerpillow5234]

@@vollyentertainmentinc.djvo8265 im not even joking it does work, i use gura voice and its very spot on, this may be because of my high voice but whatever

[@Atom224]

@@vollyentertainmentinc.djvo8265 You mean sceptical as in malware?

[@si0773]

those who want to know, the virtual character, Tsukuyomi - chan, the l0li character with white hair he used in beginning for demonstration. She's just a character for free material that can be used for commercial purposes, such as for this voice changer.

[@flowersnothere]

Isnt that Kamisato Ayaka from genshin impact??

[@safin_]

@@flowersnothere nah the label for the voice changer says tsukuyomi chan in hiragana

[@rice_frying_shrimp]

@@flowersnothere looks absolutely nothing like her but okay

[@LavaCreeperPeople]

@@flowersnothere L game

[@LavaCreeperPeople]

weird "l0li" thing, but i guess it looks interesting so i'll try it out as this appeared on my right tab randomly.

[@rulercamelot3687]

I love this! I also love how the very day I find out this thing exists is the day you put this video out. It was destiny for me to troll my friends as an anime girl! I am having an odd problem however, there appears to be a large amount of static in my right headphone while the app is open, and it crashes when I try to change settings. If you have any insights as to why that might be the case, do tell! Edit: It was just my audio driver that was out of date by two years lmao

[@theAIsearch]

I’m sorry that you are having those issues! I have not experienced those so I’m not sure what would help. My first thought is to make sure you installed the right version for your computer, and that the correct version of PyTorch installed. I would try making an issue report on their GitHub and they can help you further! Here’s the link: github.com/w-okada/voice-changer/issues

[@cuerdencats4151]

Does it only happen with that headset? Try an alternative if you can to figure out if it's just some wierd driver thing, or if somehow the program is causing the problem. If it's just the headset, maybe just uninstall and reinstall your drivers~

[@kl0nos]

have you found a fiz yet? im having the same problem :/

[@rulercamelot3687]

@@kl0nos I updated my audio Drivers and it worked, but it's still a but wonky sometimes, I also unplug and replug my headphones and that tends to fix it

[@kl0nos]

@@rulercamelot3687 oh i fixed it too!, turns out i was using the directMl instead of using the onnxcpu one :), instaling the other one pretty much fixed it (i have a nvidea graphics card)

[@joyul8216]

I play a lot of tabletop rpg, and I'm envisioning players using AI to roleplay their characters, thanks for the idea.

[@RoxyGotMoxy.]

did you have any luck with this? I play via zoom, hoping it works there??

[@theskeletonman2092]

I accidently clicked no when it said 'do you want 'voice changer' to change your computer' and now it sounds like every voice I try to use is haunted

[@kanromusic]

Discord will never be the same again.

[@LavaCreeperPeople]

You!

[@kanromusic]

@@LavaCreeperPeople Hii!!

[@LavaCreeperPeople]

@@kanromusic hey :D

[@kanromusic]

@@LavaCreeperPeople hiiii what's your discord?

[@voiddiver1377]

@@kanromusic I've heard it's BoeJiden#8831

[@krozareq]

Sounds fantastic. This will be so fun on VRchat.

[@Southern_Pixel]

Thank you so much for making this video! I've been trying to figure out how to do a voice changer for months now and I never could figure it out until I saw this video. I got a voice model of Abby Trott made for me and it sounds great! c:

[@radraccoon9489]

As incredibly but and high quality as this is, i find it horribly terrifying that there's also real voices, an in, youtubers' voices, in this... And I'm pretty sure some of them don't know their voices have been taken.

[@calculateddeclination5534]

Remember, never trust any girl you meet in vrchat. It could be a guy using an ai voice changer.

[@Nymxy]

fr ♾

[@jetison333]

so?

[@rem3dy_e]

Even better

[@_ahsiA]

@@rem3dy_e 100% better

[@mrincrediblebecominguncann4549]

@@rem3dy_e💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀💀

[@msterofficial]

Thank you for providing an informational video, much appretiated. Congrats on 1000 subs, well deserved. I know you will keep growing if you keep putting out great content like this, the algorithm has catched you so now just surf for a while. Wish you all the best

[@msterofficial]

10 months later and you're at 126k subs. Knew you'd make it!

[@puzzlepuddles6712]

i'm not embarrassed to admit i was here for the anime girls but holy shit i was not prepared for that markiplier one

[@linknero1]

I want this to make a funnny podcast with some characters to have a good time. Also I want to use this to modify a voice in a movie to match the character. This is gonna make it real! thanks!!!

[@theAIsearch]

Good luck!

[@BoxingQ]

can you record and save the voice clip to use in a movie ?

[@GeneralDonato]

1 - Damn, hearing the voice of Ai Hoshino once again give me mixed emotions. I miss her so much 😭😭😭 2 - We need a voice model for Dmitry Yazov IMMEDIATELY

[@lucas.lagoriaa]

she literally came out in one episode and you say you miss her lol

[@littlemilk973]

Bro the show made us too attatched DD:@@lucas.lagoriaa

[@RinRin72769]

​@@lucas.lagoriaaOne 1 hour long episode

[@GeneralDonato]

@@lucas.lagoriaa Well I'm pretty sure that's the whole point

[@fosamil]

​@@lucas.lagoriaa That's the entire concept of missing someone though.

[@feroexe7965]

God thats terrifying, the Smi77y and Gura one is spot on

[@MySkinIsntMine]

Finally, I can trick 40 yearold discord mods into paying me all of their lifesavings. This is truly the future

[@medievalwebman2917]

done using it. and all i can say is. ITS SO FREAKY REAL!

[@الگويت]

ITS SAYS THAT ITS VIRUS?

[@medievalwebman2917]

nope its not. it works.

[@medievalwebman2917]

@@الگويت the only problem i encountered was uploading some voice models, probably because my GPU is only 1030.

[@Railey_Pg3d]

@@medievalwebman2917 Mine is the rtx 4050 laptop gpu with 6gb vram. But my voice changer have issues such as being choppy, excess pitch, robotic voice leaks. Does the microphone you use matter to make this work properly?

[@medievalwebman2917]

@@Railey_Pg3d mine has only 5 gb vram in gpu but it works just fine. also i made the processing resources all goes to the voice changer also turning off other background processes that interferes with voice changer. maybe you haven't tweak the program yet to use the gpu's core instead of your laptop's core. also i'm using a desktop.

[@NoAkemi]

I finally got discord nitro because of this, thank you soo much.

[@thatzaliasguy]

If using a dedicated AMD GPU, use the ONNX(DirectML) version. This also gives benefit to AMD over Nvidia due to ROCm having far more efficient machine learning cores than Nvidia's now-ancient CUDA cores.

[@abhishekshrestha6441]

OMG THANKS

[@jaimeflores4683]

And can you explain more settings?

[@GhoulSoulToll]

This is so awesome! Would you be able to make a video on how to create the actual models themselves for use?

[@theAIsearch]

Thanks! Sure, I'll add this to the agenda!

[@GhoulSoulToll]

@@theAIsearch Looking forward. I made sure to subscribe and turn the bell on.

[@stumbling_]

I'm just on the internet looking for some more like.. voice changers in the sense that my voice echoes and all that but I had to watch this and the cuts between the anime girl voice and your voice is making me laugh so hard.

[@BiggestBrother]

the first 15 seconds of this were absolutly amazing

[@AstrayCuriosity]

The more ai tools developed the more terrified I become. It's incredibly cool but in the same time also incredibly scary and really makes you think about our future.

[@IlBiggo]

99% of the so-called "AI" is just expert systems, i.e. large databases and fast calculations. The only scaring thing is people misusing computers, and it's in been full throttle for a good while now.

[@AstrayCuriosity]

@@IlBiggo 🤓

[@confusedjay717]

@@AstrayCuriosity You're more of a nerd for being scared of that shit if you think about it

[@damarbob]

I think the chunk is what I consider the buffer. The machine will process chunk by chunk. Unless you have a powerful machine, you might want to put higher value there. Or it will sound choppy because your machine can't keep up with the buffer size.

[@Sloff1155]

AI acceleration definitely is way better in the 20 series and above, I have experimented with AI models on my GTX 1070 for my desktop and it is ungodly slow, however when I do the same task on my 3070 TI even on my laptop it's near instantaneous so it probably will work way better.

[@theAIsearch]

yes, rtx + ti is great!

[@Peacuch]

Have you tried the 40 series at all? I'm having an isuse where it's not even showing me a gpu option...@@theAIsearch

[@godzilla24616]

@@theAIsearch can you still use a GTX 1070?

[@Nezros0]

dude, I was looking for an ai voice changer for other reasons a few months ago I couldn't find anything. I was about to bite the bullet and just do all the audio production myself, but knowing this tool exists is fantastic. I just want a voice changer that makes me sound like a very specific text to speech voice (an oldie) I hope it's possible to do this with this program. I'll probably have to create my own model because no one cares to do what I want to do. If you could change your voice, why the hell would you choose text to speech of all things? I'll tell you, I feel like it.

[@Altair4611]

"other reasons"

[@Zaki-.-]

​@@Altair4611I already have an idea of ​​what it is...😂😂😂😂

[@theAIsearch]

see this new tutorial: kzbin.info/www/bejne/oJmbZImfebqpgNU

[@TheOne-jq4iv]

Hoshino Ai only appeared in the first episode, so there might be limited training data. Therefore, I assume that's why the output voice sounds choppy.

[@enzofranconegrutzi5339]

thanks for the tutorial! Its really detailed but simple and easy to understand

[@theAIsearch]

Glad it was helpful!

[@quitlongtimeago]

Literally took me more than an hour to figure it out. While it took long enough to download. It wasn't even opening and ngl the time wasn't even worth it. I expected it to work 100% looking at the comments but it annoyed me so much I don't recommend this in 2024.

[@k4mlover]

i spent my whole day and ut didnt work

[@Tor-Erik]

This has to be one of the most craziest thing ever invented. Turning your real life voice into an anime girl or something. I dig it!

[@theAIsearch]

Yeah it's crazy how much AI has improved in less than a year!

[@Tor-Erik]

It's actually a little scary to be honest. The AI voice changer can be used to scam people into the victim thinking it is one of the family members to get their credit card code or something. Not with anime girl voice, of course, that would be random. Thankfully it is mostly used for fun.

[@Astran0th]

Great tutorial! The software seems pretty amazing.

[@starflatinum244]

Thanks, bro. Very helpful and I really appreciate it 👍 Time to become an Anime >:)

[@GAnimeRO]

Thanks for the vid and the previous one where you warned about the voice ai!

[@stranostrani9212]

Imagine a future where no one uses their natural voice but a voice tweaked or modified according to their preferences or emotions.

[@LegethDrn]

A good future in my eyes

[@boozonggy]

@@LegethDrn that is not good.

[@AlbedoIsMyQueen]

@@boozonggy why not?

[@boozonggy]

your devoiding all humans from your life and replacing them with ai@@AlbedoIsMyQueen

[@ten10_ten10]

​@@boozonggy people having different voices is not replacing all humans with AI, but I do agree a future of it is not necessarily a "good" thing. The main argument for it is trans people. I'm not gonna get into the politics of it, but if you support trans people then instead of hoping for a future where everyone uses AI to change their voices you should probably hope for a future where people can freely train their voices to sound more female without being shamed for it. Now, no sane person should hope for a future where everyone uses AI for simple bodily functions. That sounds awful. If you life futurism and "evolved societies" and that sorta stuff, you should be rooting for biological enhancements on humans and not brainchips and AI.

[@vladislavkaras491]

Darn... This is so impressive! Thanks for the video!

[@theAIsearch]

My pleasure!

[@celshante1769]

Some people can look the same or have the same voice. But this just amplified that by a ton. This gon be wild

[@TheRealUnknownEvil]

The 'assuming you already have PyTorch installed' sent me on a whole ahh side quest 😭😭💀💀

[@Posic_]

My job used to be part-time… Now I can work full-time as a discord mod 😄 (I am not a discord mod)

[@Vikingworkstudios]

this will be useful for make my personal studio.

[@garfieldpilled]

Does it still work???

[@SenbonKaguya]

This is dangerous, and I also love it lol. No idea if it's viable to run it in a game, but I like what we have so far.

[@theAIsearch]

you can use it in a game. see this: kzbin.info/www/bejne/jnmqnaljepyYeNk

[@AnEarlyDawnInAField]

I always used to think those Vtubers voices were like that irl... This makes so much sense now 😂

[@Artista_Frustrado]

while sounding like a cute girl would be amazing, i would pretty much use it so my outter voice sounds closer to the way it sounds for me either that or sound like a Biblically accurate Angel

[@Catboy_Yuki]

Fantastic tutorial! Thank you very much.

[@theAIsearch]

You're very welcome!

[@isbestlizard]

Yessssss this is exactly what I needed thanks for sharing :D

[@theAIsearch]

You're welcome!

[@tyleaneous_YES]

Yo that smii7y one was fuken clean

[@jointhefittest1719]

After wasting time buying and returning a $300 GoXLR and a $500 RodeCaster Duo for their voice changers I can't believe that this was there all along for free. Thank you, I found your video just in time. The last day to initiate a return for the RodeCaster Duo is today. Just subbed man. Keep up the good work.

[@phantomberzerk9486]

Curious why you use this?

[@jointhefittest1719]

@@phantomberzerk9486 to change my voice.

[@Rimuru445]

I have done everything In this video, but for some reason the voice doesn't voice. I just keep hearing my own voice and the (VOL:) stays at (0.0000) on the top left corner of the model. Also finding issues with the (FO Det.:) options that give you (harvest and crepe) only give me (crepe_tiny and rmvpe_onnx) so for some reason nothing is changing for my voice.. Please help..

[@indeidk]

Im having the same problem and im so confused

[@tolunaykaradeniz6851]

did you solve it?

[@godz1174]

he didn't mention this in the video but if you're struggling. If you have a nvidia gpu you download the cuda file and if you have an amd gpu you download the DirectML file

[@Zeke-rr8sx]

there is like a gpu-cuda and a directML-cuda version, i have an nvidia card which one should i get?

[@XENON___54]

I'm so paranoid about downloading ai stuff now because of voice ai, and how it scams you. but i feel like this is a lot more trust worthy and the channel seems dedicated to this sort of stuff. (pls don't find my location and nuke it)

[@Fritzzz1]

Thank you very much! I like the Disclaimer part. Very professional

[@DylansLapplandSimping]

at some point VTubers will train their own models with their own VTuber voice and use that instead frfr

[@a.k.amatsu4876]

for real situation it's gonna backstabbed instead

[@Duck_Snow]

I haven't seen anyone talk about this but. A pc tweak that is supposed to help with stuttering in games ended up making the thing run better on my laptop. Acer nitro 5 with an I5 and gtx 1650. I'm able to run the voice changer with 256ms chunk and the lowest extra at 4096 all on f0det of rmvpe. All I did was disable high precision event timer, System timer, and composite bus enumerator in device manager. Before this i couldn't run the program on my desktop at all with nothing running even at 1 second delay it would cut out a lot. so i was gonna delete it but never did. I came across the tweak because I kept getting hitches on fortnite, tried lowering my mouse polling rate to 250 which helped but wasn't enough. Then I came across the device manager tweak mentioned above without realizing that it would allow me to run the voice changer with a 1/4th second delay and fortnite at 120 fps with no issues at all. again on a gtx 1650 i5 LAPTOP. I'm on a desktop now 12400f, 16gb 3200mhz ram, and rtx 3050 oc. and the program is able to run 150ms 4096 extra. and run fortnite 240fps no issues(only with the tweak). But I don't actually use it on my desktop anymore. I use my laptop(with the tweak) to run the program and then use a male to male aux cable from my laptop to my desktop using the line in. So now I can run the program and play any games with no performance hit. I can't stress enough how helpful it is. turn on high precision event timer and system timer it will cut at half second multiple times, turn them off IMMEDIATLEY runs absolutely no issues at a quarter second with 4096 extra, this worked well on rmvpe. it only runs well like this on rmvpe not sure why, any other f0det will cut out no matter what even with the tweaks i tried all of them but only rmvpe works, but imo rmvpe just sounds the best anyways so it's win win. another weird quirk with this is that it runs better with the lowest extra with these tweaks but the more extra the more it will cut out not sure why

[@ShadowGirl-]

If anyone is reading this, the discord AI Hub (which is linked in the video), is actually a cesspit of abusers and should be avoided at all costs.

[@pacmanpowerghost]

From Screamingbee to this, I welcome this change.

[@Thom_kk]

[Voice Changer] Pipeline is not initialized. [Voice Changer] Waiting generate pipeline...

[@jontylerlud]

I need an answer to this too. :( Only one of the default voices doesn't have this error

[@allaithsalkini]

insane bro thanks

[@reshzy3807]

does the quality changes depending on how good your mic is?

[@theAIsearch]

It depends on how good it is. Most mics will sound fine. If it is a headset with a mic it might not sound super great. But I think if it is a standalone mic, you should be fine!

[@crystalecho_]

He chose crepe for the F0 Det. but it wasn't working too well for me and when I changed it back to harvest, the response time improved immensely. My GPU is AMD Radeon RX 580 if that helps anyone.

[@tukami187]

which version did you download? because my client is not using my gpu at all

[@justinbena6392]

@@tukami187 same

[@jaimeflores4683]

But how are you using your gpu? AMD doesnt have cuda

[@AlisSpark]

Especially male to female voice changers are still quite lacking for any guy who likes to be an anime girl and who may be very excited about this, hate to tell you it is very hard to convert male to female voices because just increasing the pitch doesn't do it alone, but many of the same sex voice changers (female -> female/ male->male) and female to male voice changers are already by now really good. But don't worry, technology will keep getting better and it's going to be really awesome in the years to come!

[@Mixtry425]

nice info thx buddy

[@feedmewithhate]

hopefully not

[@TakahashiQR]

O simplemente aprende imitación/doblaje básico, te centras en mejorar tu falsette para llegar a todos agudos y luego le aplicas el cambiador de voz para sonar más auténtico a chica anime

[@vollyentertainmentinc.djvo8265]

@@feedmewithhate I feel your desire

[@The_BlackGoose]

*this software sends shivers down my spine* 💀

[@Kugly]

random ass video idea for someone to use: play a Mario Kart or Mario Party game with your friends, but everyone uses this voice changer to sound exactly like the character they picked... i have to yet try this myself, but it would be hilarious oh, and good tutorial btw...

[@zywei.]

I have a radeon GPU and the dropdown for GPU doesnt actually pop up. I can only choose CPU instead of a dedicated GPU. does this voice changer only work for Nvidia cards or is there a solution?

[@theAIsearch]

For AMD GPU's, here's what it says on the Github: "If you are using a Windows and AMD/Intel GPU, please download ONNX (cpu, DirectML) and PyTorch (cpu, cuda). AMD/Intel GPUs are only enabled for ONNX models." "The developer does not have an AMD graphics card, so it has not been tested. This package only includes onnxruntime-directml." Hope that helps

[@zywei.]

@@theAIsearch Cheers thank you!

[@Mitsuki-meow海月]

But I am a mobile…

[@nightthemoon8481]

buy a pc

[@nightthemoon8481]

@@Mitsuki-meow海月 you could buy a laptop then

[@Fox7063-l3z]

Get a dell OptiPlex tower or other tower workstations you can buy them fairly cheap then just throw a low profile rtx 3050 or a 4060 or a other low profile card

[@System32crowdstrikewin11]

Hi mobile

[@raiyansyed1166]

Amazing video! How do you record the output and can you also share how to train your own model?

[@ak47manplaysall94]

currently having issues with the voice coming out super choppy most of the time but then sometimes it just clears up super weird. Anyone know why this might be happening I have tried several different versions and they all end up sounding super choppy with all the voice models.

[@theAIsearch]

Try increasing the chunks! Or maybe your graphics card is having a hard time processing it

[@Genji-wt8bo]

I realize the ai work really good , but at one side before using it , we have to make sure our env sound is same as you quiet or not the surrounding noise will be filter in too . Secondly , even tho it filter really good , it take a person to speak well ,or pronounce the word right . As an introvert , I find myself really hard to speak a thing really fluent , it does make me think

[@Ernismeister]

i have an RTX 3090 and the listen (and actual) delays are identical to yours. I feel like this could use some optimization

[@theAIsearch]

Definitely! I am excited for when it becomes faster and easier for everyone to use!

[@LavaCreeperPeople]

yup

[@Homiloko2]

I think the delays are fixed. Not sure how it works but perhaps your quality will be better with less delay than a slower GPU would be. Giving more delay is giving it more processing time, thus making it better, but each GPU will have different performance.

[@PuReXtremeGaming]

​@@Homiloko2did u test it and the delay is good

[@Dil-ka-music]

Great video man... I think its the best video on youtube if one is in search for real free software. I m still looking for TTS AI Voice clone. Did u find one or have done a video on it yet? thanks in advance. Appreciate ur content. Keep it up

[@thesavior8541]

I get why voice actors are so scared now

[@headmaster4806]

Hello! I have problem! In the program my GPU is GPU (dml) and it has options: cpu, 0, 1, 2, 3. Why there's no my graphic card?

[@timpl0168]

How much does the mic quality influence the output? I have tried a lot of settings but it still sounds chunky and robotic from time to time. I have EXTRA maxed out, run a RTX 4080 and everything over 640 CHUNK sounds the same. Has anyone with a bad mic tried this and it did work well?

[@statics1]

I know this is late but my mic quality is pretty bad but works very well

[@kaishepherd7914]

This took me 2-3+ hours but I'm proud to say, I've officially become a computer scientist /J (it worked~to be fair, I was on Mac watching a reg pc review, but it all worked out in the end ;)

[@carlosfbarajas7755]

This tool is too powerful