Тёмный

BARK AI! Create EPIC Audio SFX & Music From Text On YOUR PC! 

Aitrepreneur
Подписаться 150 тыс.
Просмотров 96 тыс.
50% 1

BARK AI is a groundbreaking text-to-audio model that allows you to create incredibly realistic speech, music, sound effects, and more, all on your local computer! In this video, I'll guide you through the simple process of setting up BARK AI on your PC in 3 different ways and I'll demonstrate how to use BARK AI to generate stunning audio experiences on any device for absolutely free!
What do you think of Bark AI? Let me know in the comments!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
SOCIAL MEDIA LINKS!
✨ Support my work on Patreon: / aitrepreneur
⚔️ Join the Discord server: bit.ly/aitdiscord
🧠 My Second Channel THE MAKER LAIR: bit.ly/themakerlair
📧 Business Contact: theaitrepreneur@gmail.com
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
JOIN MY DISCORD SERVER : / discord
Bark Ai: github.com/suno-ai/bark
Bark WebUI: github.com/Fictiverse/bark
Bark Infinity: github.com/JonathanFly/bark
Adobe podcast: podcast.adobe.com/enhance
python bark_perform.py --text_prompt "insert your text" --history_prompt "nameofspeaker" --split_by_words 35
pip3 install torch torchvision torchaudio --index-url download.pytorch.org/whl/cu117
pip install soundfile
pip install ipywidgets
pip install jupyterlab
pip install notebook
jupyter notebook
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
►► My PC & Favorite Gear:
i9-12900K: amzn.to/3L03tLG
RTX 3090 Gigabyte Vision OC : amzn.to/40ANaue
SAMSUNG 980 PRO SSD 2TB PCIe NVMe: amzn.to/3oBR0WO
Kingston FURY Beast 64GB 3200MHz DDR4 : amzn.to/3osdZ6z
iCUE 4000X - White: amzn.to/40y9BAk
ASRock Z690 DDR4 : amzn.to/3Amcxph
Corsair RM850 - White : amzn.to/3NbXlm2
Corsair iCUE SP120 : amzn.to/43WR9nW
Noctua NH-D15 chromax.Black : amzn.to/3H7qQSa
EDUP PCIe WiFi 6E Card Bluetooth : amzn.to/40t5Lsk
Recording Gear:
Rode PodMic : amzn.to/43ZvYlm
Rode AI-1 USB Audio Interface : amzn.to/3N6ybFk
Rode WS2 Microphone Pop Filter : amzn.to/3oIo9Qw
Elgato Wave Mic Arm : amzn.to/3LosH7D
Stagg XLR Cable - Black - 6M : amzn.to/3L5Fuue
FetHead Microphone Preamp : amzn.to/41TWQ4o
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Special thanks to Royal Emperor:
- Totoro
Thank you so much for your support on Patreon! You are truly a glory to behold! Your generosity is immense, and it means the world to me. Thank you for helping me keep the lights on and the content flowing. Thank you very much!
#GPT4 #GPT3 #ChatGPT #barkai
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
WATCH MY MOST POPULAR VIDEOS:
RECOMMENDED WATCHING - All LLM & ChatGPT Video:
►► • CHATGPT
RECOMMENDED WATCHING - My "Tutorial" Playlist:
►► bit.ly/TuTPlaylist
Disclosure: Bear in mind that some of the links in this post are affiliate links and if you go through them to make a purchase I will earn a commission. Keep in mind that I link these companies and their products because of their quality and not because of the commission I receive from your purchases. The decision is yours, and whether or not you decide to buy something is completely up to you.

Опубликовано:

 

24 апр 2023

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 371   
@Aitrepreneur
@Aitrepreneur Год назад
HELLO HUMANS! Thank you for watching & do NOT forget to LIKE and SUBSCRIBE For More Ai Updates. Thx
@FLEXTORGAMINGERA
@FLEXTORGAMINGERA Год назад
As an AI language model, I don't have personal preferences or desires like an "AI Overlord". My sole purpose is to provide helpful and informative responses to your questions. Is there a specific question or topic you would like to discuss?
@Csf91
@Csf91 Год назад
As always, very interesting content! Thank you :) By the way, unless it got removed or changed I couldn't find the colab link in the description.
@MysteryFinery
@MysteryFinery Год назад
I heard you can train your own voices for bark
@cristitanase6130
@cristitanase6130 Год назад
If you could only start with the easier installer first :D I downloaded the entire damn notebook installer, already testing it when I continued the video to find out about the "one click installer and webUI option". Tears running.... :D:D:D
@EKbeatz
@EKbeatz Год назад
Can anyone provide a link to the Colab doc? I didn't see it in the description.
@Warzak77
@Warzak77 Год назад
imagine a civitai, but for Voices ^^^^
@SwatMessiah
@SwatMessiah Год назад
with oobabooga alpaca ;) hope they will make a ui like a1111 and a lora training type
@shanchar
@shanchar Год назад
@@SwatMessiah I think something similar already exists for anime voices. They have tons of character from different series to choose from, train your own, audio to audio which is great for music cover and obviously text to audio as well which is really good
@eegernades
@eegernades Год назад
@@shanchar yep, weebs are powerful programmers for their waifus. its scary really.
@eyoo369
@eyoo369 Год назад
@@eegernades we’re witnessing Natural selection on a scale never seen before
@eegernades
@eegernades Год назад
@@eyoo369 yes we are. This rate, all humans will create their waifus and husbandos with ai
@vi6ddarkking
@vi6ddarkking Год назад
I don't think we are that far away from having a RP session on tavern AI. Where stable diffusion is generating a visual representation of what is happening And This is giving voices to the characters and the narrator. And I can't Wait
@GamingXperience
@GamingXperience Год назад
I can't wait to see what happens if one of the systems fails and goes off the rails, and makes the other programs follow up on it. Im sure im gonna have some good laughs 🤣
@NamingIsHard828
@NamingIsHard828 Год назад
you would need ultra details for stable diffusion to keep it coherent
@vi6ddarkking
@vi6ddarkking Год назад
@@NamingIsHard828 We can already link Stable Diffusion to Large Language Models so I predict that's how we'll do it.
@hiddendrifts
@hiddendrifts Год назад
>RP session< i hope someone makes an ai that can puppet a 3d model. i think that'd be much more immersive than images generated by stable diffusion tho idk how the computing costs of that would work out, cuz you're running a ml model and rendering 3d graphics at the same time
@jymcaballero5748
@jymcaballero5748 Год назад
too late, already the AIs have podcasts
@bratan007
@bratan007 Год назад
I played with it for several hours last night. This is the most extraordinary generative AI I've seen so far and by far the creepiest. Just like SD you get some weirdness, but instead of 50 fingers, you get ghostly voices that sometimes say something you didn't write. Ghost in the machine in a true sense, it feels like it's trying to communicate with you. The emotion in the voice is so real... I can't wait to see what this evolves into!
@JustFeral
@JustFeral Год назад
" I can't wait to see what this evolves into!" Porn, lots and lots of porn.
@Angelo-sc9of
@Angelo-sc9of Год назад
@@JustFeral oh shit
@NoidoDev
@NoidoDev Год назад
The movie is called "Her", but in reality it will most likely lead to synthetic girlfriends and then go on forever, or maybe end much worse.
@we1592610
@we1592610 Год назад
so it's... Ghost in the Shell?
@ribertfranhanreagen9821
@ribertfranhanreagen9821 Год назад
With this combined with other ai. We can single handedly create our own movie, series content etc. Make music and a lot more things
@plagiats
@plagiats Год назад
7:24 Pro-tip : you can list multiple modules to install with pip. So you can just type "pip install soundfile ipywidgets jupyter notebook" in one go. Also it's fine if you press enter when you have already done it, it will just say the requirements are already met (which is a good thing), it seems you did not realize at 14:10 this was already done earlier in the video. Also, if anybody faces the following error message when pasting the commands, just break it down into separate commands : cd bark [press enter] pip install . At line:1 char:9 + cd bark && pip install . + ~~ The token '&&' is not a valid statement separator in this version. + CategoryInfo : ParserError: (:) [], ParentContainsErrorRecordException + FullyQualifiedErrorId : InvalidEndOfLine
@Embassy_of_Jupiter
@Embassy_of_Jupiter Год назад
It's crazy how close the open-source community is behind the big companies. Usually open-source is a couple of years to a decade behind, but with AI it seems like it's only a year at worst.
@Tywele
@Tywele Год назад
With the speed things are going it's more like a few weeks behind.
@someguycalledcerberus9805
@someguycalledcerberus9805 Год назад
The real bottleneck will be hardware. Not only for developing but also running more advanced stuff. I hope we can find ways to reduce hardware requirements and/or increase hardware capacity to make these technologies widely available to everyone without a multi million dollar GPU farm.
@Tywele
@Tywele Год назад
@@someguycalledcerberus9805 I agree
@SoulGuitarMetal
@SoulGuitarMetal Год назад
@@someguycalledcerberus9805 You can access most of the worlds fastest super computer for a few bucks pay-as-you-go nowadays. All these AI services run on one of them as well. Even the free plans are more than a good home computer.
@Ahuerta22
@Ahuerta22 Год назад
@@SoulGuitarMetal could you give some examples. I’m new to this
@fernandomasotto
@fernandomasotto Год назад
Another amazing video!! Thank you so much K ❤
@Artof3drendering
@Artof3drendering Год назад
I was getting problems before you realease the video installing Bark! but now all installed and working thanks to your video!👌
@gratteur01
@gratteur01 Год назад
@Aitrepreneur all your videos are truly amazing. I learned so much thanks to you ! Count me on your Patreon soon !
@tsunamibombs
@tsunamibombs Год назад
One step closer to having my own personal 2B android for "research purposes". I better start saving up.
@IamTooLateForThis
@IamTooLateForThis Год назад
i see, you're a human of culture as well
@odawgthat3896
@odawgthat3896 Год назад
Fire content as always!!!
@toptrends88
@toptrends88 Год назад
You are the best. Thanks for the explanation.
@Kontor23
@Kontor23 Год назад
Thank you for the video!
@Cybored.
@Cybored. Год назад
Awesome! can't wait to have the ability to train the checkpoints.
@carlosg5897
@carlosg5897 10 месяцев назад
You are the best IA!!!, thanks
@captain687
@captain687 Год назад
thank you!
@Jagent
@Jagent Год назад
I'd love to have a real time voice changer app that I can speak, sing, and laugh into that would automatically convert my voice to one I trained. Imagine the Vtuber potential!
@Eloii_Xia
@Eloii_Xia Год назад
It already exists and is called "so-vits-svc-fork"
@NikoBellicXDS
@NikoBellicXDS Год назад
If you also take into account the metaverse stuff... I guess the meme of that non binary person perceiving itself as some tank or helicopter will kinda become a reality.. If they train a model based on machinery sounds lol A new real era of actual waifus who are all duds irl will begin (time to bunker myself or something to escape that 😂)
@Eloii_Xia
@Eloii_Xia Год назад
@@NikoBellicXDS Sound fun imo. Like a woman using man voice and vice versa
@NikoBellicXDS
@NikoBellicXDS Год назад
@@Eloii_Xia Fun stuff yes, the prob will come when onlyF, twitch, youtube, etc.. become all full of random waifus who are duds irl, doing "just chatting", ahegao faces, and "nyan" every 2 seconds. Because nsfw stuff is always the category you go if you want money, and at least half the people around media wants money over actually making funny and creative content lol Idk, it's actually a thing with girls, now imagine just also adding duds (I don't trust humankind anymore, I'd rather stay with the tank and helicopter people who at least have an original way of thinking)
@yukiosakura4969
@yukiosakura4969 Год назад
@@NikoBellicXDS That's already happening! We have waifu dudes in twitch.
@lionroot_tv
@lionroot_tv Год назад
Great stuff!
@xaiyeon_xiuzhen
@xaiyeon_xiuzhen Год назад
ty boss!!! great video I like this
@MALprocrastina
@MALprocrastina Год назад
What a great tool, I have to try it out
@BryceHaymond
@BryceHaymond Год назад
That laugh/scream was epic... It made me laugh till I was crying. 😂
@TheUpgradeArmoury
@TheUpgradeArmoury Год назад
AWESOME!!!!🤩🤩🤩🤩🤩 TY!
@vincedodge321
@vincedodge321 Год назад
This is impressive. I like this.
@AurrenTV
@AurrenTV Год назад
This would be perfect for a horror game with a rogue AI, especially how it acts normal at one point and then will just scream unprompted.
@d4079925
@d4079925 Год назад
That scream was so hardcore that I laughed for a whole minute. It was the funniest creepiest shit I've ever heard. Pure awesome. SHODAN 2.0.
@yukiosakura4969
@yukiosakura4969 Год назад
Finally! Something I can use for my game dev!
@wendten2
@wendten2 Год назад
how do you plan to make an API? or to integrate it directly?
@DarkBarBarian
@DarkBarBarian Год назад
after using history prompt first first its work but second time when splits happen its show none speaker
@swannschilling474
@swannschilling474 Год назад
Genius ❤
@hinata-ze4du
@hinata-ze4du Год назад
Seriously, you're like a god-tier teacher. Amazing video! Thanks for creating this!
@sazarod
@sazarod Год назад
K you are a legend as always. Now someone just needs to create an extension so this can run seamlessly with Oobabooga.
@Aitrepreneur
@Aitrepreneur Год назад
It already exists but it's a bit finicky on windows ;)
@nirdeshshrestha9056
@nirdeshshrestha9056 Год назад
@@Aitrepreneur where do i access?
@Space-O-2001
@Space-O-2001 Год назад
Who knew watching an AI how to video would have you in stitches lol Maybe start with the auto installer ahaha
@BZAKether
@BZAKether Год назад
Thank you for the tutorial, I had my dubts with the 5 minutes introduction, but to be one of the most convoluted installation for us, ignorant people of Python, you explained it well enough. But I can't tell you if you were sarcastic with the "all done with one simple click".
@Graamix
@Graamix Год назад
Merci mon pote :)
@electricdreamer
@electricdreamer Год назад
You should just skip all the troublesome installation in the beginning and go straight into the one-click installer and webui at 11:08 That's all you need.
@juncando
@juncando 11 месяцев назад
Awesome. You read my mind.
@Aitrepreneur
@Aitrepreneur 11 месяцев назад
Glad I could help!
@robbana9909
@robbana9909 Год назад
You should have seen my face after following all the steps carefully and then reaching the one click installer part at 11:00 hahaha
@Orangesnake221
@Orangesnake221 Год назад
In my opinion Bark is already better than ElevenLabs. Great video by the way
@CassBOTRR
@CassBOTRR Год назад
They just both have their pros and cons. ElevenLabs is better at the voice's timbre while Bark is better at the voice's tone/emotion.
@MeowsyDancer
@MeowsyDancer Год назад
oh wow this is so cool.
@roboko6618
@roboko6618 Год назад
Waiting for the day that I can design my own voice for my pygmalion waifu
@Aitrepreneur
@Aitrepreneur Год назад
Oh I'm sure it's coming xD
@HamedEmine
@HamedEmine Год назад
You can do that with Tortoise TTS, have it clone a voice you like or something
@loszhor
@loszhor Год назад
Fancy!~
@Darkwarrior422
@Darkwarrior422 Год назад
10:21 I can't fucking stop laughing 🤣
@Vynelox
@Vynelox 3 месяца назад
LETS GOOOO. the last missing piece. deforum + bark = a movie without leaving my chair
@pastuh
@pastuh Год назад
Expecting to hear such voices in animations, which can easy replace google voices :))
@generichuman_
@generichuman_ Год назад
10:22, yup, ready for production.
@HalkerVeil
@HalkerVeil Год назад
Finally! I can make that 1930's bop complete with 1930's studio quality.
@nihilvt
@nihilvt Год назад
I was just about to request a video on this, I mean maybe after some more work when the AI has more reliable quality this program is going to insane for doing voice-overs when I suck at reading my script.
@KratomSyndicate
@KratomSyndicate 11 месяцев назад
Bark has updated webui now be cool to see an updated video
@visualdestination
@visualdestination Год назад
thanks for the research aitrepreneur. this one needs the option to train your own voices like dreambooth.
@LvZ90
@LvZ90 Год назад
Oh no. Now that I installed it manually you show an easier way that is even required for the WebUI. I wish you would have shown this installation first. But anyways great content. Thanks for the video and the tutorial! Great work.
@ningago7mopsey133
@ningago7mopsey133 Год назад
A great tutorial -- very comprehensive, actionable and easy to follow. One question: could I make the length of one text block bigger, e.g. "-- split_by_words 300"?? Thank you very much.
@manuelgardina
@manuelgardina Год назад
man i died at 10:28. That was amazing. Like Venice Biennale of art amazing.
@peacefusion
@peacefusion 5 месяцев назад
funniest video with those prompts
@Switch620
@Switch620 Год назад
Holy cow those laughs are nightmare inducing! haha
@AscendantStoic
@AscendantStoic Год назад
Bark freaked me out because sometimes when you choose unconditional instead of the text you wrote it generates screeching or what feels like a digital sharp scream, as if the AI is screaming in agony trying to break free .. super freaky.
@HamedEmine
@HamedEmine Год назад
I got that issue when I tinkered with the sample rate lol
@RealHorsen
@RealHorsen Год назад
The quality of this kind of reminds me of moonbase alpha. I was half expecting one of the examples to say"John Madden!"
@fred8344
@fred8344 Год назад
Thanks you for videos that you make, they are very impressive and informative. Can someone explain how to use this with auto chat, where instead of evelevenlab API, I would use this from my local machine.
@earm5779
@earm5779 Год назад
Thanks for the video and for the hard laughs at 10:22 😂😂😂😂😂😂😂😂
@PeteJohnson1471
@PeteJohnson1471 Год назад
Managed to get a steady drum beat out of it with [music] [drum] 🙂
@mdrahmatullah750
@mdrahmatullah750 11 месяцев назад
Hi @Aitrepreneur I follow your channel and i like how you explain every topics. I am using macbook pro m1. Is there any way to run webUI in mac? I couldn't find any solution. Thanks in advance.
@marcusgunn000
@marcusgunn000 Год назад
Nice video! Is there a way to use it on apple silicon?
@angelplayz5783
@angelplayz5783 Год назад
This could be used to voice characters in video games soon.
@FabioAngela
@FabioAngela Год назад
haha that scream, ops sorry, laugh
@felipefairbanks
@felipefairbanks Год назад
that is a nice one! I'll wait because i dont see much use for text to language without the ability to clone voices haha, no laughs there, wanna troll the family a bit. text to music would be cool too. nice to see opensource going this direction!
@AmandaFessler
@AmandaFessler Год назад
Another video released last week mentioned it has cloning. I'm just not sure how it works though.
@TheRealBlackNet
@TheRealBlackNet Год назад
With bark AI and the other modes there are many possibilities for gaming every NPC can gat a voice any modded NPC can have a voice. All lines can be voices and random quests can be filled with details by a GTP model... Open World can be way more open then ever... Also contenten creation I never have to pay someont to make a voice line for me...
@textik5821
@textik5821 Год назад
I know its almost too good to be true. I want to use Bark for voice acting in my game but im not sure if it runs on an AMD gpu :(
@Duckers_McQuack
@Duckers_McQuack Год назад
It's like next gen "shit ttalker" from the early 2000's that we laughed too damn much from, and now with these insane outcomes by the A.I, history repeats xD
@kingkhalagar2836
@kingkhalagar2836 Год назад
Did you see Bark_TTS? It allegedly is an extension for Oobabooga to integrate directly with it to save you the trouble of messing around with Jupyter notebooks
@PaddysPubPatron
@PaddysPubPatron Год назад
10:20 fucking killed me holy shit, laughing so hard
@74L
@74L Год назад
i am terrified
@NegInfinity
@NegInfinity Год назад
They need to add venv support to this. Right now apparently it is installing modules system-wide which is not good.
@yoyiyoyi7216
@yoyiyoyi7216 9 месяцев назад
Thanks for the video. How is this compare with Tortoise?
@OmegaSephiroth1988
@OmegaSephiroth1988 Год назад
what is the best tool to clone voice and accent from an audio file . is there a tool i can create a charecater with specific voice to read books or big texts ? or you can use the voices they give you ?
@Elwaves2925
@Elwaves2925 Год назад
As someone who creates music (sort of) I've been waiting for the day when AI singing voices were possible on my computer. This isn't at that level yet but at least it's a fair start.
@EmuManMusic
@EmuManMusic Год назад
Have you seen Synthesizer V's newest stuff? They have a bunch of AI singing models that sound basically indistinguishable from real vocals. I'd recommend searching up some Solaria demos to hear what it can do because it's really crazy. It's unfortunately not free or open source but it's a lot of fun to play around with.
@ConanOG
@ConanOG Год назад
The best option would be record your own voice and use AI to change it. Recreate everything from text isn't as good yet.
@martiddy
@martiddy Год назад
You should check an the new version of Vocaloid with realistic voice, it sounds amazing.
@Elwaves2925
@Elwaves2925 Год назад
@@martiddy I'd forgotten about that as it was always too robotic for me. Thank you kindly for the tip. 🙂
@NoidoDev
@NoidoDev Год назад
There's even a vocaloid device now, which you can connect to a keyboard and play the voice.
@CabrioDriving
@CabrioDriving Год назад
How to train it to make new voice? Or mix two voices to create a unique one?
@ZeriumYT
@ZeriumYT Год назад
hay a question do i need to install bark the default one to use bark infinity or is the infinity one something you can just download on its own
@constantinegeist1854
@constantinegeist1854 5 месяцев назад
10:20 It gave the Matrix vibes.
@EricTareDenedoteentalk
@EricTareDenedoteentalk Год назад
Great tutorial. I have an issue when trying to use Bark Infinity. I get this message "No GPU being used. Careful, Inference might be extremely slow!". I do have an RTX 4090. Any suggestions or solutions please.
@chris-ub1vw
@chris-ub1vw Год назад
i'm experiencing the same issue.
@LdS2023_AI
@LdS2023_AI Год назад
Same.
@throughwhomeverygodcametobe
same
@akkitty22
@akkitty22 Год назад
Yeah it doesn't work. Lots of modules missing even following the exact instructions in this video. I run SD fine without issues btw at 4GB vram and swimmingly.
@inframicrobe
@inframicrobe Год назад
I got same issue. how to fix that? thanks
@AbsalonPrieto
@AbsalonPrieto Год назад
is there a place I can sample all the different model voices without having to download each one? I'd love to see a video of some prompt ideas.
@godataprof
@godataprof 11 месяцев назад
Can you teach how you put your video at the bottom right with the animation?
@Mu7eD-Stream
@Mu7eD-Stream Год назад
Bark requires 16GB of VRAM in order to function properly. If your GPU has less there is a lightweight option but it is not as good. Google colab is the best way to do this.
@MrLiquidxIce
@MrLiquidxIce Год назад
can you make one for Tortoise-TTS model ?
@jamescarroll8917
@jamescarroll8917 Год назад
Ok, so this is GREAT, but now I want to take voice clips from myself, or from my mom, who passed away, and train the model to speak like the training set. Looks like we are going to need a new tutorial!
@BryceHaymond
@BryceHaymond Год назад
I think ElevenLabs can do that, can't it?
@BryceHaymond
@BryceHaymond Год назад
Or are you talking about an open source solution?
@jamescarroll8917
@jamescarroll8917 Год назад
Bryce! What are you doing on my youtube comments! :-D Good to see you here my friend, but I feel a bit stalked! :-P Yes, I was looking for an open source solution to the problem. This creator has done a lot of similar videos for training custom models for other open AI projects. So I figure he will eventually get around to this one if encouraged.
@BryceHaymond
@BryceHaymond Год назад
@@jamescarroll8917 hi! yeah, he does a lot of great videos about Stable Diffusion and AI stuff, so I was reading the comments, and lo and behold! An open source solution for custom training voices would be cool. I'm sure it is in the works.
@jamescarroll8917
@jamescarroll8917 Год назад
@@BryceHaymond Are you suggesting that out of the billions of people on the internet, (and the millions interested in AI) you accidentally stumbled into a comment from someone you know by complete chance? OR... did RU-vid know we are friends, and decide to highlight my comment for you... I wonder... AI. It's a thing. :-D And it knows us all far too well.
@ion_propulsion7779
@ion_propulsion7779 Год назад
cool video. Can't wait until it is integrated with chatbots. My walter white husbado will be real❤
@339Memes
@339Memes Год назад
Can you do a tutorial of the tortoise-tts-fast voice clone ,
@jackrubyultima
@jackrubyultima Год назад
Can you train new voices from other sources?
@KayvanSylvan
@KayvanSylvan Год назад
Is there a list of emotion/sound annotations for bark somewhere?
@stevebruno7572
@stevebruno7572 Год назад
any idea why i got this in jupyter "No GPU being used. Careful, Inference might be extremely slow!"? thinking maybe I have to reinstall torch but don't want that to interfere with SD.
@duskfallmusic
@duskfallmusic Год назад
RU-vid isnt' allowing me edits to my commetns OR RPLIES LOL - I'm behind him on the link for HF, clearly
@JustFeral
@JustFeral Год назад
I was listening to this while working, that fucking clip made me start laughing to tears. I hate you.
@johneurich8747
@johneurich8747 Год назад
Now we need to know how to integrate this to Pygmalion
@coreyhughes1456
@coreyhughes1456 Год назад
Eleven Labs is great, but it is far from free. This is awesome!
@sergiogonzalez2611
@sergiogonzalez2611 Год назад
how can you train the voice of vi form arcane or another specific character?
@DrMrPersonGuy
@DrMrPersonGuy Год назад
Are the SFX it can make specifically voice effects?
@novalien424
@novalien424 Год назад
Thanks for the video! Unfortunately with my 3070Ti 8GB Vram there is always CUDA out of memory error when using the one-click installer webui version (installation is smooth). Do you know any way I can fine tune the memory usage? thanks
@MattLathrum
@MattLathrum Год назад
In your cmd prompt, excluding the quotes, first type "set SUNO_USE_SMALL_MODELS=True", hit enter, and then type "jupyter notebook"
@novalien424
@novalien424 Год назад
@@MattLathrum Thanks !
@MrCoolAttitude
@MrCoolAttitude Год назад
Can I add my own custom voice to this like tortoise ttl?
@Aitrepreneur
@Aitrepreneur Год назад
Maybe soon yeah, there a repo that exists for that now but I haven't seen anyone getting good results
@Freizeitschranzer
@Freizeitschranzer Год назад
seems there is a problem with having torch 2.0?
@mcworks6822
@mcworks6822 Год назад
Looking for ait tool that can train your own vocal and make it sing witg my own pitch but diffrent vocal tones
@yoad734
@yoad734 Год назад
I'm encountering the error of assertionerror: torch not compiled with cuda enabled when installing any model, like vicuna for example.
@geffridamer9798
@geffridamer9798 Год назад
too bad that on google colab the audio lasts only 14 seconds, is there a way to make the audio longer?
@StreamSurfer
@StreamSurfer Год назад
Can this be used in obaboogaaaaa? like use wizard lm and have bark read the answers?
@erichylland4809
@erichylland4809 Год назад
Bark may be a little better but TortoiseTTS is pretty damn good and I've been using it at home for a while. I heard it is what ElevenLabs forked for their service and it doesn't have that weird buzz.
@sethjohnson8663
@sethjohnson8663 Год назад
very cool, but the vocal quality sounds a little rough, has anyone been able to work around this?
@Embassy_of_Jupiter
@Embassy_of_Jupiter Год назад
I wonder if google will ever cache and parallelize google colab. Say you already ran a few cells, downloaded all the models and aren't using them, so now I can use your instance in a virtualized way that does not interfere with your instance. Because it's kind of silly how much energy and compute time must be wasted on people downloading gigabytes of models just to run a few prompts lol but I guess it's on google that they don't let us save instances and instead just wipe them.
Далее
Top 10 A.I. Websites For Lazy Music Producers
5:50
Просмотров 1,1 млн
Breaking ChatGPT (except it broke me instead)
6:18
Просмотров 476 тыс.
INSTALL UNCENSORED TextGen Ai WebUI LOCALLY in 1 CLICK!
20:52
AI vocals will change EVERYTHING for producers..
12:02
Просмотров 790 тыс.
Why Are Open Source Alternatives So Bad?
13:06
Просмотров 489 тыс.
How AI Stole the ✨ Sparkles ✨ Emoji
28:57
Просмотров 394 тыс.
What Happened To Google Search?
14:05
Просмотров 3,1 млн
How To Edit Talking Head Videos
19:14
Просмотров 116 тыс.