This Audio Editing Tool "Deep Faked" My Voice 👀 (Actually Useful or SCARY?)
HTML-код
- Опубликовано: 6 сен 2024
- I've been using a new tool, Descript - www.patflynn.co... - for editing audio and video, and it's definitely made my life a lot easier. It's actually a game-changer. However, within the tool, there's a feature called Overdub that allows the program to read text in your voice, without you having to record it. Let me show you:
So what do you think? Useful, or not?
Also, here's a link to a video where I show you more about how awesome this tool is for general editing for podcasts and videos: • This New Audio & Video...
Interested in AI and how it could potentially even write sales copy? Check out this video here: • A.I. Robots Can Write ...
=-=-=-=
Listen to podcasts? Here are a couple of podcasts that I personally host (with over 65 million combined downloads) that will help you on your online business journey:
The Smart Passive Income Podcast: www.smartpassi...
AskPat (these are real life business coaching calls): www.smartpassi...
Also, have you thought about starting your own podcast? Check out my famous podcasting tutorial here on RUclips, the #1 podcasting tutorial on the platform:
• How to Start a Podcast...
The podcasting equipment I use: www.kit.co/patf...
My video and live streaming equipment: patflynn.com/l...
Also, follow me at these places below and say hi!
Personal site: www.patflynn.com
Instagram: / patflynn
Twitter: / patflynn
Cheers, and as always, #teamflynnforthewin
Musicbed SyncID: MB01NFJO8AER7YY
This could be massively useful for generating spoken dialog in RPG games, instead of having to read every word.
Yeah! Soon enough games can just generate random voices of non-existing people, which will make the development much cheaper and faster!
wow never thought of this, Nvidia has made ai facial animations as well.
YES. Crpgs can finally have dub with a small budget
First faces of non existent people now voices of non existent people then bodies of non existent people. Throw it in a nerve link vr game by unreal engine 10, and forget it's not real life, then call the devs scanning for bugs ufo's. Imagine 😂😂😅😅🤔🤔 hmm.
This... this alone has pushed me over to the "I need this" realm
Yup there comes a lot of memes of ancient famous people "predicting" the future
SUP ZACHHHH!
Yooo
"There will be a virus that kills many people in the 2020s. Hee hee" -Michael Jackson, 1997.
@@CaseCat Well, "many" is a bit overshoot ^^
@@surronzak8154 well, there's like atleast 16, 16 is a lot for me.
now imagine this is the future. You're writing a novel and having it played back to you in your voice which each of the characters sounding exactly as you imagine them because the AI saw the quote marks, looked ahead to see who was talking, and temporarily switched to that voice.
Further more, you could write a simple script and it would give you an AI generated movie with any actor or actrees you want, all for $30 a month
Nice Idea bro
@@lozersheep8921 AI will write books, so I think the conversation is over, we just give them instructions of what the book is about, kind of what I am doing with CODEX now, next 5-10 years are going to be crazy
It seems you don't have any clue about HOW AI actually works.
In order to have a voice, Ai need PARAMETERS, SAMPLES. Simply changing the pitch won't work, and we can change pitch on studio since the begining of times.
@@flaviomorofurian5271 A.I. might, but Machine Learning is machine learning because there are forms that are parameter-less. samples yes of course, but the collective data we already have can do the OP's idea very easily already today. weve had hundreds of thousands of existing recorded audio to train from for years.
to the OP: you only need a believable voice assigned to a character.. not a forensically accurate voice. a trained tool can analyze and guess a large majority of context of who is speaking.. a configure file can assign character name to voice. and there are ML models that can take guesses at the "intent" of the words ( the emotion)
i bet an ML generated short story is already possible. with voice talent. and we are pretty much there for an expressive, stylized video result too. ( not film quality yet, but shortfilm project quality 90% there)
I wish I had enough of my mom’s voice recorded so I could hear her with this again since she past
I'm sorry. I hope she rests in peace.
Bro💀
yes😭
Wow
Aww. Man, the people in the comment section are thinking up all kinds of wonderful ideas to use this tech.
Where I see this being a HUGE benefit is for people who do audiobooks and read HUGE amounts of text. Another use is for people who voiceover their videos. I think this is a great tool. Not creeped out at at all by it.
Dangerously useful. 😆
tru I can make a sus audio of my friend
Usefully dangerous
@@Bulususedits yo I don’t think that’s a good idea 😂
Yeah
If processing speed increases it can even be used as a next generation voice changer.
The overdub sounds a little too clean when played right next to a recording. By itself, it's pretty great, but side by side like that the difference is a bit jarring. I imagine at some point they'll have the AI mimic any kind of mic and background noise when overdubbing. Not dissimilar to how you can add certain grains to photo/videos to mimic different films.
You could, however, clean those up in your base track beforehand.
Descript now has a new feature called Studio Sound that's designed to clean up audio. It's actually crazy how good it is. I've used it on some audio from my friend I used to do a podcast with. Unfortunately he recorded through a gaming headset into his phone so the quality was pretty terrible. Using their new Studio Sound feature, it legit sounds like he recorded it in a proper microphone with no background noise.
It already exists. It's called iZotope Dialogue Match.
The overdub sounded like NileGreen to me.
@@micahtouchet あっぷ
Deepfakes are about to reach a whole new level.
Now you can FAKE the voices easily too
Command voice activated
@Satoru Gojo I know. It was just a joke.
When he said fake my voice that's why I mentioned the t shirt.
All in fun.
Deepfake already made us into cakes
One day this start THE WORLD WAR.
Whats crazy is that this could also be used in the music industry. The more I think about it based off of what you’ve shown in the video using someone’s vocal tonality and kind of making it midi based. You could type your lyrics in a plug-in and every time that a note is triggered it could read the next line on the midi grid, in the correct notation. This of absolutely fascinating and could work in metal vocals too
Emvoice Pro
With various effect processing over the signal, the flatness/robotic nature of the voices could easily be masked. Especially true for music (like chorus and/or autotune).
That would be so cool
A liquid Drum and Bass album using the voices of Frank Sinatra and Nat King Cole. That would be wild, Endless possibilities.
From what I read recently, over 100 songs on the music charts currently are AI. It's here.
Everyone should be absolutely terrified at the implications of this.
We all are, but at the same time we also can't help but be curious
I'm almost 99% sure that the Don voice is Epic voice guy from the Honest Trailers videos!
Pretty sure that it's a meta-reference by using the Jon Bailey's (the Epic Voice Guy) voice, changing the name one letter so it's not just Jon, and also making it Don which is references Don LaFontaine, the most famous trailer voice narrator ever.
I'm 99.9999999999999999999999% sure that's definitely, possibly, the Honest Trailer voice.
Yeah that's his voice alright I've listened to him for hours on end, I was doing to make the same comment
was about to comment the same thing lol
Made the same comment, but saw this one, and deleted mine.
Totally amazing. I only have a RUclips channel but this is making me want to do a podcast. The editing and overdub options are total game changers.
@Angel A okay, you're right, we're taking it down, btw i'm an fbi agent looking at youtube comments to find out ilegal tools, thanks for your cooperation
@@fabrizio_sant lmao
@@fabrizio_sant LOL
I don’t know if this is satire or if you’re young
@@Socvinc yea idk either
“Im an fbi agent”
Seems pretty useful. They just need to somehow a add a hidden aspect to the file to show that was artificially generated, like an audible equivalent to a watermark that all microphones can pick up but people cannot hear.
wouldn't be that hard to find and edit it out
That's the point to makes sure edited voice files don't get used easily in court. If it say uses -hz or 20,001+ Hz so that you don't hear it but if there is a specific pattern of unhearable Hz throughout the recording then it will clean watermark without ruining the voice file
@@meh6513 and would take 5secs in editing to remove
@@LiLBitsDK better than nothing. would you rather remove the 'watermark' completely?
@@gwyneth8306 Yes.
It sounds pretty good. As a commercial editor I can see using this in the future when it gets better for corporate training videos
I've honestly expected voice deepfaking to pop up much, much faster/sooner than graphical deepfaking.
I am not surprised to the slightest that its here now too.
It's been here for a while. I remember using it 3 or 4 years ago when the first ones started coming out and be publically available.
@@michaelcaplin8969 Can you tell me what is the name of this program and who can download it
It did, but a video of a synthesized Tom Cruise voice isn't as clickbaity as a video of his face but not his face
I need that scary tool :)
Definitely cool. Most definitely scary.
Won't bother me none.
$30 a month.
For what🤣
Adobe made one called Adobe vocoder which took a 15 min speech sample and on the fly take text and playback accurate voice speech..
Wish it would leak to the public..
Lots of applications...there are always some "deep" stuff that can be generated from everything and anything today. I'd put those fears aside coz if you don't do it, somebody has already done that somewhere and you just don't know about it, yet.
I think this is a pretty amazing tool....not just for editing and overdubbing pretty quickly but it also brings consistency to your work. Pretty useful for coaching/learning videos and can be integrated with LMS platforms for delivering engaging content. Will.be good for educational institutions as well as for talent management in corporate environments.
I feel like it would be handy for voice lines in animations and animatics. Why organise to record voice lines with friends, colleges for an early pass when you could copy paste your script and have a working prototype to get right into animating.
Can you tell me the name of this program and where I can download it?
Daaang, crazy powerful tools!
Ok
Ye
This is a dream come true for those who make or want to be able to make animated shorts but are too poor to pay for voice actors. Hopefully they will improve or continue to improve this.
Dude, this tool is freaking amazing! Whoever made this program, what an incredible mind behind its creation. I'm sure this'll help anyone that doesn't want to use your own voice, or even a day that you cannot simply talk normally but you had your backup voice to do this for you. This is awesome!
OMG, 9:23 sounds like CinemaSins
Well this is amazing. Game developers could use this for dabbing characters ingame. Like you get someone who is going to give you "his voice" and that´s it. You can just type, get this tool to generate voice, and use it ingame. No need for actual person whose voice this is to read character script dialogs. And when developer wants new script he just use this tool to generate more and doesn´t need that voice actor to be there.
As a writer I would love to test this out with characters. I would love to test using one of my character’s voices and see if the AI will create a believable voice around that. UPDATE: it works with characters to an extent. You must keep in mind to speak clearly and when typing that grammar is phonetic as far as the AI is concerned.
as a musician I could hear even the differences in the room recording "around the voice" - it might not fool an avid "hearer" but it was and is stupidly good
Add some Altiverb with the right room, and there'll be no difference.. You could make an impulse of the exact room and it'll be hard to distinguish. Really hard. Being able to hear a difference in room really doesn't say much about how good something fakes your voice, it's not a reverb.. Most Voice-Overs are recorded in acoustically really dry rooms anyway, And a lot of commercial voices even have the breaths and noise in between cut out.. So there won't be any "room" there either.
@@jazzdirt Yeah. But it does not do any reverb cancellation. if it did. I'd 110% concede this point. but it doesn't and reverb + reverb does not = new reverb. OR my life would be a lot easier some days.
@@twobob If you clean up the base track first, like do a manual noisegate thing (just bluntly cut out every space between the words .. mind the s's and t's), you mostly get away with it tho.. There will still be a smidge of old room on top of the actual voice but you really don't perceive that anymore
@@jazzdirt yeah . I totally agree. to be honest I have ACTUAL tools that can just remove the verb easily - there are plenty - and then you could do a slight "room" pass (subtly) over the final to provide a touch of reality. Not a problem one IOTA. however this does not do that. Heck, I am very happy to provide the details of some "tail stripping" algos even to fixup the post. They could even mix it through the sox library and get that done with a bit of thought. But right now. OOTB. It is not good enough to fool a musician.
i guess the best way would be to do a spectral analysis of an acual recording and the one generated by the ai to see what it is doing in the harmonies to generate such a close result. there has to be artifacts of some sort
I’m a fiction writer, so this seems like it will be a good tool for recording audiobooks and editing them. Re-recording sentences and importing them never really works out because there’s always different background sound so I’d think this tool would be incredibly useful for helping even out those mess-ups so I don’t have to reread the entire paragraph.
Rain, have you found any program you like for this purpose?
This is fantastic for independent animators. Voice actors are expensive and to know that you can create a wide range of characters for next to nothing is awesome!
AI generated animations are awesome for independent voice over artists! Animators are expensive and to know that you can create a wide range of animations for next to nothing is awesome!
@Mark's Voice I think I love you. People don't realise how hard voice work can be, physically, mentally and technically. The equipment is expensive and we have to pay the bills somehow. You get to hoping other creative people would support us and our right to be paid fairly, but I guess not.
Wow. This thread escalated quickly.
@@JohannPascual so why don't they use the real people over on casting call club website? There's a bunch of really talented people over there who mostly don't charge? It would be a symbiotic relationship. It helps give starting out Voice Actors practice and a portfolio, whereas the animators get the work for free. Why do we have to take the humans out of the equation completely?
@@NickDrawzComix Google Casting Call Club. Loads of young human voice actors there who will voice your stuff for practice (no charge)
You can clearly tell when it transitions to overdub when you're going from an actual recording to overdub and back, but DAAAAMN that is a good emulation! This is gonna be crazy believable in another few years.
Don sounds exactly like the Epic Voice Guy from Honest Trailers.
that guy is trying hard (and fails) to sound like the classic guy Don is actually named after
I’m positive it is. Honest Trailers guy is doing a Don DelaFonte impression.
Now we don't need to ask him to say things in his epic voice lol.
This would be amazing for people with disabilities or who have communication challenges.
Somewhere out there is a deep fake of Stephen Hawking.
best idea
Yes, but that's been possible for many years. The quality back in the '80s wasn't great, but it was good enough. More recently, the technology has been good enough that there's not much point in further improvements as you really don't want an AI voice to be confused with the real thing in situations like that.
What if they're mute?
there are glasses with realtime subtitles nowadays :)
All this technology is getting scary. You could be framed all kinds of ways. Better make sure your alibi is airtight
If they can use this tech to frame you, then they can easily turn your alibi into your accomplice.
@@anonanon7278 true. Gotta make sure your alibi has an alibi smh
or maybe you are more protected if you use it... you could claim that someone hacked into your descript account
There is ai to counter ai generated voices already.
This completely changes the training world. It baffles me that I could record a something for an eLearning and then make adjustments as things change! Thanks for sharing!
It's crazy how there's all these crazy things that some psycho could literally use to frame people.
It's incredible. I was working on a short film and we needed to make some corrections to some of the actor's work, and Overdub did a great job for us. Pat, I love how you did your demo too.
How did you use that actor's voice without verification
Hey, I think “Don” is actually Jon Bailey A.K.A. Epic Voice Guy, who’s done a slew of Honest Trailers! We’re acquainted. Cool guy, with an intriguing backstory.
Yea it's mostly likely his voice
Stolen no doubt, let's be _honest_
@@professord8888 then how can I steal Morgan Freeman s voice? 🤔😂
@@roxayso just put your microphone to your speaker that playing video of morgan freeman. lol
@@FerlianSatria lol yea but according to this video you have to make Morgan Freeman s voice read that text , which is not possible to do
This is extremely dangerous. As I learned in my lifetime, every single really awesome thing or technique is finally ALWAYS used in the worst manner possible.
BTW... because you read the text about the pinguines..... Here is something really awesome done by nature: these pinguines staying there in the coldest times of the year, guarding and nesting their egg, are the males only. While the females head to the equator to gain weight and grow strong, the males stay with the egg. Hereby they stand very closely in a circle and every about 15 minutes, the males from the center move to the outside circle. This is how they keep each other and the eggs warm, while suffering great weight loss. Awesome fathers, these guys. ;-)
Where I think this will be really useful in the future is with foreign video dubbing. Instead of having a possibly bad dubbing, an AI could do it with the actors original voice. Couple that with a deep fake for the mouth, and you have better conversions.
Smack dab in the middle. This is incredibly useful, but it’s scary to think that this, without regulation, could get really scary. But, as a creator, this is super, super cool!
For everyone out there who just started with YT, wish you all the best and may we all be successful!!
Is it only for English, or it works with other languages, that have their own scripts/letters...dying to find one.thanks
This is great, but I'm currently in a whole, "I'm sick of software companies just doing subscriptions now so I can pay thousands of dollars over time for software that should cost $150 once" phase. Maybe another time.
Yeah eff them for that. I've done tens of thousands of dollars worth of design work with CS5. I'm never upgrading.
True. But in this case, it could be that it takes 20 high-end computers to process the data and build the waveforms in the timeframes that are being demonstrated.
I wonder if there's a way I can pirate it? 🤔⛵
@@brokenrobot2004 lol
It's getting pretty bad. I decided to cancel 2 or 3 subscriptions so I could pay for descript. Someone needs to make an all in one swiss army knife subscription software... hmm
I think it is neat to use in the ways you suggest as I am getting ready to start a new RUclips channel. But, as a private detective, I could see "recorded" statements of witnesses being manipulated by investigators with an agenda, or more likely, with clients who have an agenda. In those situations, a single word might be all that is necessary to change, just to make a an affirmative answer to a question be positive, or vice versa. It now has me thinking about the forensic tools it would take to detect this.
Isn't that voice of the honest trailer guy ??! I freaking love it.
I always wanted his voice and this software does it.
OMG YES!! Descript is 100% one of THE Best tools when not only creating video but editing it as well.
PLUS anyone on your team can learn how to edit (without video editing experience) it also saves a ton of time compared to traditional video editing software.
All you need to do is edit the actual transcript it creates, and it'll cut it from your video as well all in one swoop. (and overdub mistakes)
@Pat Flynn does a great tutorial on this if you want to dive in and haven't used Descript yet. shows you a lot of ways you can use the tool.
This video literally just cut out the most time consuming part of my workflow! I use voice to text to pre-edit recordings for content to begin with THEN go over the audio and do the actual audio editing manually. This just skipped that whole second part of my workflow!
Plot twist: This whole video is just him lip syncing to overdub
This is getting closer to being able to import an audio file of any voice and being able to recreate it perfectly, imagine how good tts things would be with fictional characters or famous people
This video has been in my recommended for like 2 months WTF
What's up Dj Cook cleaning the internet
To Dj cook I'm your first like
I have never seen an "8mo old verified popular youtuber that I watch" with barely any likes before. That is so weird
lol
I run a VoiceOver business with my wife and we've had a few cases of people using Descript to recreate her voice for their own use. Like everything it will be exploited because it'll end up on the wrong hands. Luckily I think it's not quite there in terms of fully replacing the human voice... but it's not far away :(
It's not
How can you convert audio to text accurately ?
I'm smack in the middle, like with most things. In the right hands this is an amazing tool, for example for people who lost their voice to throat cancer or other diseases and who could speak with a real human voice again. But of course in the wrong hands this is a tool that can be used for fraud or other nefarious reasons.
I like to think that means we're on both ends at the same time, not in the middle.
I am also in the middle. I love this tech, even for good memes, but their must be a special randomized frequency that plays at say 30,000 Hz (not heard by humans, only by computers) over the voice that identifies the sound file as an AI production, and not a real human recording
@@thatguyalex2835 well thats easy to edit out.
@@mqegg Yeah, that is the problem. :) This tech should be highly regulated
One day we'll be able to make our own text-to-speech voice, and use it for everything we want. Probably even add it to our own virtual avatars/personas, for VR, etc.
Finally, Ren × Ryuji fans can hear Ren confess "His love" to Ryuji.
So that will be speech-to-speech? Like, the AI recognises what you're saying, and before that you choose voice you will talk with
I believe that its utility doesn't quite outweigh its potentially dangerous uses. That being said, purely from a technological point of view this is amazing and I'm going to take a look at it.
I can see this as a cool tool if you're reading something and want to bring different characters in to read certain parts. Thanks for showing this.
Awesome tool. I've installed voicemail systems for many years for small businesses. I had to record all their menus and options in my own voice because no one in the office would want to use their own voice ...or take the time to do it.
Making edits was also a pain because every menu would need to be completely re-recorded just to make a tiny change.
This tool would be great.
This is how Skynet got the database for the terminators! LOL
Super Meta Moment: Watching this video come up when I loaded Descript to edit my course videos...
And this could be next level for replacing those little flubs I sometimes make...
This is pretty awesome. I've been wanting to do my own RUclips channel but I actually have a nervous stammer when I'm doing voice overs or camera work but this will work great for my voice over Speed Art
I love the fact you demonstrated the overdub with quite significant modulations in your voice, rather than the old days of dragon naturally speaking where you had to speak in a monotonous dull tone. Love the demo
It can be rather scary and amazing at the same time. All I know after this we can't like believe everything we saw on the internet, like fully believe every words or video we hear cause everything has a possibilities of being altered by this kind of software.
Just imagine all the people's lives they could ruin with this tool.
Like Photoshop?
@@ThadMiller1 yeah, but photoshop it can't replicate a whole video. This could be used to act like someone confessed to something they didn't, or say something that could cancel them. I still think this tool is very cool and helpful but it's important that we can distinguish it from a real person.
yea you can creat fault statement of someone...like they own you million dollar or something.
It would cast doubt on audio evidence so that kind of evidence would be less useful in court.
@@sonicj.shadow5072 Not necessarily. You can see if something is edited or not.
This looks like an amazing technology with bright future ahead. The only thing required is to embed the identity of the speaker to the file, so it is clear it was you that either said that words or you gave consent to create this digitally. Obviously the best solution would be to do that through the blockchain where hash of the file would be stored and linked to your DID (digital identity).
No?? Then you'd have to have the entire blockchain to verify anything. Just signing it with a private key would work better because then you just need the person's public key to verify the signature
That Don voice sounds JUST like the honest trailers guy.
That's what I came down here to comment
I have throat cancer and may lose my voice. This will enable me to continue to talk, and teach. Thank you for this video.
This could be useful for me as a teacher remote learning. I could just type out my talks and have this read it in my own voice. I wonder if the students would notice the difference between me and overdubbed me?
Those who have speech issues, this is amazing.
However, for criminals it’s a gift 🎁
This sounds scary, exciting and amazing at the same time. Also, "Don" sounds like RUclipsr voice actor Jon Bailey. Might try this. Also it reminds me of the app Plotagon a bit. Except the voices sound real.
I believe it's a great tool.
Quite some time back, I was lamenting on a particular public figure who had passed away. There was a project to create a documentary of this person's life. I thought it would be a great idea, if we could get this person ( the voice specifically) to speak out certain parts of the documentary.
Well looks like the possibility of that idea is now possible.
Good & interesting ... I'm glad I watched this video.
Don's voice in the end is of Jon Bailey (aka Epic Voice Guy) who narrates Honest Trailers in Screen Junkies channel, for those wondering.
It's both as all the things in the world: It can be used for good ( voice impaired people who can have a pc speaking with their own voice ) , or for bad ( making people say something they shouldn't / wouldn't ).
Don is short for Don LaFontaine, the "in a world" voice over actor in 80s and 90s movie trailers.
Just realized that “Don” voice was based on Don LaFontaine, the famous voice actor known from recording movie trailers.
Right! From Honest Trailers!
This is amazing stuff. I have never heard of this before. I can see how this is going to help me in my video creation. All I can say is WOW!
We use Descript Overdub (Paid) on our channel. Such a great tool❤️
Sounds really good. Hope this can help podcasters like us or even audiobook talent (imagine licensing their voice at scale and get paid for being the voice in 100 audiobooks per day) when it can do long-form audio very well (consistent on per chapter basis at minimum). This is a good example of how tools like this can synthesize our voice as part of synthetic media now available to use today. #syntheticmedia
"In a world..."
-Don
😂
simply dangerous, if I use that tool, I personally I just want that Don or whoever in that list to voice my script, but never want to submit my own voice, and yes I figure out several bad ways to use this tool, I keep it for myself due to fear that it might actually inspire people to do it...but I think you yourself more or less know what they are
This could be the replacement for the standard Alexa voice.
Google and Amazon servers would crash if Jon Bailey becomes the default AI voice
How about a voice overdub that can sing? I’m a musician and if Don can sing I would love to write one song for him and play along😁
This is honestly perfect for ai dungeon. If you don't know what that is look it up and you will quickly understand why something like this would be a game changer.
seems to me like the tool all the "true animated story" channels use
I can imagine to let the AI learn my mom voice so when her gone I can still listen to her.
That's actually an incredible idea
This could be helpful to make a separate audio track for another languages.
Software is useful for people making 3D movies or games. Without a voice actor available. And also creating music without an actual vocalist. I'm also developing a software that can translate or mask any language in a movie and translate it into english with the real voice of the actor. Retains original voice and pitch or modulation but in different language.
Wow, wow, wow! I am so delighted. This is certainly a life saver for me resolving a serious issue for me regarding video creation. Thank you so very much.
Hold up! so the movie trailer voice from honest trailers is an computer!?!
in the near future, we might need voice id , voiceprint or something like that
This is an amazing, incredible and revolutionary tool to use for crazy, dangerous and scary stuff !!!
It can't replicate emphasis and other ways that humans will speak. There's multiple ways you can phrase the same sentence, and this is what adds emotion to speech. Humans arent monotonous when communicating.
This isn't surprising because I'm on the spectrum, and growing up it was very difficult to determine the meaning behind what people were saying. This is because like an A.I. I would interpret everything in a literal, straightforward sense.
Modern A.I. isn't capable of distinguishing these nuances, and despite capturing your voice, it will need direct input on HOW to use it.
There’s small difference when listen on earphones, like new txt is more stereo than default mono
This program has some huge potential, but I can hear it getting confused about what is actually your voice, and what are the reflections in the room that the microphone is picking up. Plus, it may be an AC on or something, but the high noise floor may also aid to this. A few things can be done to help this - 1) Move the microphone closer to your mouth, 2) Eliminate as much background noise as possible, and 3) Treat your room to discourage as many acoustic nuances and reflections. I can actually see this program doing quite well when you train it in the right environment. It's pretty cool, in my opinion, but in the wrong hands, can quickly become an asset for malicious activity.
Amazing. Pair this with a no face RUclips channel and you're 🔥
great idea! 🤔🤑
I saw this when you shared descript a few days ago. Do not like this feature at all, dangerous territory...If this system is hackable, and I believe every system is, can't defend myself if horrible things were ever said in my own voice...Also gives me that Terminator vibe! Lol
At first I expected you to have a different voice, then you spoke and it matched the AI and damn..
This is a game changer for prank calls.
Finally, i can just feed this Beyonce interviews and get 'her' to say she loves me back.
This is why I refuse to let my bank use my voice as a password or other stuff as my face.
From amazing to scary spectrum with the scale of 1 to 5, I am at 2. I am mostly amazed, but I am also concerned of the dangerous potential as people trying to steal others' voices without getting their consents. For me at the moment, I would use this tool to preserve my voice as a young adult, so that I can hear and emulate what I sounded like in the past.
You don’t need this software to preserve your voice, any audio recording tool can do that.
How would you be able to steal other peoples voices
@averageinternetuser you need to record a voice id of that persons voice
@@RemSenS912 Finding the voice on any youtube video will work buddy..
@@ajitkhad right but you need to record a voice id using that persons voice. The voice id is a script that you have to read proving you are the owner of that voice. They then authenticate and review it to see if the voice id matches the RUclips clips or audio files
hey, now I can fake myself reading the dictionary.
This is VERY cool, I'm going to look into this some more, might be useful for my application also.
As someone trying to be a voice actor this upsets me more than it impresses me.
Unreal! There goes fivers movie trailer voices.