This Audio Editing Tool “Deep Faked” My Voice 👀 (Actually Useful or SCARY?)

81 thoughts on “This Audio Editing Tool “Deep Faked” My Voice 👀 (Actually Useful or SCARY?)”

1. I need that scary tool 🙂

   1. Definitely cool. Most definitely scary.

   2. Won’t bother me none.

   3. $30 a month.

   4. For what🤣

   5. 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..

2. Totally amazing. I only have a Youtube channel but this is making me want to do a podcast. The editing and overdub options are total game changers.

   1. @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

   2. @@fabrizio_sant lmao

   3. @@fabrizio_sant LOL

   4. I don’t know if this is satire or if you’re young

   5. @@Socvinc yea idk either
      “Im an fbi agent”

3. I’m almost 99% sure that the Don voice is Epic voice guy from the Honest Trailers videos!

   1. 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.

   2. I’m 99.9999999999999999999999% sure that’s definitely, possibly, the Honest Trailer voice.

   3. Yeah that’s his voice alright I’ve listened to him for hours on end, I was doing to make the same comment

   4. was about to comment the same thing lol

   5. Made the same comment, but saw this one, and deleted mine.

4. Dangerously useful. 😆

   1. tru I can make a sus audio of my friend

   2. Usefully dangerous

   3. @@i2i3i2ihs yo I don’t think that’s a good idea 😂

   4. Yeah

   5. If processing speed increases it can even be used as a next generation voice changer.

5. Daaang, crazy powerful tools!

   1. Ok

   2. Ye

6. 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.

   1. You could, however, clean those up in your base track beforehand.

   2. 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.

   3. It already exists. It’s called iZotope Dialogue Match.

   4. The overdub sounded like NileGreen to me.

   5. @@micahtouchet あっぷ

7. Deepfakes are about to reach a whole new level.

   1. Now you can FAKE the voices easily too

   2. Command voice activated

   3. @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.

   4. Deepfake already made us into cakes

   5. One day this start THE WORLD WAR.

8. This could be massively useful for generating spoken dialog in RPG games, instead of having to read every word.

   1. Yeah! Soon enough games can just generate random voices of non-existing people, which will make the development much cheaper and faster!

   2. wow never thought of this, Nvidia has made ai facial animations as well.

   3. YES. Crpgs can finally have dub with a small budget

   4. 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.

   5. This… this alone has pushed me over to the “I need this” realm

9. 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.

10. Yup there comes a lot of memes of ancient famous people “predicting” the future

    1. SUP ZACHHHH!

    2. Yooo

    3. “There will be a virus that kills many people in the 2020s. Hee hee” -Michael Jackson, 1997.

    4. @@CaseCat Well, “many” is a bit overshoot ^^

    5. @@surronzak8154 well, there’s like atleast 16, 16 is a lot for me.

11. 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.

    1. 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

    2. Nice Idea bro

    3. @@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

    4. 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.

    5. @@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)

12. 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.

    1. 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.

    2. @@michaelcaplin8969 Can you tell me what is the name of this program and who can download it

    3. 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

13. Everyone should be absolutely terrified at the implications of this.

    1. We all are, but at the same time we also can’t help but be curious

14. I wish I had enough of my mom’s voice recorded so I could hear her with this again since she past

    1. I’m sorry. I hope she rests in peace.

    2. Bro💀

    3. yes😭

    4. Wow

    5. Aww. Man, the people in the comment section are thinking up all kinds of wonderful ideas to use this tech.

15. 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.

16. 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.

17. 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

    1. Emvoice Pro

    2. 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).

    3. That would be so cool

    4. A liquid Drum and Bass album using the voices of Frank Sinatra and Nat King Cole. That would be wild, Endless possibilities.

    5. From what I read recently, over 100 songs on the music charts currently are AI. It’s here.

18. 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!

19. Isn’t that voice of the honest trailer guy ??! I freaking love it.
    I always wanted his voice and this software does it.

20. It sounds pretty good. As a commercial editor I can see using this in the future when it gets better for corporate training videos

Comments are closed.