Freakishly Good AI Voice Cloning is Now Open & Free...

OpenVoice, the revolutionary open-source voice cloning app by MyShell AI. In this video, we'll explore how OpenVoice is changing the game with its accurate tone color cloning, allowing users to generate speech in multiple languages and accents. We'll demonstrate its flexible voice style control, showing you how to manipulate voice styles, rhythm, and intonation for personalized results.

▼ Link(s) From Today’s Video:

-------------------------------------------------

▼ Extra Links of Interest:

-------------------------------------------------

Thanks for watching Matt Video Productions! I make all sorts of videos here on Youtube! Technology, Tutorials, and Reviews! Enjoy Your stay here, and subscribe!

All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.

-------------------------------------------------

[MattVidPro]

*IMPORTANT NOTE PLS READ* The model on google colab is only using half performance due to restrictions of the free google colab. A Local install on a more powerful GPU should produce better results!!!!

[officialfanofrichiebricker]

Dont ya love it when your told to go to a website and click a link thats not there

[thomasj]

To be honest man, I appreciate that you struggle to get it working correctly. I think your struggle with trying to get this stuff sounding usable and your passion to keep trying anyway, is representative of a lot of people like myself who are just coming to youtube to try to get something working. There's way too many AI youtubers (with the clickbaitiest titles) who tend to get away with glossing over just how hard it is to actually replicate some of the results we're seeing, both here on youtube, and on the github pages themselves.

[Rangsk]

I hope all these sound/music/voice generators in the future are able to use better sampling rates and audio quality. Right now they're all practically unusable in professional contexts because they sound like they've been compressed through a Discord call or something.

[christopherwilms]

I got it working locally on my mac; quality and speed seem very similar to your examples: cool, but kinda robotic; Great video!

[davidedemurodominijanni]

When we talk about voice based AI a lot of the talk around the subject seems to focus on cloning other people's voice, with all the consequences of the case, but for me it's all about cloning our own and being able to apply it in every creative direction we need and we want. As an artist and as a fresh Indie-solo Game Developer I personally feel I'm gonna be finally able to create new content I couldn't imagine back in a few years ago... from creating speeches I wouldn't be able to perform on my own on a multilanguage platform to the most basic use in creating NPCs' dialogues for NPCs and quests in my own games rather than modding other games like I did with Skyrim and Fallout 4 for just personal use. I believe copying and cloning and using other people's voice is the most lame use we can do of this technology. I agree with you Matt about the fact all this should be opensource and available to everyone, for many different reasons and for one in particular... if these technologies were Pay to Play kinda tools like ChatGPT and others of that level a lot of people would be cut off from the advantages whoever could afford those costs would have, creating social and financial division, something we all should talk about in more depth, more than from any other ethics' point of view.

[ILIKECRYO]

Important to note, that it is "Source Available" and not "Open Source" (As per their License, one can not use it commercially).

[morleyjade]

Your videos are becoming misleading. Can't you get softwares that really works & installed locally?

[setop]

Really interesting, I compared it locally to CoquiTTS and it seems that it's way better for some voices, and way worse for others. On average it's on par with it but in a very complementary way. I suppose the way it works is they start from a reference voice and modify it to reduce the difference gap between it and the input so, if their reference voice is already pretty close it works wonder, but the opposite is also true.

[AnthonyGoodley]

One must keep in mind that for the most part all these major advances in different AI technologies just began in the last year.

These are still very, very early days. Just imagine what's yet to come.

I do realize that there have been decades of prior research and advancements etc. But things didn't really start to take off until early on in 2023.

[UnderOneSky]

we always enjoy not only how much you dive into, but also your passion and excitement. Thanks for doing what you do! let the cloning begin, where our avatars talk to your avatars. :) Let's keep it open-source!

[rgsiiiya]

the audio IS impressive!
Could you do an "how to install locally" video ?

[Shigawire]

Cloning voices is one of those AI things that I am more concerned than excited about. But it is very cool!

[icosiel]

Meh, some day, but not this one. Popped in my voice (UK) and it sounds like a generic American AI voice. Maybe need to try longer samples.

It's free, so yey!. Looking forward to seeing them make more progress, would be interested in seeing updates. Would be nice to merge 2 audio voices for interesting accents and so on.

[cbuchner]

Maybe their demo voices are part of the training set, so cloning these works perfectly. But the model might not generalize well.

[quickcinemarecap]

00:02 Open Voice offers versatile instant voice cloning.
02:46 AI voice cloning now open & free
05:04 AI voice cloning captures emotions and realism
07:07 AI voice cloning technology is now freakishly good and free.
09:00 AI voice cloning with diverse accents is impressive
11:01 Free AI voice cloning with multiple language support.
13:26 Open Voice offers impressive features for speech cloning.
15:17 Voice cloning can be challenging for certain types of voices
17:18 AI voice cloning is not as perfect as demonstrated
18:56 Open-source AI voice cloning with potential drawbacks
20:37 Voice cloning is versatile and has both positive and negative implications

[Rollthered]

Hoping this can do voice to voice conversion too! This will open up a HUGE usecase for making my own cartoons on my own.

[MaJetiGizzle]

14:09 You know, part of me wasn’t expecting to see an Andrew Ng reference in this video. But honestly, in hindsight, I’m surprised that there aren’t more references to Andrew Ng in these videos.

So yeah, another great video, Matt!

[chariotsx]

I don’t want to clone voices. I just want to create unique & emotional voices with AI that I can use for characters in a movie I’m making with the help of AI.

[MB-ncdv]

It would be great if there were tools to create entirely unique voices. Or at least start with a cloned voice and turn some knobs to adjust it. Sometimes you just want a voice that sounds a certain way and it would be nice to skip all the ethical issues of cloning someone's voice without their permission.