Відео

Look at all the others that can copy and replicate music... KITS is even bigger and easier then udio or suno and you sound perfect making even more then those lame ai... ua-cam.com/video/py0ujeZLQi8/v-deo.html this lawyer is so greedy cause she makes money on the side with her own connections with artist.

I think all the "copyrighted" music from now on is probably created in suno first then used as inspiration 😂

wow what a great video, thanks so much for sharing!

Is this now a CapCut Pro feature? I've got to the Export stage in CapCut and it says 'you are using the following pro features/materials - auto captions'

Thanks so much for the video.. What would you say is the most natural und best choir vst you encountered..

They dont need to copy. The ai can simply learn from ”listening” to Spotify 24/7

As usual, Apple have come up with a great computer, but then sting people for the extras that many will need. The ram and ssd upgrades are really overpriced and to not even give you a keyboard and mouse is dreadful. Having said that, my 2015 iMac is due to be replaced as it won’t run some of the software I want to use or update macOS anymore so I’ll be getting a Mac Studio next year when I’ve saved up the cash. I do wish they had put 4 usb 3.0 ports on it. Most synths and audio interfaces use the old usb A connectors but I guess I’ll be buying a hub or dock of some kind too. Oh, and a monitor of course - doubt I can afford the Studio display😪

Thanks!

Thank you! I wish there were more suggestions for shortcuts.

What are you using for that sound. Incredible!

If you say that "users of Suno and Udio aren't making musing, they're entering prompts", then you could also argue that "the person who plays the piano isn't making music, he's pressing keys". I understand that AI is heavily disruptive to the industry of creators and distributors, and that society might want to think of a way to protect those who could be harmed severely by that. (I would support that idea a lot.) But the current arguments to sue software companies for their technological innovation seem quite ridiculous. You can easily copy a painting by taking a picture of it, but until now, it was always the responsibility of the photographer... and when trying to sell that picture, he should be held accountable if that would be a copyright infringement - nobody would think of suing Canon or Nikon or another camera manufacturer. Why is it so hard to treat the current audio creations in the same way? When a song created by one of these tools is considered a copyright infringement by a court, then the person who tries to make money from it should be the one to blame.

It´´s all about money. Major labels want money, composers are afraid of losing jobs, musicians too.. again, it´s all about money! They dont want innovation, unless that innovation dont touch their interests

You need to provide more details for blend mode in the inspector. It took me an hour and half to find it which was ridiculous.

This video seems to of ignored the fact that you can load your own music , melody, words, voice and instrument, then use Udio to create a backing track. I write my own words and melodies, and arrangements. Lots of songwriters will use It to create amazing demos of their own work, I use it like a very sophisticated DAW. I used to have to pay producers and sessions singers rather a lot of money to produce and sing my songs, I found some session singers very challenging to work with, now I can produce a great demo without the cost and drama.

I see it as Fair Use Act content. As a professional artist of over 40 years I have seen my work in AI art, countless times. In every scenario I believe enough change was made to my work to justify "fair use" under US law. The reason why I endorse AI art is because it empowers the garage inventors of the world. You can literally scribble an invention on a napkin and the AI will give you a real 3d representation of your idea. Enough to visualize and adapt to needed changes. Enough to take to an investor with a good business plan. If my art helps this cause I am 100% in favor of OpenAI and Stability AI, regardless of how they obtained their training data. Not to mention the inspiration my art can contribute to. It's an honor! I'm not a professional musician, but I would hope there are some of you out there that share my thoughts above. Imagine some mother of four stuck at home. To pass the time she is writing her own songs. Now she uploads her words to Suno and gets to hear her masterpiece in real time. This is empowering. It is in the greater good of mankind, as a whole. And for musicians and artists this is just as empowering. AI has a very real (and productive) practical use application in what we do on a daily basis. Don't just stand behind the AI wave pointing at it. Grab your surfboard!

Really helpful!

but if there are multiple instruments that are missing the samples in one bank i have to do that for all of them or is there a way refresh it for all of them?

I can't get it to work in Reason 13

These tools are a lot of fun. Cats out of the bag, jurisdictionally it is impossible to stop this train globally. You are just handicapping yourself by attacking the leaders in your jurisdiction.

I love this song, love the lyrics and the piano, but I have to wonder, upon first listen I said to myself, is this a decades old song I just had never heard before , by a much younger Billy Joel? But it was recorded with such clarity it had to have been recorded recently…which leads me to think Billy Joel laid down the basics and then the other three guys listed on the credits used AI technology to make his voice sound exactly like Billy Joel’s voice as it was 40 years ago. In the same way they merged the young Billy’s footage with the current one in the official video, it really seems like they did the same with the music-heavily synced/enhanced by AI…anyone else get this feeling?

Thank you very much!!! Solid tip!

I'm sure I've heard much better quality ai material, described as brand new material from current popular artists. I suspect the technology used may be simply swapping vocals. AI voices too close to major well known artists can only end up protected to prevent sales. And introduce big fines. Al will certainly replace artists in many fields. The lure and ability for a company not to have to spend on hiring artists is too great. Entirely fictional AI music artists are a given, I'm more skeptical about AI ever being able to create a good movie

Thank you David...your video was AWESOME and you explained it very well. I teach news related English in Korea, and this was a story we did in class yesterday. I tried my best to explain it but I shared your video with my students as your explanations are perfect and clear with some great examples! Fantastic video! Cheers! 👍👍👍

BOOM! This was a great find. You're helping me faster ways of getting captions done.

Awesome - lifesaver, thank you. I have a wedding video to edit and am using the speeches as the main narrative. I want to be able to quickly identify soundbites from this to create a backbone, and then use this as background to the visuals. I'm going to have a go at using this app for that purpose, to make an audio edit list. Hopefully this will make it a lot easier. Thanks again for the clear and no-nonsense video.

Thank you, David, for doing all that work. I was already convinced but now even more. Have been using NP since even before I started Dorico. The combo is a win for me. One question: have you tried exporting an .xml (.mxl) into ProT or Logic and then adding other tracks? Hard to line up because of the delay in NP. If you’ve made it work, would love to video how to on that! Nice job!!🎉

Well the reason why the lawsuit shouldn't really frighten anyone is the same reason why other platforms who do similar things shouldn't be worried either (or even be fearful of a similar lawsuit). For Example; Twitch implemented "Famous" voices as TTS voices for donations to streamers, trained on song artists voices, and mostly all (if not all) are trained on song data - The Weeknds voice is completely trained on one song; if you wrote down the lyrics for the song in your TTS, the song would essentially be played. Although the data is trained on these copywritten voices, anyone can get paid with the addition to these voices, adding formative content to their streams. Where is the line in this regarding copyright , and how does it relate to infringement as a whole for AI training data? well that's the whole point of the example, these things still need to be defined, and lines need to be drawn before estimations of crossing those lines can even be made. In the same way these companies are mad that these AI generations are creating things using previously existing art/ "their art" - the logic should fall under all matters of this magnitude, including but obviously not limited to that example. The problem with that, is that the very foundation of the lawsuit (This is data trained using our licensed music) Needs to first have a category to even fall under the guidelines of what is considered "wrong" of them to do, *first*, before they are even considered for doing "said wrong thing" within the confines of those guidelines. The courts need to define what they consider within the fair use-age regarding training data for AI as a whole. And THAT is a process that I don't think these companies realize just how long it is. Even if the AI companies are in the wrong, they first need to be defined within the confines of what type of copyright infringement the Music industries are claiming first. They might not even get that far. And this will take at the very least a decade to even draw the line of distinction. All in all, I believe this won't get very far. By the time they draw the lines on AI training data to even start this fully, the lines will be even further blurred.

Please stop. They emulate a group because many hours were put into generating that emulation. You are being deceptive when you infer you get that through normal usage. Every songwriter is sampling from music they have heard through a life time. Is that stealing, you are doing the exact same thing the software is doing. The only time musicians care about ai is when it could affect them. They don’t give a damn about ai being used to fire employees if it means lower prices. I have never heard more whining in my life.

Thx so much for doing this, David. Your video couldn't have come at a better time; I've been using MuseScore (MS) for years now, but have been considering trying Dorico with NPPE to play back BBCO and Berlin Orchestra. Noteperformer's crisp execution is astonishingly good...worlds better than the others to my ears. Unfortunately, in other videos I've discovered that NP's string sound on slower passages is a tad 'synth-y' to me. In my experience, in slow expressive passages MS's strings really shine, but as you noted, in up tempo work MS can be terribly sloppy...repeated notes are awful. On another note, I was surprised that the playback of NPPE with BBCSO was so inconsistent...I had high hopes for this configuration, but I'll now have to reconsider. Perhaps I'll try the demo versions. Thx again for an insightful evaluation!

It began with artworks being labelled as "content," and now the artistic process has been reduced to "generating output." Language matters. But make no mistake, these are jackals suing pirates.

Artists get inspired by listening to music. So what's the diffrence? Maybe they can take Carl Orf to court to. He took multiple music parts to create Carmina Burana. The only thing that this case is about is money and the labels beeing scared of competition. And note to the maker of the video. If you write your own lyrics, the AI will not find any comperison. But if you give in a promt with the lyrics of an existing song, you'll come close to that song. So...

Thanks!!..way better than the official tutorials. I wish youtube had suggested this one a while ago when I was learning ...how to learn Dorico

Isn’t that life in general ? We copy of existing material and transform it into something new Like chopping up an existing sample n flip it into a new record.

I see that concept of "We want to make it possible for everyone to make music" to be one of the fundamentally flawed ideas behind this. Why should *everyone* be able to make music? Why? That would remove all the magic from it. Making music is a gift, a special talent, and not everyone can do it. Some things, like the arts, should stay in the realm of talents and craft that only a small segment of talented people can do. By the AI companies' logic, I guess we should also make it possible for everyone to also be... professional athletes? Brain surgeons? Astronauts? Why not let everyone become talent-deficient pretenders in every field? Why is this "make it easy-peasy even for people with no talent" stuff being reserved only for writing, art, and music? What's that you say...? You don't want your surgeon to be some faker who is having AI do all the heavy lifting? Interesting!

The regular NotePerformer, without NPPE, stands head and shoulders above the competition, it's almost laughable. In my opinion, NPPE is a significant waste of time and resources for what little it offers. MuseScore has great potential. While its notation features might be lacking, with some tweaking, Muse Sounds can achieve what NPPE aims for, and it actually sounds good. Plus, it's free. ;)

Noteperformers own payback outperforming the rest by a landslide. MuseScore, considering it is free is quite ok. But the precise articulation in NP is not achieved by any competition.

Cant wait till they figure out how to train these models on less data. Aka only public commons, or self generated and rated dated. The sooner the ai midels can sidestep the copyright/ip paradigm the better

Its NotePerformer for me too, it gets the rhythmic crispiness of MIDI while maintaining a nice orchestral timber quality. Listening to rhythmically sloppy MIDI is just rough for me

Great ideas, thanks. I'm wondering too about the best "place" to keep the libraries and instruments I buy. I feel like I want them in a directory backed up on iCloud, and I also keep a backup copy on a very large thumb drive. Your thoughts?

All music created is based on previous works essentially. As a musician I grew up studying and learning music and those influences absolutely are present in the music I create. The only issue here is Industry Rule #4080, Record Companies are shady. Embrace the tech. The best music will have human input. Prompts are no different than a producer telling session musicians what to play.

I don't think you listed out your computer specs, but IMO a lot of the glitches with NPPE performance have to do with the immense strain it puts on your computer memory. As to the dropped voices, one thing to consider is the "Support more voices" option in NPPE? For fast stuff, like the Rossini strings here, it might be critical to running BBCSO

Record companies are finally reaping what they have sown. For years, they have exploited artists, profiting immensely from their talent while giving little in return. However, the advent of new technology heralds a transformative shift that could drive these companies into bankruptcy. Their arguments against this innovation are utterly unfounded. Artists have always learned from one another, drawing inspiration from chord progressions, rhythms, and harmonies. Now, AI enhances this creative process by providing us with prompts that lead to original work. There is no fundamental difference between the ubiquitous use of the same four chord progressions in countless songs and the use of AI in music creation. I find it amusing that the record industry, after years of exploitation, is finally facing the consequences of its actions.

Would the major lables be content with a piece of the action? You're "forgetting" one crucial aspect. AI generated art (including music) can not be copyrighted!!! Why would any label be interested in something that can't be copyrighted, since they make their living soley from copyrights? That makes no sense, whatsoever!

I've spent a ton of time trying different libraries for marching arts playback. I've definitely found that quite a few libraries have more lifelike, realistic sounds than NotePerformer, but that along with the realism comes weird artifacts and inconsistencies. NotePerformer isn't quite as realistic, but also plays back more consistently than any other library I've found.

As someone who didn't have the luxury of learning music while growing up (3rd world countries didn't have things like school bands or things like that 25 years ago) I apppreciate the fact that I can record a piano melody or a multitrack sketch of what I hear in my mind and send that recording to Suno so that it helps me recreate what had been already created by my brain but I didn't have the skills and knowdledge to transfer it over to the real world, and you can do that as many times as you want in case the AI didn't come up with something similar to what you had in mind. That in itself is a miracle to me, the next step would be having a hardware piece that could "hear" what you hear in your mind and replicate that using Vsti's, I'd love to see that because sometimes you have an idea and it goes away by the time you find the right sounds/presets/kontakt libraries that sounded like the ones in your brain.

Great video man thank you!

I really loved what sounded like the clicks of the keys for the winds in the Musescore rendition of the full orchestra

I use Sibelius and NotePerformer 4 but I must admit, I was impressed with MuseScore. Perhaps because I've had a low expectation. They certainly have improved their playback. NotePerformer is still my favorite. What I can't get over is having to rewrite the strings so the double stops sound real and not like a chord. I've had this problem with violin solos. I want a real violin cord, not something that sounds like divissi a4.

Thank you for this informative video. I bought NotePerformer three years ago and have been extremely happy with it. The latest update (4.5) makes improvements to an already good version 4.4.

Very good video. Congrats! I share every feeling you show here. It happens I also copied that score and made some tests myself, some months ago. NotePerformer is the only playback engine that is reliable when it comes to proof-auditioning (as a means to find errors that proof-reading has not found). But I really dislike the strings sound. I've never understood why people are so much into BBCSO. I've bought it since day 1 or 2, but never really used it, because of its muddy sound. The hall builds up too much and there's quite a lot of work to do on the mixing level to get it satisfying. And then, there's the problem with runs or with bad levelling depending on articulations. All in all, I never use it. I find VSL synchron and HOOPUS engines to be way more workable. Actually, VSL strings are my go-to strings, and as for woodwinds, I find AcousticSamples have done such a GREAT job with the flutes, clarinets and double-reeds that they will replace anything else I have (synchron, spitfire's, hollywood orchestra…) It's quite an expensive hobby but the output is really satisfying. Next step : when Arne Wallander will provide us with different stylistic interpretations (especially jazzy styles), his tool will be perfect for us engraving people. Note: I don't own any CSS stuff nor Orchestral tool stuff, although I understand they're very good. You can't have them all!