I almost included this in the "Ghost Town" thread but then thought it might deserve a separate treatment.

This is what I asked my AI assistant:

Q. Do your best to predict the future based on existing trends. Where will music creation software be in 5 years?


A. Predicting the future of music creation software is both exciting and speculative. However, based on existing trends and technological advancements, here are some potential directions for music software in the next 5 years:

1. AI-Driven Composition and Arrangement:
a. Sophisticated AI Composers: We’ll likely see AI composers evolve further, generating intricate melodies, harmonies, and arrangements. These tools will assist musicians in creating original content more efficiently.
b. Customizable AI Styles: Musicians might have AI tools that adapt to their unique style preferences. Imagine an AI composer that can mimic the sound of your favorite artists or blend genres seamlessly.

2. Real-Time Collaboration and Remote Jamming:
a. Virtual Jam Sessions: Music software could facilitate real-time collaboration across distances. Musicians from different parts of the world might jam together virtually, sharing ideas and creating music in real time.
b. Latency Reduction: Improvements in network infrastructure will reduce latency, making remote collaboration smoother and more natural.

3. Immersive and Interactive Experiences:
a. Spatial Audio and VR/AR Integration: Music software might incorporate spatial audio techniques, enhancing the immersive experience for listeners. Virtual reality (VR) and augmented reality (AR) could allow musicians to perform in virtual venues or create interactive music experiences.
b. Haptic Feedback: Imagine feeling the vibrations of a bassline through haptic feedback devices while composing or performing.

4. Personalized Sound Design and Effects:
a. AI-Enhanced Sound Design: Musicians will have AI tools that analyze their preferences and create custom sounds, presets, and effects. These personalized elements will enhance creativity and uniqueness.
b. Dynamic Effects: Real-time effects processing will adapt to the music’s context. Imagine an AI-driven guitar pedal that adjusts its parameters based on your playing style.

5. Blockchain and Decentralization:
a. Decentralized Music Platforms: Blockchain technology could revolutionize music distribution, ensuring fair compensation for artists and transparent royalty tracking. Decentralized platforms might empower independent musicians and reduce reliance on major labels.
b. Smart Contracts for Licensing: Smart contracts could automate licensing and royalty payments, simplifying the process for artists and creators.

6. Eco-Friendly Practices:
a. Energy-Efficient Algorithms: As environmental concerns grow, music software developers may prioritize energy-efficient algorithms. Sustainable practices will become essential in software design.

7. Accessibility and Inclusivity:
a. User-Friendly Interfaces: Music software will continue to become more accessible, catering to musicians of all skill levels. Intuitive interfaces and guided workflows will empower beginners.
b. Assistive Technologies: AI-driven tools will assist musicians with disabilities, enabling them to create and perform more effectively.

Remember, these predictions are speculative, and unforeseen breakthroughs could shape the landscape differently. The future of music software will likely be a harmonious blend of creativity, technology, and user needs!

[Even if half of this list reaches 50% maturity in 5 years we’re talking exciting! Thoughts?
And interestingly enough, I’ve floated the idea of BiaB to include item 1b on the Wishlist in the past. So me and a non-sentient, emotionless bot arrived at a common thought. Not sure if that's good or bad ]

User-friendly interfaces. That would take all the fun out of it. 😎

That’s the most “coulds” and “mights” I’ve ever read in a short article. AI … the consummate bet hedger. OK there was an occasional “will.” 😀

Bud

You're right Bud, a lot of "coulds". But think about it. Do you reallly want to see "With 100% confidence in 5 yrs . . ." or "It's an absolute certainy that so and so will happen" ? How credible would that be?

AI may be good but it ain't that good; hence the "coulds" and "mights".

That said, 6 out of the 7 predictions look plausible to me and business leaders in this sector might do well to ponder them. I know nothing about #5 (blockchain) and don't want to know anything about it

In any event, exciting is already here and will sure to increase with time.

[img][/img]

Biab is already years ahead of other software of what it can do with real audio of real session players that are real people, DI (divinely inspired).

Agreed. Actually I’m quite happy with the equivocal outlook until some sound reassurances surface regarding the many issues AI’s emergence has raised. I hope approaches will be like PG Music’s i.e, use it to augment not replace a service.

Bud

So far only a non-human has offered any predictions. Let me be the first to change that.

In 5 yrs, I think it’s quite plausible for

1. The “stem separation problem” to be solved for all but the most discerning/exacting musicians. AI should be able to separate the 2 stems in piano pieces for 4 hands. It’s just a matter of sufficient training data.

2. BiaB’s overall feel and capability will be noticeably improved.

3. BiaB will face formidable competition in its business space but will maintain it’s place at the top.

4. Affordable AI delivered music instruction will begin to threaten music instructors up and down the educational ladder and it will sense where the student needs to focus. The current annual cost (without financial aid) at the the University of Chicago will set you back more than $80,000. AI augmented music programs will significantly slash this cost.

5. AI-enhanced hearing aids will allow musicians and others to make adjustments in real-time. “Alexa, I can barely hear the upper register of the string section, fix it without altering anything else.”

6. AI-enhanced DAWS will do a surprisingly good job at mixing multi-track songs with little or no human input. This technology will also creep into the mixing engineer’s toolbox at live music events.

7. Music creation software will be able to build near radio-ready, high quality complete songs (including vocals) across a variety of genres from simple text prompts. The general public will be none the wiser, nor care about the origin of such music.

256 bars available! maybe even 257! VST3.5

Steve, I will add a number 8 to your list:
8-AI enhanced effects. That has started now but I can envision great strikes in that area, things like realistic reverb, true echos, and/or add the effects chain that Eric Clapton used in Layla.

Rob and Mario, thanks for contributing your ideas.
It should be fun to look back in 5 short years and see how well our predictions stood up.

Anybody else have thoughts on how music creation software will change?
It's easy to predict, just extrapolate a trend that you have observed.

I predict BIAB 2029 will have 49 new features and lots of nice RealTracks. And I predict those of us who haven't croaked yet will still be wishlisting and complaining about stuff like 255 limit, VST support, etc. I predict musocity will have changed their username a couple of times and still be at the forefront of cool new ideas for BIAB.

Music that you want to hear "now". Live analysis of biometrics / mood state > interpreted into music or combination of sounds synthesized & personalized based on that data, specifically for dear you. Meaning, a person would be a composer, conductor and performer(s) in real time with highly skilled orchestra at their disposal, that has no limit understanding music, no matter how bizarre, complex or abstract it might be (Chicken dance castrati opera in one of extinct languages). Phone app...

As far as "traditional" music recording / composing goes, it will just amplify current idea. Your DAW as recording station hub and various VSTs as creative engines for different task as Composition, Sound(+robo vocals) and FX... With or without use of AI. DAWs will start transitioning to "online" place. More enforced subscriptions.

BIAB- re-written. Perhaps a single product instead of BIAB, RB and Plugin. Leaving / polishing best ideas, killing redundancy, focusing mainly on workflow. MTP Library at it's heart. Live arranger function.

New way quicker generation for the BB Plugin, brand new simplified backend added, this will be a game changer:

Sadly some of us might not still be here in 5 yrs as you point out, if so, hopefully the music, knowledge and contributions will live on.
But 49 new features sounds good.

Wow! This is some forward thinking predictions indeed; especially the biometrics/mood state stuff.
I hope DAWs don't move online, I like my local copy just fine; but we'll see.

Can you clarify what "brand new simplified backend" might look like?

And I had never seen that Ver 1.03 screenshot before.
Would be a great display item for the The Grand Curiosity Museum Of All Things Band In A Box

I think Peter Gannon will sell the company and BIAB will be subsumed into some other thing in 3-7 years.

I think music 'creation' software will be in a van down by the river in 5 years .. much like mrgeeze
Keep those external hard drives around, they may become very valuable. <grin>

Music 'recording/producing' software will continue down the charted path

In the same way that programs like SynthesizerV have replaced concatenative synthesis with AI to generate vocals, BiaB will hopefully offer the option to generate AI tracks trained on RealTracks. Based on what I've seen, this is something that is available with today's technology, not five years out.

AI can be trained using existing tracks on two elements:

• Learning the note choices an artist makes over chord changes, and
• Learning how an artist converts notes to audio performances.

Instead of supplying RealTracks as audio played over a given chord progression, RealTracks will become neural networks that can:

• Convert chord progressions into MIDI notes based on an artist's style, and
• Convert MIDI notes into audio, based on an artist's performance

This will allow BiaB to do many things that currently can't be done:

• Training will include performances in all keys. A riff that might have only been available in D would now be available in all keys.
• AI can interpolate new riffs using notes that didn't exist in the recorded performances.
• Note choices by one artist can combined with audio performances by another.
• Users will be able to edit pitch and duration notes directly (like MIDI) and get RealTrack quality audio.

I've pretty much given up on my own vocal synthesis program, because cheap AI vocal synthesis is about to become ubiquitous. It's been a fun journey, but there seems little point in continuing down that path.

I think that BiaB is in an interesting position. They've currently got boatloads of high-quality audio on which to train AI with, assuming the contract allows it. The main problem with AI synthesis is speed - it can take a long time to generate tracks! I suspect that GPUs will soon make that a non-issue for most people.

Plus, AI tracks could be optional. That is, the standard fast method could still be used to generate audio by default. Users could then choose tracks or portions of tracks where they would want to work with using AI.

What current music AI programs don't give people is a level of control, so the appeal is primarily to people who want AI to do all the work. I suspect the audience for that - once the shiny, new aspect has worn out - is smaller than the companies are betting on. Social media will be flooded by sound-alike AI songs, and people will turn to trusted sources to provide curated music.

In contrast, BiaB appeals to people who want that level of control. AI will allow people to have control of elements that had been immutable, unless they used time-stretching and pitch correction software.

Interesting.
If Peter does decide this I hope a suitable buyer or grantee is found to continue building upon this great program far into the future. This must be a labor of love for him, it would be for me.

When the time is right, maybe an existing employee will take the helm; Callie or Andrew??

Hey "Moneybags Mario" . . . how deep are your pockets?

No wheres near deep enough

This is the new backend that will speed things up:

Several good predictions and very well articulated.
2029 will be here soon.

You never know.
If the opportunity ever arises I think you'd do a good job at the helm; not quite as good as Peter, but still plenty good.

I think there's some irony of asking an AI assistant about the future.

After all, ChatGPT is little more than a program that predicts what word is likely to come next, trained on what people on the Internet have written.

It's a bit like asking someone to write a paper, and they use the first 10 results from Google as their research.