• WANTED: Happy members who like to discuss audio and other topics related to our interest. Desire to learn and share knowledge of science required. There are many reviews of audio hardware and expert members to help answer your questions. Click here to have your audio equipment measured for free!

End Game DIY Loudspeakers

mcdn

Addicted to Fun and Learning
Forum Donor
Joined
Mar 7, 2020
Messages
559
Likes
780
In all fairness he does address room EQ with this design.
Yes there is a semi-active option, but it's only a Hypex plate amp to drive the bass separately from the mid/tweeter. The end user can then do some manual room correction if they have a suitable measurement setup. The design itself doesn't _assume_ room correction and then work forward from there. Obviously mass market design can't do this because most people aren't audio nerds. But Steinway-Lyngdorf shows that there is a market for super high end room corrected systems - they simply won't work without room correction, and cost USD100,000+.

DIY can assume room correction, multiple subs, and active speakers, work forward from there, and achieve results for say $10,000 that surpass almost anything in the commercial market.
 

Absolute

Major Contributor
Forum Donor
Joined
Feb 5, 2017
Messages
1,084
Likes
2,125
I agree with this - the performance reason to DIY is to integrate something into a room that could not be commercially sold. When I think "endgame DIY speakers" this now quite old design is what first comes to mind:

That's brilliant. It's baffling (ho-ho) how few soffit-mounted systems we see in the home-market. Have you any experience with it yourself?
 

Razorhelm

Active Member
Joined
Jan 31, 2020
Messages
160
Likes
316

sorry if this has already been mentioned but this could be a good one, my understanding is you can buy a kit

"The speaker can be purchased complete through Salk Sound for $2395 - 2595, depending on what finish you purchase. Alternatively, this speaker can be built as a kit via Meniscus Audio and you can also even purchase a “flat-pack” for the cabinet from Speaker Hardware. Fully assembled (but unfinished), the DIY route would cost you in the neighborhood of $1150 to 1450 (depending on the flat pack order) and if you decided to upgrade components from Meniscus you could do so as well."
 

tmuikku

Senior Member
Joined
May 27, 2022
Messages
301
Likes
336
Me:
How to build best loudspeaker in the world

ChatGPT:
There are a few key factors to consider when building the best loudspeaker:

  1. Materials: Using high-quality materials such as rigid, lightweight cabinets and high-end drivers will help to ensure that the speaker sounds as good as possible.
  2. Design: The design of the speaker, including the shape and size of the cabinet and the placement of the drivers, can have a big impact on the sound quality.
  3. Crossover design: The crossover is the part of the speaker that divides the audio signal into different frequency bands and sends them to the appropriate drivers. A well-designed crossover can greatly improve the sound quality of the speaker.
  4. Amplification: The amplifier used to power the speaker will also have an impact on the sound quality. Using a high-quality amplifier with a good signal-to-noise ratio and low distortion will help to ensure that the speaker sounds its best.
  5. Calibration: Properly calibrating the speaker, including setting the correct crossover points and equalizing the frequency response, can also help to improve the sound quality.
Me: What would be an end game DIY loudspeaker?

ChatGPT:
An "end game" DIY loudspeaker would likely be one that is built with the highest-quality materials and components, and is carefully designed and calibrated to deliver the best possible sound quality. This could include using premium drivers, a rigid and well-damped cabinet, and a carefully designed crossover network. It might also involve using advanced design techniques such as finite element analysis (FEA) to optimize the speaker's performance.
Building an end game DIY loudspeaker is likely to be a challenging and time-consuming project, and may require a significant investment in materials and equipment. However, for those who are passionate about music and audio, the rewards of creating a speaker that delivers exceptional sound quality can be well worth the effort.

Me: How you define sound quality?

ChatGPT:
Sound quality refers to the overall character or nature of the sound produced by an audio system or device. It can be difficult to define sound quality objectively, as it is a subjective perception that can vary from person to person. However, there are a few key factors that can contribute to good sound quality:

  1. Clarity: Good sound quality should be clear and easy to understand, with all the elements of the audio being distinct and well-defined.
  2. Dynamics: Sound quality should also be dynamic, with a wide range of volume levels and the ability to reproduce both soft and loud passages accurately.
  3. Frequency response: The frequency response of an audio system should be as flat as possible, meaning that it reproduces all frequencies within the audible range (20 Hz to 20 kHz) with equal accuracy.
  4. Distortion: Sound quality is also affected by the level of distortion present in the audio. Distortion can take many forms, including harmonic distortion, intermodulation distortion, and crossover distortion, and can create unpleasant sounds that degrade the overall quality of the audio.
  5. Spatial characteristics: The way that an audio system reproduces the spatial characteristics of the original recording, including the sense of space and the positioning of instruments and vocals, can also impact sound quality.
Me:
What is required for great clarity, dynamics, frequency response?

ChatGPT:
For great clarity, a speaker or audio system should have a wide frequency response and low distortion. This will help to ensure that all of the elements of the audio are distinct and well-defined, with no muddled or blurry sounds.

To achieve good dynamics, a speaker or audio system should be able to reproduce a wide range of volume levels with accuracy. This may require using high-quality drivers with a large excursion range and a powerful amplifier.

To achieve a flat frequency response, a speaker or audio system should be able to reproduce all frequencies within the audible range (20 Hz to 20 kHz) with equal accuracy. This may require using high-quality drivers that have a wide frequency response and a well-designed crossover network to divide the audio signal into the appropriate frequency bands.

In general, using high-quality materials and components, and carefully designing and calibrating the speaker or audio system, can help to ensure that it has great clarity, dynamics, and frequency response.

Me:
How to have good spatial charasteristics then?


ChatGPT:
There are a few key factors that can impact the spatial characteristics of an audio system:

  1. Speaker placement: The placement of the speakers relative to the listener can have a big impact on the sense of space and the positioning of instruments and vocals. In general, it is best to place the speakers at an equal distance from the listener and to aim them towards the listener's ears.
  2. Number of channels: Using a multi-channel audio setup, such as a 5.1 or 7.1 surround sound system, can help to create a more immersive listening experience with greater spatial realism.
  3. Speaker type: The type of speaker being used can also impact the spatial characteristics of the audio. For example, using a speaker with a wide dispersion pattern can help to create a more expansive soundstage.
  4. Room acoustics: The acoustics of the room where the audio system is being used can also have an impact on the spatial characteristics of the audio. A room with strong reflections or too much bass can create an unnatural sense of space.
In general, careful speaker placement, using a multi-channel audio setup, and paying attention to the acoustics of the listening space can all help to improve the spatial characteristics of an audio system.

...and so on..

Before AI is capable of giving exact steps for personalized system here is philosophy you can use to derive your own :)

How to make end game DIY speaker: Forget about commercial products, drivers, brands and makes and models for a second and think best sound you've ever heard that gave most emotional feeling, can you imagine it? Have you heard sound that is so good it almost makes you cry, somewhere sometime? If not then seek for it, you need it before you start with the end game. And then keep it in mind for the whole process, you want to maximize emotional impact. It could be a live event by the way.

Now, few more things: We perceive sound roughly on 20-20kHz bandwidth. Also, it seems that anything sounds better while turning the volume knob, the louder the system is, up until it is not comfortable to you anymore. This is the base line for end game, you need to fully reproduce the whole bandwidth with enough SPL capability on the system. Can't call it end game if the system distorts before your ears, or isn't capable of wide enough bandwidth. Very basic stuff.

Well, now you listen in a room most probably, so the speaker and room need both to be adjusted and play together. It is complex system, not just pair of speakers. Your hearing system interpreting sound in a room that was put there by the playback system including x amount of loudspeakers.

If its end game speaker we could assume sound quality, what ever that is to you, has top priority over things like aesthetics, cost and size. If you are not willing to make sacrifice on some of these prepare to make sacrifice on sound quality. Set your priorities straight on this very root level of things and base your decisions on the design process on the priority list. This means you can now comfortably make compromises during design process so that no trade-offs are on the areas important to you, like in sound quality, but in cost and size instead. Remember though, that the speakers don't necessarily end up being big or costly, its just something you don't stress about until done.

Here is the recipe for end game speaker:
make a system design that push all trade-offs to the size and cost and aesthetics in order to have no compromise on sound quality. Assume anything is possible, assume you can use ideal drivers, what ever crossover topology and so on, have no limits until done. After you are done then minimize cost by using best stuff you can afford that fit the design, if at all possible figure if size and aesthetics could be improved, like hiding some of it. Done :D

I'm not gonna go further on this as everyone can now reason further, stuff like: how I'm gonna get loud enough in the room I have, how loud should I go? What about spatial perception, can I position the speakers where I want or do they have to be on the wall or something? How wide soundstage is most natural, how about 3D? Why there is no 30Hz at listening spot even if I have these huge speakers in that should be perfectly capable of it? What make and model drivers should I buy? Wait aminute, I don't know yet what size(s) drivers do I need? and million more questions on the way to the end.

Basically, map your situation and make best out of it. Power in DIY is that you can tailor fit the system to your situation. Forget about commercial stuff, they most probably have trade-offs in audio quality for better aesthetics, for lower cost to keep making profit and for small size to keep everyone in the house happy.

Most importantly, have fun, as its supposed to be fun hobby and it certainly is!:) Don't expect end game speakers happen in a year, or even two, might take time, but its a fun journey if never getting there because you'll learn tons and probably get pretty nice sound while prototyping. I think its my fourth year now.. or fifth :D
 
Last edited:

gnarly

Addicted to Fun and Learning
Joined
Jun 15, 2021
Messages
992
Likes
1,390
So, for all the DIY experts here, what would be your recommendation for an end game DIY loudspeaker that would equal or exceed what we on ASR would consider to be the best available on the retail market?

Thanks!
Hi all and MKR,

In my experience, the idea finding of an end game speaker (whether commercial or DIY) is not realistic.
Because inevitably, if one is in the hunt for such, the realization that the room/environment matters so much to finding "end game sound", that the speakers and room become a marriage of sorts.

End game sound then becomes an exercise in starting with a room design, preferably from the ground up, and choosing appropriate speakers for it.
Given most don't have that luxury, we get the best speakers for whatever room we are working with.
So let's say you find end game speakers for whatever room you're working with.......
are you really going to be in that room forever? Not sell house, move, etc?
Or not change your idea about what end game sound is, or even what music tastes are?

My humble advice is forget the idea of end game, and whether you want to go the DIY route or the commercial route.....plan for inevitable change.

I spent the first 40 years of my adult life going the commercial route (always thinking I could find end game.)
And the last 10 years going the DIY route ( knowing I'll never find end game Lol.)

The main reason for the change in attitude about end game, has nothing to do with commercial vs DIY, however.
It came from simply downsizing homes, where the one I left had a large room designed from the ground up for optimum acoustics.
I've also learned how much better just about any speaker sounds outdoors, free of the room.

So anyway, if you love shopping for commercial speakers, auditioning at dealers, trades shows, etc...by all means do that.
If you are excited by DIY, and can visualize how you're going to actually build the speaker with shop/tools either already owned or need to acquire,....
and how you are going to measure and design xovers/EQs, again with skills/tools either already in possession or need to be acquired.....by all means do that.

Just don't expect either to get you to end game, is my best advice. :)

On the direct issue of which can be better, DIY vs commercial, my experience is DIY exceeds anything I've found commercially.
That, I'm pretty sure I've spent more on DIY than I ever would spend for commercial speakers.


Pure aside: If i were back in the commercial market, I'd only buy used. Reason: CHANGE will occur.
I'd only buy home audio gear that has a super wide following.
But prosound, I could buy unheard...if pulled pulled from a church or theatre etc. Such has a good chance of making some of the best sound out there, and near certainly be a best value. Many boxes have Ease data for modeling, although I don't know how well the modeling works for home-sized rooms.
Used prosound......"Have you music for near nothing and you can change speakers for free !" (high resell to used purchase)
 

GXAlan

Major Contributor
Forum Donor
Joined
Jan 15, 2020
Messages
3,868
Likes
5,954
A good example of a DIY endgame speaker could even be dualmuzak’s setup. Most would say that it is unreasonably complex for a company to offer it as a commercial solution but in a DIY setup, you can do all sorts of unreasonably complex things in the pursuit of audio. In his case, he is not even building speaker cabinets — just integrating multiple different vendors but it’s so complex that this is an example DIY endgame.

 

hege

Senior Member
Forum Donor
Joined
Dec 25, 2018
Messages
466
Likes
819
Location
Finland
just integrating multiple different vendors but it’s so complex that this is an example DIY endgame.
When such a system requires dozen steps for startup and shutdown procedures, it's probably gone a bit too far. :)
 

Mr. Widget

Major Contributor
Forum Donor
Joined
Oct 11, 2022
Messages
1,147
Likes
1,697
Location
SF Bay Area
When such a system requires dozen steps for startup and shutdown procedures, it's probably gone a bit too far. :)
That's what my GF says about my system. :) I have considered automating it, but that adds even more gear. :facepalm:
 

DrFG51

Member
Joined
Dec 22, 2022
Messages
11
Likes
15
I offer this "as is" - this is the process I went through to make mine.

I'd always been drawn to valve amps - my father was an engineer way back when, and I remember dinner table projects as a wee lad and being fascinated by these glowing tubes. Then I got into hifi as a teenager, and realised that valve amps were beyond the means of a paperboy :lol:
I went through various systems over the next 30 years, some really enjoyable, and simultaneously none of them were quite right. And then for the first time in ages, maybe 12-15 years ago now, I heard a valve amp running some horn drivers. And that was it - lightbulb moment - that was the sound I wanted. So already, if your goal is an ASR score, move along...!
I researched horn designs, and eventually came across the works of Geddes and Parham, and was more drawn to Parham's approach. Big drivers, very sensitive (so hopefully happy with a little valve amp), go VERY loud, and according to reports, seem generally quite room-tolerant. Scan through the range to find a design that ticks the boxes that I know about, and settled on a big midrange (15" JBL 2226), paired with a horn (B&C DE250), in a relatively simple 2 way ported box with a custom waveguide and passive crossover, and then flanked by a pair of subs. I like simple, but note already by this point you're out on a limb. You can I believe buy the speakers as complete units, but I'm 4000 miles away from him, and couldn't find anyone remotely close by who's got some to listen to. So you're about to build a set of speakers on spec, based on internet reviews of people who seem to like them, and on hoping that they'll produce the sound I want from the components they're made of.
He sends the plans for by email. I look over them, nothing too alarming, users seem generally really happy with them, and so then just decide to crack on. I hadn't been a woodworker for long then. Took about 6 weeks part-time to make them. Still not a "cheap" project - around £2500 at 2013 prices for the bits and a lot of time. I think to put them into a 'What are they worth?' context, now - probably £3000-3500 (depending on veneers/capacitors/whatever) of parts and raw materials, and 2 weeks of a full-time professional woodworker's hourly rate. Call it £6500-£7000 ticket price. I've had them 10 years, have heard speakers many times more expensive than that, and have not once thought about changing them. That's the honest answer.

Lessons:
1. The average lifespan of a human is about 4000 weeks, and I'm *well* into the second half! Better to build *something* imperfect (IMO) than never build the perfect ones. At the very least you'll have things to work with.
2. What's your aim - ASR score? Being moved to tears by Eva Cassidy's voice? Do you want to spend years tweaking them or build them and just listen? Do you want the process, the result or a bit of both? All those are fully legitimate approaches, but will send you down different paths.
3. With the benefit of looking at the process in hindsight, I chose some features that I thought were most important to me, added to that constraints of size, performance, availability, my technical skills, budget, etc etc, then found something that appeared to tick many of the boxes and then took a deep breath and just built them. But an educated guess at best.
4. You'll only know if they're "endgame" once you get to the end...

I'm a simple furniture maker - most of the stuff on this forum is light years above my head - but I do think you should go into what could be a significant DIY project (in both cost and complexity) with your eyes wide open. Don't take on something that will result in you getting sick of the project before you've half finished!
 

Wolf

Addicted to Fun and Learning
Joined
Nov 21, 2020
Messages
557
Likes
589
Location
Indiana
I disagree that passive xovers are an ancient and archaic. I've heard a good many passive commercial and DIY speakers that sound better than fully active dsp systems.
 

Mr. Widget

Major Contributor
Forum Donor
Joined
Oct 11, 2022
Messages
1,147
Likes
1,697
Location
SF Bay Area
I disagree that passive xovers are an ancient and archaic. I've heard a good many passive commercial and DIY speakers that sound better than fully active dsp systems.
I agree with you that well designed passive crossovers can sound exceptional, however a properly implemented active system can match any passive design and in most cases exceed them.

That said, often the full potential of a properly setup active DSP system is not achieved. Sometimes the active DSP tuned system measures really well but sounds less than stellar.
 

Tangband

Major Contributor
Joined
Sep 3, 2019
Messages
2,994
Likes
2,789
Location
Sweden
I agree with you that well designed passive crossovers can sound exceptional, however a properly implemented active system can match any passive design and in most cases exceed them.

That said, often the full potential of a properly setup active DSP system is not achieved. Sometimes the active DSP tuned system measures really well but sounds less than stellar.
The best systems I have heard for + 10 000 dollars has always been expensive active systems , and of all the active systems, a DSP crossover system seems to be the best sounding .

There are many cheap ” active ” computer loudspeakers out there for 100 bucks that give active systems bad reputation . Its not even hifi .
At the price above 1000 dollars then the active approach starts to make real sence.

To make the most of the sound from your endgame speaker , you also have to have a really good sounding source .
Garbage in - Garbage out .
 
Last edited:

jaakkopetteri

Active Member
Joined
Apr 10, 2022
Messages
180
Likes
111
So what should I say anymore? Was this already third false claim in the same thread? Luckily I don't need to ignore you because also this discussion shows that ASR is not worthy for DIY as long as discussion is just unnecessary depating with false claims based on own imagination and biased interpretations.
Do note that the person also said "this is absolutely incredible". While the sarcasm in the reply you're talking about was rather cocky, it was a perfectly valid concern even if it turned out incorrect. I share your frustration when it comes to fanboys and the dogma here, but you don't seem any less arrogant in the way you label reasonable opposing views as "biased interpretations". That's just how conversations work.

I'm sure the vast majority of people here are eager to learn about your designs. You could even shift the dogma (if you haven't already), as long as you don't let some silly comments get under your skin
 

mcdn

Addicted to Fun and Learning
Forum Donor
Joined
Mar 7, 2020
Messages
559
Likes
780

sorry if this has already been mentioned but this could be a good one, my understanding is you can buy a kit

"The speaker can be purchased complete through Salk Sound for $2395 - 2595, depending on what finish you purchase. Alternatively, this speaker can be built as a kit via Meniscus Audio and you can also even purchase a “flat-pack” for the cabinet from Speaker Hardware. Fully assembled (but unfinished), the DIY route would cost you in the neighborhood of $1150 to 1450 (depending on the flat pack order) and if you decided to upgrade components from Meniscus you could do so as well."
BMRs and multiple subs would be very nice indeed. Has anyone figured out an active XO for them?
 

Mr. Widget

Major Contributor
Forum Donor
Joined
Oct 11, 2022
Messages
1,147
Likes
1,697
Location
SF Bay Area
The best systems I have heard for + 10 000 dollars has always been expensive active systems , and of all the active systems, a DSP crossover system seems to be the best sounding .

There are many cheap ” active ” computer loudspeakers out there for 100 bucks that give active systems bad reputation . Its not even hifi .
At the price above 1000 dollars then the active approach starts to make real sence.

To make the most of the sound from your endgame speaker , you also have to have a really good sounding source .
Garbage in - Garbage out .
Agreed.

My point might be self evident, but what I was trying to say is that simply going active and having the full capabilities of measurement and DSP correction is no guarantee of a superior system. The design and the designer must also be excellent.
 

tinnitus

Active Member
Joined
Jan 26, 2021
Messages
144
Likes
199
Location
Germany
Before starting DIY speaker building, you need a measuring system for impedance measurements.
For example DATS V3 and a system for frequency response measurements at the MLP. For example ((acourate)), which i also use for XO generation and room correction.
I think everybody who wants serious information about his speakers and room interaction should make frequency response measurements.

When i decided to build my own loudspeakers, i had the following goals: no shoe box enclosures, a point source if possible, a lot of membrane area for the low frequency to reproduce a good impulse, digital crossovers and room correture. furthermore, it should be modularly adaptable.
And this is the result, after a long development path so far.

IMG_20220130_161627.jpg

and here are some more variations
IMG_20190623_114511.jpg
IMG_20190711_163758.jpg
IMG_20190905_131636(1).jpg
IMG_20210128_171601 (1).jpg
and the black module sounds a bit darker, but the white one a little brighter, so in sum neutral ;-)
and it is quite end game.


and no post without measurements
acourateTest-ripol-1x2buero (2).jpg


cheers
 

Draki

Active Member
Joined
Jan 22, 2020
Messages
112
Likes
148
Location
Macedonia
Before starting DIY speaker building, you need a measuring system for impedance measurements.
For example DATS V3 and a system for frequency response measurements at the MLP. For example ((acourate)), which i also use for XO generation and room correction.
I think everybody who wants serious information about his speakers and room interaction should make frequency response measurements.

When i decided to build my own loudspeakers, i had the following goals: no shoe box enclosures, a point source if possible, a lot of membrane area for the low frequency to reproduce a good impulse, digital crossovers and room correture. furthermore, it should be modularly adaptable.
And this is the result, after a long development path so far.

View attachment 255274
and here are some more variations
View attachment 255278 View attachment 255279 View attachment 255280View attachment 255281 and the black module sounds a bit darker, but the white one a little brighter, so in sum neutral ;-)
and it is quite end game.


and no post without measurements
View attachment 255284

cheers


Kudos to your effort, very original and nice.

However the 255 dB (!) scaled graph is a little....excessive.
The unwritten rule is that 50 dB is the usual format for the SPL graphs.
Of course one can use any scale at will, I am just saying.
 

tinnitus

Active Member
Joined
Jan 26, 2021
Messages
144
Likes
199
Location
Germany
Hi Draki you are right. The db scale is a bit wide, but this is not s SPL measurement it's a frequency respose measurement from the MLP.
 

Rednaxela

Major Contributor
Joined
Mar 30, 2022
Messages
2,052
Likes
2,676
Location
NL
Check out this discussion.

The area between your decades is roughly a square.

8C78016E-6D4D-415A-8567-7547A8327C24.jpeg

If you’d do what @Draki suggests your graph would have the most flattering of the three aspect ratios of the mentioned standard.
 
Top Bottom