Artificial intelligence AI-generated Audio Loudspeaker MidJourney Speakers

Loudspeakers Generated by Artificial Intelligence – How AI Can Boost Your Creativity

Artificial intelligence in loudspeaker design

Artificial intelligence is a tool that loudspeaker designers can use when they want to think outside the box and come up with modern and unique designs. We will focus on image-based AI in this text because that is easily available to the public and does not require engineering considerations. Although AI-generated images seem to take cues from existing designs, AI can merge features in a novel way. For example, merging loudspeakers and furniture or blending the loudspeakers with the interior design. Instead of specific technical or topological solutions, think of it more like a mood board or general family of concepts. The greatest benefit of artificial intelligence in the design process is generating a multitude of new concepts in a short period of time.

artificial intelligence loudspeaker
Clever combination of furniture and loudspeakers. Posted by Lucas D. on the Facebook group AI Loudspeaker and Stereo Design.

How to get started

One of the most popular tools currently is MidJourney, which creates “unique imagery from short text descriptions”. You can start using AI algorithms like MidJourney to generate new designs by simply coming up with your own unique prompts. The easiest way to start using MidJourney is to join one of their newbie channels, create your own server and invite the bot there (see video at the end of this article).

Another option is using DALL-E, which is oriented more towards generating art, but also image editing. DALL-E is developed by OpenAI, who are known for GPT-4.

A great upcoming alternative is Imagine: AI Art Generator by Vyro AI. It is available for iOS and Android operating systems. The free trial has video ads, limited settings and watermarks.

artificial intelligence loudspeaker
AI-generated image when prompting for a sphere-shaped loudspeaker.

Contrary to what some guides tell you, direct messaging prompts directly to the MidJourney bot does not work in the free trial version. You have approximately 25 free prompts (0.4 hrs GPU time) without a subscription. Upscaling, generating variations and repeating a prompt (“rerolling”) uses up your GPU time quota. The most inexpensive subscription plan is $8/month at the time of writing this and it gives you 3.3 hrs of GPU time and ownership of results.

If You are not a Paid Member, You don’t own the Assets You create. Instead, Midjourney grants You a license to the Assets under the Creative Commons Noncommercial 4.0 Attribution International License./…/By default, Your images are publically viewable and remixable.

MidJourney Terms of Service

Examples of AI-generated loudspeakers

Coming up with useful prompts can be challenging and the output is seldom what you had in mind. That’s the beauty of it though. To give you an idea of what kind of results can be obtained, we have listed some of the more successful prompts and their corresponding results. They are by no means the best that can be achieved, but rather a result of simply experimenting with AI. We have included some comparisons MidJourney vs. DALL-E to give you an idea of what kind of results to expect. First, let’s give both image-generating AIs something ordinary like:

/imagine small loudspeaker with scandinavian design in a livingroom
artificial intelligence loudspeaker
Results from MidJourney
Results from DALL-E
Result from Imagine

Next, let’s ask something more specific:

/imagine studio monitor loudspeaker with waveguide in recording studio environment
artificial intelligence loudspeaker
Result from MidJourney
Result from Imagine

Since RD Physics develops 3D-printed loudspeakers, let’s see how well the AIs understand that and how creative they get:

/imagine 3D printed loudspeaker in livingroom
artificial intelligence loudspeaker

You can also upload images to your Discord server and use the URL of those as part of your MidJourney prompt or upload an image to DALL-E and create variations. Below you see what happened when we uploaded a photograph of our Circular Sound Eikosa speaker and placed it in another environment using MidJourney and asked DALL-E to create variations:

/imagine <image URL> on a table in a scandinavian livingroom white colour
artificial intelligence loudspeaker
Placing into another environment with MidJourney
Asking DALL-E to create variations

As you can see above, MidJourney will often mess up the shape of the original input photograph. For some reason, the pentagonal face of the speaker always becomes hexagonal and the icosahedral shape is also lost. You can also directly ask for a shape in the prompt (with varying success):

/imagine small icosahedron shaped loudspeaker in livingroom
artificial intelligence loudspeaker

Future Outlook

We asked ChatGPT to explain the potential benefits of AI in loudspeaker design and here’s what it had to say (edited for brevity):

Firstly, AI can help to optimize the design of loudspeakers for specific applications. By analyzing data from simulations and experiments, AI algorithms can identify the optimal shapes, sizes, and materials for loudspeakers that are intended for different uses.

Secondly, AI can help to reduce the time and cost of designing and testing loudspeakers. With AI, simulations can be run to test different design parameters, allowing designers to quickly identify the best designs without the need for expensive and time-consuming physical testing.

Thirdly, by analyzing large amounts of data, AI algorithms can identify patterns and correlations that might be missed by human designers. This can result in more precise designs that perform better and are more consistent across different manufacturing runs.

Overall, using AI for designing loudspeakers can result in more optimized designs, faster design iterations, and more accurate and precise designs, all of which can lead to improved sound quality and performance.



The easiest way to implement AI in loudspeaker design is to use a visual tool like MidJourney. It does not consider acoustics, materials, or 3D dimensional structures. Knowledge in those fields is needed to evaluate the feasibility of each concept created. Nevertheless, AI-generated images can be of assistance in the ideation phase when one would typically use sketching or other quick visualization methods to explore new designs.

artificial intelligence loudspeaker
Posted by David M. on the Facebook group AI Loudspeaker and Stereo Design

At first glance, these ideas may seem way too complex to fabricate. That is true if confined to traditional woodworking methods. However, 3D printing is a technology that can help in making these intricate designs become reality. The design freedom that 3D printing allows is not limitless, but unparalleled. Many of the AI-generated loudspeaker designs could not be fabricated economically in any other way. For advice regarding 3D printing in audio, we recommend our DIY blog and the Facebook group 3D Audio and Hi-Fi Projects. Have fun experimenting and remember that the AI only knows what it has been taught and only does what it is told.

Below is a video explaining how to set up MidJourney with Discord.

3D printing Audio DIY Loudspeaker Speakers Technology

A versatile 3D printed coaxial loudspeaker – RD Physics CX2

The first version of our 3D printed coaxial CX loudspeaker series was made using the Desktop Metal Forust method, which is, at the moment, too expensive for most DIY audio enthusiasts. Therefore, the CX2 was designed based on fused filament fabrication (FFF).

3D printing gives design freedom

The starting point for the design is simple but effective: sealed enclosure and coaxial driver. This inherently gives us controlled cone displacement in the low-frequency region and a coherent radiation source in the crossover region. 3D printing allows to easily implement two more acoustically beneficial geometries: large roundovers and compound curved walls. These translate into a Minimal Edge Diffraction Enclosure (MEDE™) and reduced panel vibrations, respectively. Curved walls mean that the loudspeaker requires a stand. This requirement can be turned into a benefit: the symmetric loudspeaker can be tilted or laid on its side when placed on a so-called Isopodd stand 3D printed from soft TPU material. 3D printing allows complex shapes at no extra manufacturing cost. For example, the front baffle is stiffened on the inside with a honeycomb strucure that acts also as support for the overhangs, but robs very little internal volume.

What you need to build your own CX2

  • 3D files for 3D printing, sold on Etsy. Dimensions 210x273x170 mm, ~1200 grams of filament.
  • SB Acoustics SB13PFCR25-4 COAX or SEAS MP15 (contact us)
  • Active crossover, miniDSP recommended
  • Two channels of amplification per speaker, ICEpower module recommended
  • Neutrik NL4MPR SpeakON connectors and fastON crimp connectors
  • 4.2 mm wood screws
  • Bitumen or similar visco-elastic damping sheet and fibrous damping material such as pillow stuffing
  • Soldering capability (super easy)

How to build it

3D print the enclosures using the files mentioned above. It’s a single-piece print with no support needed. Wood-filled PLA or similar material is easy to sand and no other surface finish besides sanding is needed. If you are using the SEAS drivers you also need to print the TPU gasket/adapter. The speaker can be tilted and rotated when you print a small stand for it from TPU material. Some rubber feet on a plate will do the same job just fine. The assembly order is as follows:

  1. Finish the outside of the enclosure and make sure the driver and SpeakON connector fit.
  2. Line the inside with bitumen damping material and fill it quite densily with wadding.
  3. Solder wires to the speaker drivers and crimp fastON connectors at the other end. Mark woofer and tweeter positive and negative wires.
  4. Feed the wires through the SpeakON connector opening and mount the driver using wood screws. Use gasket/adaptor if you have the SEAS driver.
  5. Connect the fastON connectors to you SpeakON connector and mount it.
  6. Setup your bi-amping and crossover configuration. A good starting point for crossover frequency is 2 kHz. On-axis response will be bright, so keep that in mind when equalizing. Some toe-in may be beneficial.


Bluetooth speaker 3D printing Audio Circular economy DIY Loudspeaker Recycling Speakers Sustainable development

Bluetooth loudspeaker without an internal battery

What’s wrong with having batteries in your portable boombox?

Wireless electronics, such as bluetooth speakers, are extremely popular nowadays. All such devices must have a power source and typically it is a lithium-ion battery. However, the demand for battery raw materials is rising at an alarming rate:

The supply of some of these [battery] materials, in particular cobalt, natural graphite and lithium, is of concern today and for the future in view of the large quantities needed and/or very concentrated supply sources.

European Battery Alliance (EU)

As we have discussed earlier, when launching our Circular Sound program, the best solution for reducing reliance on critical raw materials is to reduce their use. The RD Physics BB1 boombox enables you to do just that. It is designed to use existing external power sources and therefore no new batteries are needed. Battery service-life or battery replacement is no longer a concern.

Alternatives to dedicated batteries

The BB-project started by looking at how power tools are sold without accompanying batteries. The idea being that the user needs only one battery (plus spares) that fits all tools. While this approach reduces the amount of batteries needed, it is also used to tie the customer to a specific brand. We wanted a universal solution and therefore the USB-C standard was chosen. The BB1 and BB2 boomboxes use a USB-C port as an interface to feed power to the amplifier. The boombox can be connected to any USB port: power banks, phone chargers, laptops, extension cords, solar panels etc. Obviously, the input voltage and current draw is limited, which leads to limited sound pressure level (SPL).

The weather-proof USB-C port is located at the top.
Frequency responce of 3D printed bluetooth speaker.
Frequency response of BB1 at maximum drive level.
BB2 boombox with Dayton Audio RS100 drivers.
Frequency response of BB2 at arbitrary drive level.


What you will need to build your own batteryless boombox:

  • Geometry files for 3D printing (free under Creative Commons License at Thingiverse)
  • 3D printer big enough to fit a 235 mm diameter sphere
  • Slightly over 1 kg of filament depending on your settings
  • Two active drivers. Either Peerless 3″ (BB1) or Dayton Audio 4″ (BB2)
  • One 6½” Dayton Audio passive resonator
  • A Sure (Wondom) bluetooth board with additional cables set
  • USB-C panel mount plug (from eBay) and 6 mm DC plug
  • Wood screws (4.2 mm for the drivers and resonator, 3 mm for the BT board)
  • Drawer handle, IKEA Eneryda 703.475.16
  • Damping material (bitumen or similar automotive damping mat and fibrous wadding, for example pillow stuffing)
  • Optional: Wall mount bracket, Genelec 4000-410B
  • Minimal soldering capabilites

The enclosure for the BB1 and BB2 can be downloaded from the link above. Assembling everything takes 30 minutes.

3D printed boombox enclosure
3D printed enclosure ready for assembly.

How to build the BB1/BB2 bluetooth speaker

  1. Start by soldering the 6 mm DC plug to the USB connector. Red (+) goes to center pin and black (-) to outer shell.
  2. Connect DC power and speaker cables to bluetooth board and fasten the board inside the enclosure by tightening the screws via the driver openings.
  3. Mount the USB connector and handle.
  4. Line the inside of the enclosure with bitumen or similar visco-elastic damping material. Heat will aid in conforming to internal shapes. Make sure the damping material is fully bonded to the walls.
  5. Bring the speaker wires through the driver openings and solder them to the drivers. Make sure polarity is the same for both drivers. Then fasten the drivers using wood screws.
  6. Fill the enclosure with fibers (cotton, polyester, wool etc.) and fasten the passive resonator.
  7. Optional: Attach the wall mount bracket.
  8. Connect a USB port and the bluetooth board powers on automatically. Pair your signal source with the device (“WONDOM”). Enjoy!
BB1 portable bluetooth speaker with 3D printed enclosure.
BB1 ready to rock.

Assembly instructions

Concept and sound test

Audio 3D printing Circular economy DIY Loudspeaker Speakers Technology

3D printed wood – A revolutionary way of making loudspeakers

3D printed loudspeakers do not have to be made out of plastic anymore. There is a new way of 3D printing wood called Forust. It is a binder jetting process where upcycled sawdust is used together with a binder to form the closest thing we have to 3D printed wood. We are particularly interested in the possibilities this offers loudspeaker manufacturers.

RD Physics CX1 – A coaxial loudspeaker

RD Physics has been developing speakers with full-range drivers for some time now and while they have their inherent benefits, it is time to look what coaxial drivers have to offer. The starting point was a spherical shape, which is known for its benefits. However, the limitations in build volume favored a shape closer to a rectangular cuboid. The shape of the CX1 has the largest possible roundovers, with the constraints imposed by driver size and maximum baffle dimensions. This is to reduce edge diffraction. The sides are compound curved to maximize stiffness. There is also internal ribbing to stiffen the enclosure without taking up internal volume like a sandwich structure would. The enclosure is made in two parts; the front baffle has a separate cover that conceals the driver flange and mounting screws. The driver is a proprietary SEAS unit designated MP15 (15 cm diameter). The idea is to have an external active crossover and bi-amp the loudspeaker via the Neutrik SpeakOn 4-pin connectors at the back.

3D printing a loudspeaker using Desktop Metal Forust method

The geometry files were sent to Forust for 3D printing. The chosen colour is “natural” with the artificial wood grain introduced during manufacturing. The result is a structure that looks like plywood. Parts can be ordered without the grain and with darker colours, too. The grain is more interesting, however, because various surface texture effects can be achieved by aligning the layers at low angles relative to the principal axes of the printed shape giving a zebra stripe effect.

Post-processing of 3D printed wood

The parts printed with the Forust method can be sanded smooth, but it is not like sanding natural wood. The surface can be varnished, but not stained. The Forust material does not absorb wood stain. It does not tolerate ethanol and perhaps other solvents either. Long-term exposure to water should be avoided, otherwise there will be is a sticky brown residue on the surface. Although a wooden look can be mimicked, post-processing is not similar to wood. Instead, it resembles the wood-filled polymers used in our previous builds. This is not a serious drawback, it just means that 3D printing skills are more useful than woodworking skills. In terms of aesthetics this is the closest thing available for increasing the acceptance of 3D printed loudspeakers in the audio community, where wood veneer is the go-to solution.


Technology Audio DIY DSP Loudspeaker Speakers

Acoustic panels and DSP – Both are beneficial

It is tempting to consider “room correction” with Digital Signal Processing (DSP) as a substitute for acoustic treatment. We implemented both in the same room to see what the effects actually are.

Experimental setup: DSP and acoustic panels

The setup used is a normal living room/home theater. The loudspeakers are Genelec 8351A active monitors with DSP and automatic calibration using a microphone and frequency sweeps.

Home theater with active DSP speakers
The test setup with Genelec active monitors.

Five acoustic panels were placed in the room. They are mineral wool panels measuring 60x60x10 centimeters. Two of them were placed at the side walls in order to address first sidewall reflections and three of them were placed behind the listener by the back wall. The measurement point is also the normal listening point. Measurements were done with REW software:

The effect of acoustic panels and DSP on room response

Effect of acoustics panels and DSP on frequency response.
Effect of acoustic panels (top) and DSP (bottom).

From the magnitude response we see that the acoustic panels bring down some of the peaks in the mid-range. When we then apply DSP and automatic calibration, we get attenuation of the low-frequency peaks caused by room modes. DSP does not really affect the mid-range and the highs. It only raises their level back to where it was earlier. Using DSP and equalizing for mids and highs would be very difficult, because notches and peaks are very narrow.

Waterfall chart showing reduced decay time with acoustic panels
Waterfall charts show faster decay at mid-range frequencies when acoustic panels are applied.

Spectrograms show massive amounts of energy in the bass domain, where we have room modes affecting. Panels this size should not be very effective at long wavelengths according to the manufacturer and our magnitude plot. Yet, adding acoustic panels brings down the energy across the frequency range according to the spectrogram. DSP reduces the bass peaks which, of course, reduces the energy in that region. DSP brings up the mids and highs, so we can see slightly increased energy in that region, which leads to an evenly distributed energy across the spectrum of frequencies.

Effect of acoustic panels and DSP on acoustic energy content
Spectrograms of the reference condition (top), with acoustic panels (middle), with acoustic panels and DSP (bottom).


So do you need both digital signal processing and acoustic treatment? Yes. Looking at the magnitude response, we see that DSP addresses the peaks in the bass region and adjusts for the overall level, while the acoustic panels address the mid-range frequencies. Looking at the energy spectrum, we can see that actually both acoustic panels and DSP even out the energy distrubtion across the frequency range. It is encouraging to see that placing only five panels has a measurable effect. Headphones are immune to room acoustics, but benefit from DSP. Check out our post on headphone DSP:


This blog post can be found in video format as well.


Technology Audio DIY DSP Headphones

Digital Signal Processing – Improve your headphones for free

Using a computer as your signal source gives you immense DSP possibilities. It does not cost a thing and reverting back is easy in case you do not like it. There is really no reason not to give it a try. A good place to start is here:
There you will find EQ presets for most headphones and links to applying equalization in your operating system using Equalizer APO. Some users may like the Peace add-on which can be found together with Equalizer APO. If you have issues with system-wide equalization, you may want to try a plug-in for your music player. We can recommend Foobar2000 (oldie but goldie) and Math Audio Headphone EQ.

Math Audio preset files for Porta Pro and HD800S headphones

Here’s the preset file to be used in the Math Audio plug-in when listening to Koss Porta Pro headphones. It’s based on Oratory1990’s EQ profile.

Equalizing curve for Koss Porta Pro headphones
EQ for Koss Porta Pro based on Oratory1990’s measurements

We found the equalizing curve for Sennheiser HD800S to be too harsh, brightening up the sound too much. Therefore, the gains of the peaking EQ were halved and entered into the Math Audio plug-in. You can download it here:

Equalizing curve for Sennheiser HD800S headphones
Modified Sennheiser HD800S EQ

We have got to remember that the EQ files found online are obtained using a measurement head and aiming at a flat frequency response. However, each individual has physically different ears 
and a flat frequency response may not be what we actually want. The recordings that we listen to vary and the type of music varies. The presets are a good starting point, but they should be tweaked to make sure the sound is to your liking. Are there any downsides to processing the signal? There could be some artifacts from filtering such as pre-echo and you could get added distortion from excessive bass boost, but as long as it sounds better to you then that’s all that matters. Give it a try!


This post is available in video format.
Technology Audio DIY DSP Headphones Loudspeaker Speakers

Headphones are better than loudspeakers – One factor is behind it all

The argument for headphones instead of loudspeaker as your main sound system is one that you don’t hear too often. Which is why we think it’s important to make it here. It all boils down to one root cause, and that root cause is the room. Let’s divide the consequences of the room into two categories: cost and sound.


First, speakers are played in a room you need more power. Power means power amplifiers. You need to buy expensive amps to power your loudspeakers. Second, you need to place those loudspeakers somewhere, so you need to buy stands. Or if they are floor-standing speakers you need to buy feet. You need to connect them with cables and buy other accessories. Third, you need to acoustically treat your room, so you need to buy acoustic panels, diffusers, bass traps etc. Fourth, you need to buy presents to your spouse because you’re placing the speakers in the middle of the room.


You can buy good loudspeakers and ruin them by placing them in a bad listening environment. Optimally, you would have the loudspeakers and the listening position at least two meters away from the nearest wall. However, that is seldom even possible in the available space. You would need a large room. And with this kind of placement, a livingroom quickly becomes a listening room only. Headphones, on the other hand, have multiple benefits compared to loudspeakers:

  • Single point source
  • No crossovers
  • No sweet spot or particular listening position
  • No room effects
  • Tonal balance can be fixed using only DSP

Some of the drawbacks often stated include poor sound stage or imaging. People say that it sounds like the sound is coming from inside one’s head and it doesn’t feel like you’re at a concert. It is a matter of personal preference, but we suggest looking at headphone listening as something separate and different from live events or loudspeaker listening. It is our subjective opinion that crossfeed will not correct for this phenomena and only makes the sound worse. Another common argument is that there’s no physical sensation of bass. While that is true, the pros outweigh the cons.

Recommended hardware

Which ever headphones you use, applying equalizing with the help of DSP is definitely worth considering. Check out our post on the topic:

Sennheiser HD800S open headphones.

 Enthusiast level:

Hobby level:

  • Sennheiser HD650
  • DAC/amp in price range 200-300€
  • DSP at signal source

Budget level:

  • Koss Porta Pro
  • Analog jack or DAC/amp in 100-150€ price class (get one second-hand, for example)
  • DSP at signal source


The contents of this post can be found in video format

Technology 3D printing Audio DIY Loudspeaker Speakers

Powerful 3D printed 5 inch subwoofer – SW2

Subwoofer Concept

Our previous 3d printed subwoofer, the SW1, is a 13 liter subwoofer with a 6.5″ driver, a matching passive radiator and a plate amp. We wanted to develop something smaller that would still offer the bass extension that satellite speakers so badly need. The result is the SW2 using a Tang Band W5-1138 5″ long-throw driver and the same Dayton Audio DSA175 passive radiator as in the SW1. The enclosure is now only 5 liters and much easier to fit on a desktop. The passive resonator allows tuning the resonance frequency to avoid overlap with room modes, for example. The spherical shape is optimal for material use and stiffness. Combined with the small diameter driver with large surrounds, the appearance is quite unique. If a traditional box is what you want, then this build is not for you.


The measured resonance frequency of the passive radiator indicates that some air-coupling occurs due to the downward firing placement. Simulated resonance frequency matches the measured value (53 Hz) when 16 grams of added mass is used. Mass can be further added using washers to tune the response. In practice, the frequency response starts to drop below 50 Hz. The Arylic amplifier offers DSP capabilites and using a computer as the source allows unlimited DSP with zero cost. Therefore, frequency response in not that meaningful especially when considering the room effects, but we have included some measurements to give an idea of the natural response especially around the lower cut-off.

3D printing

The enclosure is printed in one part (234 mm diameter) and takes approximately 1.5 kg of filament. Print time is about 48 hours. The mass can be increased by lining the walls with sound deadening mat. Although the external wall is spherical, there is a cylindrical inner wall that braces the woofer to the passive resonator and, thanks to a single curvature surface, allows easy installment of thick sound deadening mat. The drivers are fastened using 4.2 mm wood screws. There is a geometry file for a gasket for the woofer which can be printed from TPU. Traditional gasketing methods will work, but the 3D printed gasket is seamless and has the screw hole pattern accurately incorporated. The binding posts are recessed deep into the enclosure and only accept banana plugs in that configuration. An O-ring under the binding post washer is recommended and there is a chamfer for it. 3D printing using a wood-filled filament allows easy sanding for a smooth surface finish. The photos show 15 minutes worth of post-processing making this a very easy and fast build without compromising in function and looks.


Sound quality

The subwoofer was compared to the much larger, THX certified Logitech Z623 subwoofer. The sound is very similar, but in a much smaller package. The SW2 is a great companion for small satellite speakers and brings fullness to the bass. Electronic music will benefit from the “boom” offered by this small unit, while other types of music may require turning down the level a bit for a tighter bass.

Links and video

The 3D files can be found in Etsy store:

Please support us by using the affiliate link below just before ordering the components:

TangBand W5-1138 on

Dayton Audio DSA175-PR on

Arylic 2.1 BT amp on

Technology 3D printing Audio DIY Loudspeaker Speakers

3D printed active subwoofer – SW1

Our 3D printed full-range speakers needed something to beef up the lower end of the frequency spectrum. We set out to design a compact subwoofer that can be used together with our FR3 speakers. The result is a 13 liter enclosure with a 6.5″ driver, a matching passive resonator and a plate amp. The passive resonator allows tuning the resonance frequency to match room modes, for example. The plate amp can power satellite speakers and has a fixed high-pass filter. The low-pass cut-off frequency for the subwoofer can be adjusted and the level too, which means that this system can be easily mated with signal sources that do not have equalizing or DSP capabilities in themselves.

3D printing

The enclosure consists of two parts, which are glued together after printing. Total print time is about 100 hours and uses about 4 kg of filament. Support is only needed for the small recess where the plate amp is mounted. Dual-material printing is not needed. The mass of the enclosure can be increased by filling the walls with epoxy through the holes in the back. A geometry file for 3D printing a matching funnel is provided, too. 2 kg additional mass can be obtained this way.

The 3D files can be found on Thingiverse for free:

Please support us by using the affiliate link below just before ordering the components:

Dayton Audio DSA175 on

Dayton Audio DSA175-PR on

Lepai LP210PA amp on


The video below explains the concept in more detail.

Audio 3D printed 3D printing Carbon fiber DIY Loudspeaker Speakers Technology

Six reasons 3D printed spherical loudspeaker enclosures are popular


It is striking how often 3D printed speakers take the shape of a sphere and that is also how RD Physics started with the FR1 full-range speaker. What are the benefits of spherical loudspeaker enclosures and why are they so popular?

  1. Rigid and void of panel vibrations
  2. Minimum material use for a given volume
  3. Potentially avoid edge diffraction
  4. Omnidirectional up to a relatively high frequency and controlled baffle “step”
  5. Aesthetically pleasing with a single circular driver
  6. Difficult to manufacture any other way than 3D printing

As RD Physics has extensive experience in these types of enclosures, we have decided to share our learning in one blog post. The models are presented in chronological order allowing the reader to understand the development that took place over the years of building and listening to various versions of the FR. Most of the designs are offered open-source to the community.

FR1 – Full-range bliss in a compact form

The FR1 is a spherical (180 mm diameter) full-range loudspeaker with a sealed enclosure. Internal wall stiffeners are used in order to maximize internal volume as opposed to simply increasing wall thickness, which robs internal volume. We use Noise Killer paint to both seal the enclosure and also to add mass and damping. The sound of the FR1 speakers is very unique and quite tricky to get the most out of. The full-range emitters are very directional and the listening distance also changes the sound markedly.

ModelRD Physics FR1
DriverMark Audio Alpair 6M 2.5″
Enclosure3 liters sealed
MaterialUPM Formi3D
ConstructionInternal webbing with Noise Killer damping
TiltFixed at 15 degrees

FR2 – Exotic carbon fiber skin reduces resonances

Additive manufacturing (AM) has many benefits over traditional construction methods, such as design freedom, fast product development, and integration of functions into one part. There are drawbacks as well. The plastic AM parts tend to be low in mass and not very stiff. Air-tight walls are sometimes difficult to achieve, too.  Adding mass by increasing the fill density of the print is not a good solution, since it adds build-time and material cost. Stiffeners and bitumen paint were used in FR1. However, the stiffeners were cumbersome to paint with bitumen and it did not add significant weight. For FR2, we used the vent as a part of the mechanical structure and used a thicker wall. But some additional means were needed to bring 3D printed enclosures on par with traditional cabinet materials.

Carbon fiber in loudspeaker building

Dry carbon fiber tow was wound around the enclosure and then wetted with epoxy resin. The composite skin was sanded after curing and additional coats of epoxy were added. The result is a unique unidirectional carbon fiber surface finish. The composite shell adds mass and stiffness to the enclosure. The loudspeaker sits on four feet printed from TPU material, which allows rotation.

ModelRD Physics FR2
DriverMark Audio Alpair 7MS 3″
Enclosure5 liters vented
MaterialUPM Formi3D + CFRP
ConstructionStructural port and carbon fiber skin
TiltTPU feet allow tilt ~0-15 degrees

FR3 – Metal-filled filament for mass and rigidity

The FR1 used internal ribbing and Noise Killer paint to reduce enclosure resonance. The FR2 used an external carbon fiber shell. Both approaches were a bit cumbersome and laborious. For the third version, we wanted to fully use the capabilities of 3D-printing. Therefore, a high-density metal-filled filament was used an internal gyroid-shaped support was used even where overhanging surfaces would not have required it. In addition, height and tilt can be adjusted using three threaded rods that form a tripod. The finished enclosure with three 14 mm trapezoid-threaded nuts bonded to it weighs 1.2 kg. The RS100 drivers have a distinct on-axis peak at the upper treble, which actually works nicely for those who like a bright sound. Those who don’t should toe-in the speakers a bit.

ModelRD Physics FR3
DriverDayton Audio RS100 4″
Enclosure2 liters sealed
MaterialColorfabb steel fill
ConstructionGyroid infill as an internal stiffener
Tilt14 mm leadscrew tripod

FR4 – Refining the concept further

The metal-filled filament used in the FR3 was too brittle and difficult to post-process. The FR4 uses wood-filled filament, which is more ductile and easier to sand if needed. The surface is quite nice straight out of the printer thanks to the matte surface. A quick touch with an orbital sander gives a smooth finish. Leadscrew nuts are bonded into recesses in the enclosure and allow for adjustment of the legs. Small TPU feet can be printed and placed at the ends of the leadscrews in order to avoid scratching the desktop. These are satellite speakers and need a subwoofer to complement the lower frequency spectrum.

ModelRD Physics FR4
DriverTangband W3-1878 3″
Enclosure1 liter sealed
MaterialAddNorth Textura
ConstructionGyroid infill as an internal stiffener
Tilt12 mm leadscrew tripod

FR5 – Returning to square one

Reviewing the FR project so far, we came to the conclusion that all things considered, the original FR1 is the DIY project that was the most fun to build and listen to. It’s simple but rewarding once dialed in. For the FR5 we went back to basics by ditching the tripod and returning to a simple white spherical enclosure. The tilt adjustment is handled by a TPU mounting ring that allows a large adjustment range. The Scan Speak 10F driver is one of the best for voice reproduction, but our subjective view is that it needs a tweeter in addition to a subwoofer making it suitable for three-way builds only.

ModelRD Physics FR5
DriverScan Speak 10F 3″
Enclosure2 liters sealed
MaterialAddNorth Textura
ConstructionStiffeners and alu-butyl sound-deadening mat
TiltTPU ring +-30 degrees

3D files and components

In the table below you’ll find links to the drivers used in each version as well as the geometry files needed for slicing the toolpaths. Support us by clicking on the Soundimports affiliate links before buying anything from them (we get a small commission and it won’t cost you a dime). Thank you!

ModelComponents3D files
FR1Alpair6M at SoundimportsFR1 at Thingiverse
FR2Alpair7MS at SoundimportsFR2 at Thingiverse
FR3RS100 at SoundimportsFR3 at Thingiverse
FR4W3-1878 at SoundimportsFR4 at Etsy Shop
FR510F at SoundimportsFR5 at Thingiverse



We wish to thank UPM for the Formi3D materials and support. Photos taken by J-P Virtanen and Markus Markkanen. Erell Bodinier handled the carbon fiber skinning.