Stability AI’s new open source text-to-audio generator was trained on free music libraries to “respect creator rights”Stability AI, the company behind AI-powered image generator Stable Diffusion, has launched Stable Audio Open, an open source model for generating short audio samples, sound effects and production elements using text prompts.

READ MORE: “Sampling will always be a double-edged sword”: Flamingosis talks modern hip-hop production on ‘Better Will Come’

The new model was trained on audio data from free music libraries Freesound and the Free Music Archive. “This allowed us to create an open audio model while respecting creator rights,” says Stability AI. The company adds that Stable Audio Open’s specialised training makes it ideal for creating drum beats, instrument riffs, ambient sounds, foley recordings and other audio samples for music production and sound design.
Users can generate up to 47 seconds of audio data by inputting text descriptions like “warm arpeggios on an analog synthesizer with a gradually rising filter cutoff and a reverb tail” and “rock beat played in a treated studio, session drumming on an acoustic kit”.
One key advantage of the open source release is that users can fine-tune the model on their own custom audio data. For example, a drummer could fine-tune on samples of their own drum recordings to generate new beats.
That said, while Stable Audio Open can generate short musical clips, it is not optimised for full songs, melodies or vocals unlike the company’s flagship Stable Audio service. The latter is able to produce tracks with coherent musical structure up to three minutes in length, and offers advanced capabilities like audio-to-audio generation and coherent multi-part musical compositions.
According to Stability AI, the open source model “provides a glimpse into generative AI for sound design while prioritising responsible development alongside creative communities.”
The company’s latest focus on ‘responsible audio generation’ follows the high-profile exit of its VP of generative audio, Ed Newton-Rex, last November, who quit due to disagreements with the firm over what constitutes “fair use” of copyrighted works.
The former executive said he disagreed “with the company’s opinion that training generative AI models on copyrighted works.” Newton-Rex also told the BBC that he thought it was “exploitative” for developers to use creative work without consent – a stance he claimed many AI firms, including Stability AI, would beg to differ.
The post Stability AI’s new open source text-to-audio generator was trained on free music libraries to “respect creator rights” appeared first on MusicTech.

Travis Scott lawyers file to dismiss uncleared sample lawsuitTravis Scott’s lawyers have filed a motion to dismiss a lawsuit accusing the rapper of using unlicensed samples on the songs Stargazing and Til Further Notice, arguing that the phrase “Alright, Alright, Alright” is “too short” to warrant protection.
The lawsuit, filed by Dion Norman and Derrick Ordogne earlier this year, accused Scott of sampling the 1992 DJ Jimi track Bitches Reply without permission. The song’s intro has been sampled frequently over the years, by artists including Beyonce, Lil Wayne, Cardi B, Kid Cudi and more.

READ MORE: Kendrick Lamar is working on new music, producer Terrace Martin says

Norman and Ordogne said in the suit that they “did not authorise” the sample’s use on either of Scott’s songs. They also claimed that the rapper had “admitted to the unauthorised use of Bitches Reply” when he had a “sample clearance vendor” contact them about clearing the sample for use in his Utopia album (where the track Till Further Notice appears).

In response, Scott’s lawyers have called the allegations “untenable”, arguing that the allegedly infringed-upon phrase “Alright, Alright, Alright” is “too commonplace to be copyrightable”.
“The only alleged copyright infringement here is the alleged copying of the word ‘alright’,” they wrote [via Billboard]. “But the single word ‘alright’ and the short phrase ‘alright, alright, alright’ lack even the minimal creativity required for copyright protection both because these lyrics are too short and because they are commonplace, or stock, expressions.”
The musician’s team also argued that copyright protection only applies to “original” works, which they don’t consider the sampled phrase to be.
Per Billboard, Scott’s lawyers stated that the “repetition of the word ‘alright’ is simply too ‘common,’ ‘everyday,’ ‘trite’ and ‘cliched’” to meet copyright law’s basic requirements. They also referenced a 2003 ruling where T-Pain’s Put It Down was cleared of copyright claims for using phrases like “I can’t get enough” and “raise your hands in the air”.
In their motion to dismiss, Scott’s lawyers also pointed out that the statute of limitations for making a copyright claim for Stargazing has expired.
The post Travis Scott lawyers file to dismiss uncleared sample lawsuit appeared first on MusicTech.

Klipsch’s Nashville offers a sweet, room-filling sound but lacks deep low-end£159/$149, klipsch.com
Best known for high-end hi-fi gear, Klipsch has recently ventured into consumer tech with its Music City portable speaker series. On test here, the Nashville sits in the middle of the range, with the smaller Austin below it and the larger Detroit model above.

READ MORE: Are SONOS’ Ace headphones better than AirPods Max? It’s a close call

What are the Klipsch Nashville speaker’s key features?
The Nashville has dual 2.25-inch drivers that act as an omnidirectional driver, which fills the room in multiple directions, instead of the quasi-stereo approach taken by other Bluetooth speakers. A handy broadcast mode is available to link together up to 10 speakers from the same range, plus the ability to configure a stereo pair.
As well as party-ready sound projection, a water- and dust-proof case ensures the Nashville is ready for the elements. Handily, the single USB-C port (hidden below a protective cover) is also able to provide reverse charging of connected phones and tablets. There’s a rugged, rubbery feel about the case and it’s reassuringly heavy, which suggests chunky speaker magnets inside. The look is smart at the same time, with a rose gold logo emblazoned atop a distinctive punched-hole grille.
There’s a full 24 hours of playback to ensure you never run out of steam mid soirée. Handy extras include an onboard microphone for taking calls and increased wireless range, courtesy of Bluetooth 5.3. But it’s a shame that the Nashville lacks physical transport buttons for pausing and restarting playback without reaching for your phone.
The Nashville in use
How does the Klipsch Nashville speaker sound?
Getting going is simple, with a partner app easily taking care of over-the-air firmware updates and simple-but-welcome EQ shaping. On first listen, we reach out for a bass and mid boost using the 3-band graphic equaliser and also roll off the highs a touch.
Taking a listen — and getting well and truly into the spirit of Nashville — we audition (from the TV show of the same name) Lennon & Maisy’s cover of Ho Hey. There’s a pristine presentation of acoustic guitars, lush vocal harmonies and sizzling cymbals but while the double bass that anchors the mix is audible and articulate, it’s slightly lacking in sub-bass depth.
The more rocking Hedonism from Skunk Anansie is similarly satisfying in the high end, with striking drum transients, luscious tom fills and non-brittle distorted guitar tones.
The Nashville’s partner app
But in Pete Tong’s rework of 7 Seconds, the throbbing lowest octave of the mix is neglected in favour of a silky high frequency tilt. Nevertheless we’re struck by the up-top brilliance of the string section’s lyrical countermelodies.
Compared to our Bose Soundlink Mini, Nashville’s drivers feel far more open — there’s less of a feeling of the frequency range being squeezed into a box, with lows and low-mids that are better separated and don’t appear to approach the onset of distortion as readily. But the Klipsch cries out for some EQ tweaking when put alongside the Bose since we find the highs glassy and the lows subdued in comparison.
Who should buy the Klipsch Nashville speaker?
Klipsch’s Nashville is a highly capable portable speaker that projects a crisp sound, with detailed highs and clarity in the bass end that’s more true to life than the plunging, resonant bass boom of other portable speakers.
It’s great for acoustic music, jazz and classic rock, or background music that doesn’t need to be booming out. The inevitable tradeoff, however, is less sub bass. Those who want bass-heavy tones will find this particular speaker misses the mark, even with the lows pushed to the max on the EQ sliders.
Top of the Nashville
Key features

Dual 2.25-inch drivers
Up to 24 hours of play time
Broadcast mode for linking multiple speakers together
Water- and dust-proofing
Companion app for EQ customisation and firmware updates
USB-C charging / reverse charging

The post Klipsch’s Nashville offers a sweet, room-filling sound but lacks deep low-end appeared first on MusicTech.

Binance CEO: Crypto industry has shifted from ‘early adopters’ to ‘early majority’CEO Richard Teng’s commentary came in response to Binance reaching the 200 million user threshold.

William Anders, astronaut who took the famous ‘Earthrise’ photo, dies at 90William A. Anders, the astronaut behind perhaps the single most iconic photo of our planet, has died at the age of 90. On Friday morning, Anders was piloting a small plane that dove into the water near Roche Harbor, Wash. His son Greg confirmed his death. Anders retired from the Air Force Reserve as a […]
© 2024 TechCrunch. All rights reserved. For personal use only.

Making Intel Mad, Retrocomputing EditionIntel has had a deathgrip on the PC world since the standardization around the software and hardware available on IBM boxes in the 90s. And if you think you’re free of them because you have an AMD chip, that’s just Intel’s instruction set with a different badge on the silicon. At least AMD licenses it, though — in the 80s there was another game in town that didn’t exactly ask for permission before implementing, and improving upon, the Intel chips available at the time.
The NEC V20 CPU was a chip that was a drop-in replacement for the Intel 8088 and made some performance improvements to it as well. Even though the 186 and 286 were available at the time of its release, this was an era before planned obsolescence as a business model was king so there were plenty of 8088 systems still working and relevant that could take advantage of this upgrade. In fact, the V20 was able to implement some of the improved instructions from these more modern chips. And this wasn’t an expensive upgrade either, with kits starting around $16 at the time which is about $50 today, adjusting for inflation.
This deep dive into the V20 isn’t limited to a history lesson and technological discussion, though. There’s also a project based on Arduino which makes use of the 8088 with some upgrades to support the NEC V20 and a test suite for a V20 emulator as well.
If you had an original IBM with one of these chips, though, things weren’t all smooth sailing for this straightforward upgrade at the time. A years-long legal battle ensued over the contents of the V20 microcode and whether or not it constituted copyright infringement. Intel was able to drag the process out long enough that by the time the lawsuit settled, the chips were relatively obsolete, leaving the NEC V20 to sit firmly in retrocomputing (and legal) history.

Can a Toy Printer Be Made Great?Now that the bottom end of the 3D printer market has been largely cleared of those garbage “Prusa i3 clone” models which used to infest it a few years ago, a new breed of ultra-cheap printer has taken their place. EasyThreed make a range of very small printers pitched as toys, and while they’re no great shakes by the standards of most Hackaday readers, they do at least work out of the box. For their roughly $75 price tag they deliver what you’d expect, but can such a basic machine be improved with a few upgrades? [Made with Layers] has taken a look.
These printers have an all-plastic snap-together construction with a 10 cm by 10 cm bed and a set of small geared stepper motors driving their axes. He concentrates on stiffening the structure, upgrading those motors, and because he’s sponsored by a 3D printer electronics company, upgrading their controller.
The motors were replaced first with some NEMA 11 steppers, and then by some over-sized ones which maybe push the idea a little far. By moving the motors to a bracket he was able to free up their mountings to secure a 3D printed insert to stiffen the arms. Perhaps he’s pushing it a little for the video with the electronics upgrade, but we think there’s a happy medium with the smaller of the two motor upgrades and the stiffening.
So if you have an EasyThreed in your life it’s possible to upgrade it into something a little better, but it’s worth asking whether that $75 might be better spent in saving for a better machine in the first place. We’ve been curious about these tiny printers for a while though, and it’s interesting to have some more of our questions answered.

AJ Releases FREE Qsynthi Quantum Synthesizer Plugin
Arthur Freye and Jannis Müller (who go by AJ) have released a new free synthesizer plugin called Qsynthi. Over the years, we have seen a wide variety of free synthesizers, including the popular Vital and Surge XT, which we have covered before. Some work with wavetables, while some may work with simple waveforms or sample-based [...]
View post: AJ Releases FREE Qsynthi Quantum Synthesizer Plugin

Getting It Done: Last Week in D.I.Y. & Indie MusicLast week, our tips and advice for independent and do-it-yourself musicians covered how to monetize your music, the benefits of collabs, Spotify playlist promotion, and more.
The post Getting It Done: Last Week in D.I.Y. & Indie Music appeared first on Hypebot.

REWIND: New music industry’s week in reviewLast week was a busy week by any definition and the music industry was no exception with new predictions for streaming, Spotify increases prices, a boost for DJs on Twist,. Continue reading
The post REWIND: New music industry’s week in review appeared first on Hypebot.

Rigid Audio launch free Rigid Grand instrument Rigid Audio have announced the launch of a free piano instrument for Native Instruments’ Kontakt platform. 

Binance reaches 200M users with $100B in assets under custodyThe 200 million user mark represents over a third of all cryptocurrency holders worldwide.

Anterior grabs $20M from NEA to expedite health insurance approvals with AIAnterior, a company that uses AI to expedite health insurance approval for medical procedures, has raised a $20 million Series A round at a $95 million post-money valuation led by NEA, according to two people familiar with the deal. Existing investors Sequoia, which led Anterior’s $3.2 million seed round last September, and Neo, an accelerator […]
© 2024 TechCrunch. All rights reserved. For personal use only.

Gas-Tight FDM 3D Printing Is Within Your GraspThe widespread availability of inexpensive 3D printers has brought about a revolution in what can be easily made at home. However these creations aren’t perfect, particularly when it comes to the adhesion between their layers. Aside from structural failures along the layer lines there is also the question of those joins being permeable, limiting the possibility for waterproof or gas proof prints. It’s something [German Engineer] has tackled in a new video, in which he’s looking at the design and preparation of small propane tanks.
This is the frame at which the 3D printed tank explodes
The attraction of propane as a fuel is that it liquefies easily on compression, so a propane cylinder or tank will be an equilibrium of liquid propane with pressurized gas above it, whose pressure depends on the ambient temperature. This means that any tank must be expected to have a working pressure somewhere between 150 and 200 PSI, with of course a design pressure far exceeding that for safety reasons.
Filling a 3D printed tank immediately results in the propane escaping, as he demonstrates by putting one of his prints under water. He solves this with a sealant, Diamant Dichtol, which is intended to polymerize in the gaps between layers and create a gas-tight tank. A range of three tanks of different thicknesses are treated this way, and while the 1 mm thick variety bursts, the thicker ones survive.
It’s clear that this technique successfully creates gas-tight prints, and we can see the attraction of a small and lightweight fuel tank. But we can’t help worrying slightly about the safety, for even when the material is a lightweight 3D print, high pressure equipment is not to be trifled with. Tanks do burst, and when that happens anyone unfortunate enough to be close by sustains nasty, even life-threatening injuries. Use the technique, but maybe don’t hit it with high pressures.

UniMagic effects plug-in from Rob Papen Rob Papen's latest plug-in is an incredibly simple processor that has been designed to offer a quick and easy way to ‘thicken up’ just about any sound source.