Audionamix Releases New XTRAX STEMS via Subscription

Audionamix Releases New XTRAX STEMS via Subscription

Audionamix Releases New XTRAX STEMS via Subscription

Subscriptions Include New 4-Stem Separation Software and Member-only Benefits

LOS ANGELES, MARCH 9, 2020Audionamix Inc., the global leader in audio source separation, releases a brand new 4-stem version of XTRAX STEMS, now available exclusively to subscription members. Membership includes access to exclusive benefits and free, regular updates to both the software and separation algorithms throughout the duration of the subscription.

XTRAX STEMS is powered by advanced AI at supercharged GPU processing speeds. With a simple drag and drop, songs are automatically separated into four parts: vocals, drums, bass and remaining music. Songs can also be separated more efficiently based on specific needs, such as creating backing tracks, acapellas, or drumless tracks. The completely redesigned software features a sleek new user interface and a De-bleed slider to refine separations in real-time. XTRAX STEMS redefines music production, music education, DJing, remixing and mashup creation.

“With this release, we rebuilt XTRAX STEMS to offer creators a new platform for unmixing,” says Nicolas Cattaneo, deputy CEO of Audionamix. “Thanks to our new subscription model, we will continuously update the software. That includes improved deep learning algorithms, but also innovative features to unlock our users’ content and use new parts of it in brand new mixes.”

XTRAX STEMS is compatible with Windows® 10 and macOS® 10.12 – 10.15 operating systems and requires a high-speed internet connection. Subscriptions are available for $40 per six-month period or $60 per year. Special subscription pricing is available via ​ for owners of XTRAX STEMS 1 or 2.


Windows and Windows 10 are trademarks of Microsoft Corporation, Redmond, Washington. All versions of macOS are trademarks of Apple Inc., Cupertino, California.

About Audionamix

Audionamix is the global leader in audio source separation. Built on advanced signal processing and artificial intelligence, Audionamix technology extracts specific elements from an audio file, including speech, vocals, drums and bass. Armed with this licensable technology, the Audionamix Professional Services team has worked on major motion pictures, GRAMMY-nominated albums, and hit TV shows across the globe. For more information, visit

Audionamix Wins ADE ’19 “Companies 2 Watch” Competition

Audionamix Wins ADE ’19 “Companies 2 Watch” Competition

Audionamix Wins ADE ’19 “Companies 2 Watch” Competition

On the second day of Amsterdam Dance Event 2019, ADE Tech hosted the Companies 2 Watch (C2W) competition inside of the exquisite DeLaMar Theatre in Amsterdam. Acting as ADE Tech’s version of Shark Tank, C2W crowns the most innovative idea or product with the potential to revolutionize the music industry. Audionamix was exhilarated to be selected as one of the top five finalists to pitch in front of the expert panel of judges. We were hopeful that our advancements in audio source separation through the use of AI and machine learning would win over the panel. Among the judges were Dr Werner Vogels, the CTO of Amazon, Suzy Ryoo, the Co-Founder and President of Q&A, and Diego Farius, the Founder and CEO of last year’s C2W winning company, Amuse. The judges were able to interact, ask insightful questions and ultimately vote for a winner based on which company they would like to follow for the next year. In the event of a tie, the audience vote would determine the winner.

Our host, Jan Maarten Hartong from School of House, kicked off the event with ADE’s shortest rave, 3-minutes of adrenaline-pumping music accompanied by great choreography and dancers on stage. We were officially ready to go!

First to present was Jambl, the mobile app that allows users to easily and intuitively create music. Using an XY parameter control, Jambl manipulates pitch and time of looping sounds from various sample kits on a mobile device. Along with a fun and easy to use interface, Jambl also allows users to interact by sharing their beats in a community of Jambl users. Jambl CEO, Gad Baruch Hingis, performed a charismatic and cleverly written rap that explained the basics of the Jambl app. His pitch was engaging and fun, just like the Jambl app!

Next up was Fangage, the fanbase oriented platform which gets rid of third parties and allows artists to have ownership over and direct interaction with their fans. International DJ and artist, Sam Feldt, spoke about his own experience attempting to connect with local fans via Facebook and Instagram and the limitations of those platforms to accurately target and connect with specific audiences as an artist with millions of followers. This conundrum led him to develop Fangage, an easy-to-use platform that offers direct fan engagement, a win for both artists and fans!

Ellie McNeil, Clément Doire, and Doc Vaporz were ready to present Audionamix! Ellie began our presentation by introducing audio source separation and how such an ambitious task can be achieved. To many, the process of unmixing a song into its respective parts from a single audio file was completely unheard of. Next, Clément dove into the science behind our technology and explained how the algorithms are trained via neural networks and machine learning. This gave a sense of how complex the task of reverse engineering audio can be, especially when using networks trained for AI. Then, we gave a preview of our upcoming release of XTRAX STEMS, including the new feature to isolate the bass stem from a song. Ending our presentation was Doc Vaporz with his live remix using samples created via XTRAX STEMS. With the remaining time, we opened up for the Q & A portion. Dr Werner Vogels quizzed Clément on how he trains our databases and on scenarios in which the AI fails. Diego Farius asked Ellie about plans to expand our offering to include an online marketplace.

SendMusic then presented their file-sharing service that streamlines online collaborations and submissions using a simple link to manage files sent for production, A&R, radio play and more.

Lastly, Marble AR provided a look at their AR app which allows users to place AR “Marbles” anywhere in the world and connect them to any content they choose, whether it be merch for a concert, a favorite song for a favorite location, or a historical fact or memory of a specific location. The judges coined Marble AR as Pokemon Go for anything.

Ultimately, the winner would be decided by the three judges’ votes. Our moderator, Jan Maarten Hartong, first tallied the results of the audience vote where Audionamix tied with Fangage!

The moment of truth was upon us, as the judges revealed their votes. Dr Werner Vogels cast his vote for Audionamix, citing that he voted for the company he felt was most important to where the industry is heading. Suzy Ryoo was up next, casting her vote for Jambl! It all came down to Diego Farius of Amuse, who revealed he also voted for Audionamix! Our team was overwhelmed by the astounding outcome that we had been chosen as the Companies 2 Watch Winner! Thank you to Amsterdam Dance Event, Paylogic, our host, the esteemed panel of judges, and to all of our fellow finalists that shared the stage. Over the next year, we will be followed, mentored and supported by Amsterdam Dance Event, along with joining the panel of judges for next year’s Companies 2 Watch!

See you next year at ADE!

Mix Sound For Film 2019

Mix Sound For Film 2019

Mix Sound For Film 2019

For six years in a row, Mix Magazine has organized Hollywood’s premier event for the audio industry to celebrate the art of sound for motion pictures and television. Held at the world-famous Sony Pictures Studio lot in Culver City, this year’s Sound For Film & TV proved yet again to be an essential event for those wanting to learn from and network with the top sound editors, composers, mixers, and recordists working today.  

As a proud sponsor of the event, Audionamix presented the latest breakthroughs in AI source separation technology. We shared the bustling entrance hall with our friends from Sound Particles, Krotos, Avid, Genelec and more to offer hands-on demos of new and exciting developments in the sound space. At our table, Scott Esterson and Brian Code prepared to give demos of IDC Instant Dialogue Cleaner to show how one can easily and quickly reduce noise in a problematic audio recording.

As attendees arrived and grabbed their swag bags, they were treated to breakfast treats to fuel the day. Wylie Statemen, supervising sound editor for “Once Upon A Time…In Hollywood”, delivered the keynote address, kicking off an exciting day full of panels, discussions, and presentations focusing on audio for film and television.

Panels covered a wide variety of topics including production sound, immersive audio, and creative mixing techniques. Sound editors from blockbusters “Ford v. Ferrari” and “Spiderman: Far From Home” shared their processes for mixing big budget features and the challenges that come along with tackling such large projects with many moving parts.

After a quick and tasty lunch, we held a special presentation about audio AI and its implications for the future of audio source separation. Ellie McNeil set the stage with a brief background of AI and machine learning, which provided insight into how Audionamix technology can distinguish and isolate elements from a full mix. Stephen Oliver then showed examples of how our Professional Services team utilizes this technology, with clips illustrating dialogue isolation, dialogue removal, and music removal. 

We were thrilled by the turnout and response to the presentation, and the enthusiastic questions that followed.  Attendees were excited to learn how to access previously unattainable audio assets, by “unbaking the cake” and reverse engineering audio. Isolating elements from a composite mix introduces a wide array of possibilities for content owners including upmixing, remonetization, and restoration. Thank you to all the attendees of our presentation, who walked away with free Audionamix mugs and USB flash drives!

Ending the night was the red carpet walk to the open bar and Sound Reel Showcase in the Cary Grant theater, where editors presented eight minute clips of films of the year’s best film sequences in glorious Dolby Atmos. There couldn’t be a better place to experience a film in immersive audio! Amazon’s upcoming theatrical release “The Aeronauts” was the big surprise of the night, featuring Eddie Redmayne and Felicity Jones in one of the most acrophobic scenes in recent memory.

See you next year! Thank you to Sony and Mix Magazine!

The 2020 TEC Award Nominees for DJ Production Technology

The 2020 TEC Award Nominees for DJ Production Technology

The 2020 TEC Award Nominees for DJ Production Technology

Much to our excitement Audionamix has the great honor of being nominated alongside legendary brands Roland, KORG, Numark, Denon DJ, and Audio-Technica for the 2020 DJ Production Technology award! This year XTRAX STEMS 2, the automatic stem-separation application by Audionamix, stands as the only software solution nominated in this category. In this blog we take a look at the history of the TEC awards and our fellow DJ Production Technology nominees!

XTRAX Stems 2 by Audionamix

Founded by Mix Magazine in 1985, the Technical Excellence and Creativity (TEC) Award honors innovative professionals and products in the field of audio and sound production.   The category of DJ Production technology aims to recognize cutting edge products and tools specifically tailored to the DJ community.  Nominees in this category have mostly been traditional DJ tools such as turntables and mixers over the years but recently the category has expanded to include audio software as well. Also nominated in the DJ Production technology are these great products.

Audio-Technica AT-LP140XP

“This fully manual professional DJ turntable features a high-torque direct-drive motor and anti-resonant, mass-damped, die-cast aluminum platter to ensure stable, on-axis rotation at 33-1/3, 45, and 78 RPM. It is equipped with an S-shaped tonearm with height adjustment, adjustable tracking force (counterweight) and adjustable dynamic anti-skate control.”

Denon DJ SC5000M Prime

“The ‘M’ (for Motorized) is, at its core, an SC5000 Prime DJ media player, already a (DJ Mag) multi-Tech Award winning unit, but now headlined with a 7″, real vinyl and adjustable torque, motorized platter.”

KORG minilogue xd 

“In addition to emphasizing real analog sound and joy of controlling an electronic musical instrument , the minilogue xd newly adds a digital multi-engine, effects, a powered-up sequencer, and micro tuning functionality, further expanding the possibilities for sound design and performance potential.”

Numark Scratch

“Numark Scratch is a 24-bit two-channel mixer that redefines what you can do with an affordable 2-channel scratch mixer. With Scratch, you’ll be able to create and perform at a higher level than you ever thought was possible—especially with a mixer in the affordable price category.”

Roland Serato TR-SYNC

“The Serato x Roland TR-SYNC update brings the power of Roland’s iconic drum machines to your DJ setup. Simply connect your Roland TR drum machine to Serato DJ Pro and they’ll sync to the same BPM. Now you can easily add your own drum loops with the same drum sounds.”


The NAMM Show has always been one of our favorite times of year and in 2020 we look forward to it with added thrill of participating in this great event.  Please join us there for the 35th Annual TEC Awards on January 18th, 2020.

Audionamix Heads to the Top of the Class at Rock Central

Audionamix Heads to the Top of the Class at Rock Central

Audionamix Heads to the Top of the Class at Rock Central

Jeff Holden Utilizes Audio Separation Technology as Part of His Drum Curriculum

WISCONSIN – Drummer and drum instructor Jeff Holden is a life-long musician and student of music. He has recorded with legendary Milwaukee hard rock band Bender, his music has been featured in the hit film 3000 Miles to Graceland with Kevin Costner and Kurt Russell, and he was nominated for the Wisconsin Area Music Industry (WAMI) drummer of the year award. He now teaches drums for Rock Central, a non-profit music school located in Lake Geneva, Wisconsin, dedicated to enriching the quality of life for children and adults of all ages through accessible music education and experiences. As part of his drum curriculum, Holden uses Audionamix’s XTRAX STEMS to isolate, solo and mute drum tracks from popular songs in order to help guide his students in finding their musicality.

Holden uses XTRAX STEMS to mute drum tracks from mixed songs for the Rock Central students to play along with the remaining music. He found that when students played their parts without the support of the backing drum track, they were better able to feel out the groove of the song and expand their creativity by formulating their own drum riffs.

Holden also isolates the drums using XTRAX STEMS to provide students with a first-hand look at a drummer’s style. He uses this drum extraction to evaluate students’ cognitive recognition of the snare and kick drum sections—how they sound and how they affect the rhythm of a song. For younger students, Holden builds auditory development by teaching them to identify the different drum sounds and components and asking them to describe what the drums are playing in a given track.

The dedicated drum tracks also help students effectively learn and practice the drum stem without distraction from the other music. “Our most talented students were recently given a song for an audition,” says Holden. “The song was ‘Red Barchetta’ by Rush, which is a really difficult song to play. I used XTRAX STEMS to pull the drums out and gave them the musical track to play along with, and the dedicated drum track for practice. There was a part in the song where I couldn’t really decipher the specifics of the drums, so I wasn’t expecting them to be able to, either. One kid nailed it, so it definitely makes a difference.”

Prior to discovering Audionamix XTRAX STEMS, Holden purchased karaoke tracks, which were expensive and not always accurate. He also called upon instructional drum books, most of which did not feature popular songs. Holden believes that teaching songs students know and like is a more productive approach. XTRAX STEMS has given him a near-infinite number of learning tools for students, at a much lower cost, and he can use songs that are relevant to the age group that he is teaching.

Holden is working to have Rock Central purchase educational editions that will benefit all its students, especially those in the vocal performance track, who sometimes have trouble determining if they are sharp or flat. “XTRAX STEMS is a glimpse into the future of music lessons and provides students with truly boundless benefits when learning to create music,” adds Holden.

XTRAX STEMS automatically separates songs into three parts: vocals, drums and remaining music. Its simple workflow is optimized for teachers looking to separate songs into stem components for educational or practice purposes. The software is compatible with both Windows (7 SP1 – 10) and Mac (10.12 – 10.14) operating systems. New users can purchase XTRAX STEMS for $99. The AI algorithms were recently improved in the free XTRAX STEMS 2.2 update, which will provide cleaner automatic drum isolation and removal.

Audionamix’s Professional Services Provides Unique Tech for Re-monetization of Older Catalogs

Audionamix’s Professional Services Provides Unique Tech for Re-monetization of Older Catalogs

Audionamix’s Professional Services Provides Unique Tech for Re-monetization of Older Catalogs

Artificial Intelligence Algorithms Allow Film, Television and Music Companies to Revitalize Older Catalogs When the Original Multitracks and Stems are No Longer Available

Audionamix’s Professional Services Division, comprised of uniquely qualified audio engineers, functions as an extension to its clients’ post departments by directly delivering separated audio elements when the original multi-tracks or stems are no longer available. These specialized engineers utilize proprietary audio extraction technologies in order to provide advanced separations that are not easily accomplished using commercially available software. This has enabled Audionamix to help bring a number of unique projects to fruition, and its clients include the biggest content owners, creatives and technicians in the professional music, film and broadcast industries.

Audionamix’s Professional Services offerings include the following: 


which can remove music from a scene


which can isolate or remove dialogue from a scene


which can isolate a vocal performance


which can remove vocals from a song

Audionamix has provided its Music Dissociation service to several classic films so that they could be viewed alongside a live orchestra performing the score. Television series such as Baywatch were able to use the Music Dissociation service to remove previously licensed music in order to re-release original episodes. Vocal Extraction allows for the creation of virtual duets, as heard in Barry Manilow’s GRAMMY® nominated My Dream Duets album. Dialogue Isolation has allowed previously released feature films to be upmixed to 5.1 surround sound, even though the sessions were no longer available.

“In a perfect world, a client would perpetually have access to all the elements to create a full mix, whether it be a TV show, movie, album or individual song,” says Stephen Oliver, senior engineer and coordinator of Professional Services at Audionamix. “But unexpected challenges arise, and archives are often lost over the years. Our team is able to extract content from a mixed audio source using our various extraction technologies. This can include vocals, dialogue, soundtrack and other musical elements.”

For Oliver and his team, there is a hands-on approach to the way they work with each client, based on the unique needs of every project. Ultimately, the Audionamix Professional Services team is able to save its clients both time and money – such as by eliminating re-licensing music content costs – which is often essential in getting expensive projects off the ground. “Every client needs something different from us to complete their project,” continues Oliver. “We take the time to figure out how to use Audionamix’s artificial intelligence (AI)-based audio technology to best accomplish their goals.”

On a personal level, Oliver says it is especially rewarding taking something old and making it new again. “It’s like taking a part of history and bringing it back to life through new and remastered recordings and video productions,” he adds. 

Audionamix is continually developing more advanced algorithms to tackle any audio isolation project. Visit to learn more about its Professional Services Division as well as commercially available versions of its music (XTRAX STEMS 2) and speech separation (IDC: Instant Dialogue Cleaner) software solutions.

For more information, head to our Professional Services page and fill out the request more information form.