Custom Solutions

AI Dialogue and Music Separation

Get Started

Untapped Revenue

How much money is sitting on your shelves?

Streaming releases, international dubs, live film concerts, and immersive upmixes transform classic content into new revenue.

These projects aren’t possible without stems or a full session, and valuable catalogue assets are locked in their original state.

Unparalleled Technology

Remonetize classic content by separating music and dialogue – even when no session exists.

Our most advanced AI technology and tools are reserved exclusively for our Professional Services clients. Services that give you the power to maximize your revenue.

Dialogue Isolation
  • Preserve original dialogue in new, immersive upmixes.
  • Separate dialogue from unwanted music or background noise
Dialogue Removal
  • Reach new markets with foreign language dubbing
  • Automate M&E creation
Music Removal
  • Avoid expensive music relicensing fees for digital and streaming releases
  • Replace cues with cost-effective alternatives
Music Separation
  • Separate songs into vocals, drums, bass and remaining music stems
  • Create instrumentals and backing tracks

Services That Fit Your Specs

Our expert engineers offer custom, secure solutions to fit every project and budget. Our range of services are completely determined by your needs and price point.

Transfer Service API Web App Enterprise
Starts at $10 per separated stem Starts at $500 per month Starts at $500 per month Get Quote Now
Best In Class Algorithms
White Glove Support
24/7 On-Demand Processing
Easy to Use & Documented
Customizable Interface
Unlimited Separations
Local / Offline Processing Available
Discounted Post-Processing Services

Untapped Possibilities with Enterprise Licensing

Enterprise licensing allows unlimited separation processing for your entire organization at a flat annual rate, meaning you’re ready to take on any challenge. Fully customizable and built to specifications your infrastructure needs. The enterprise licensing solution comes ready and secure with customizable options to met your security needs:

On-site Server

A local server hosted in your facility, with no reliance on cloud processing.

Cloud-based Integration

Built into your cloud-based asset management system (Azure, AWS, etc).

Web App

A secure, browser-based separation interface to and from our servers.

"We provided the Audionamix team with a conformed English composite and an English dialogue stem, plus the music stem conformed and phased separately for each of the foreign languages. They delivered extracted foreign language dialog, with unique attention to the challenges that varied from language to language.”

John Yanez
Supervisor of Archival Mastering at Warner Bros.

“iFit uses Audionamix’s dialogue removal service; extracting dialogue while leaving natural sound on our trainer-led outdoor and studio interactive workouts. We have been thrilled with the results, allowing us to dub the dialogue into multiple languages while maintaining natural sound, giving our foreign language customers a more robust and authentic audio experience.”

Carly Sorensen
Head of Production, iFit

“Audionamix was an integral part of our post-production team. They were there for us every step of the way with fast turn-around, meticulous attention to detail and excellent communication. We will definitely work together again and look forward to it!”

Michael Orendy
Manager, Music Clearance & Licensing

Success Stories

Case Studies

Baywatch Remastered
Music Removal
Barry Manilow – 'My Dream Duets'
Vocal Extraction
iFit
Dialogue Removal for Localization
Kubrick by Kubrick
Dialogue Isolation and Restoration

Past Clients

Blade Runner

Music Removal

Star Trek: The Next Generation

Music Removal

Barbara Streisand – 'Partners'

Vocal Extraction

Beverly Hills 90210

Music Removal

Blues Brothers

Dialogue Isolation

Charmed

Music Removal

Cheers

Music Removal

Natalie Cole – 'Acércate Más' (ft. Nat King Cole)

Vocal Extraction

Dial 'M' for Murder

Music Removal

Donna Summer - 'Love to Love You Donna'

Vocal Extraction

Eastbound and Down

Music Removal

Edith Piaf – 'La en Rose'

Vocal Extraction

Family Ties

Music Removal

Remington Steel

Music Removal

Inception

Stem Creation

Knight Rider

Music Removal

Laverne & Shirley

Music Removal

Melrose Place

Music Removal

Mickey Mouse – Get a House!

Dialogue Isolation

West Side Story

Music Removal

Verve Records 'Verve Remixed The First Ladies'

Vocal Extraction

Psycho

Stem Creation

Rod Stewart – 'What Are You Doing New Year’s Eve? (ft. Ella Fitzgerald)

Vocal Extraction

Sherlock Holmes: A Game of Shadows

Vocal Extraction

Sucker Punch

Instrumental Creation

Supernatural

Music Removal

Sylvester and Tweety

Dialogue Isolation / Vocal Extraction

Hearing is Believing

You’re invited to experience the power of separation processing through our online portal and guided demonstration with our experts.

Baywatch Remastered

Music Dissociation

While preparing a remastered HD version of Baywatch for streaming, Warner Bros and Fremantle realized that the cost to re-license many of the songs from the original series would make the entire project cost-prohibitive.

To make this re-release possible, it was decided to replace over 350 songs with new, more affordable music.

For the foreign versions of the show, however, separate audio stems were no longer available. The only audio available was the full master track with music, effects and dialogue elements combined into one, making it seemingly impossible to remove and replace just the music.

Audionamix processed over 400 clips from the show’s nine seasons, allowing for the replacement of music in the French, Spanish, Italian, and German versions of the show, and making the re-release possible.

“We provided the Audionamix team with a conformed English composite and an English dialogue stem, plus the music stem conformed and phased separately for each of the foreign languages. They delivered extracted foreign language dialog, with unique attention to the challenges that varied from language to language.”

John Yanez

Supervisor of Archival Mastering at Warner Bros.

Barry Manilow – My Dream Duets

Vocal Extraction

We are very excited to announce that Barry Manilow’s latest album, My Dream Duets, is now available to add to your collection! We at Audionamix are extremely proud to have been a part of the creative process that made this album a reality, and we’re here to share a taste of what makes Barry’s ‘Dream Duets’ so very unique.
“Through the miracle of modern technology, the original vocal tracks for each guest artist on MY DREAM DUETS have been extracted from their original source recordings, allowing Manilow to re-orchestrate the arrangements, record new musical tracks, and then transport the guest vocals into vibrant new settings. In this way, he not only pays homage to his duet partners but, he also brings them into the modern era by transforming them into recordings that are instantly familiar yet refreshingly new. From cherished idols like Judy Garland and Louis Armstrong to contemporary icons like Whitney Houston and John Denver, they have all joined Barry in his “virtual recording studio.”

Verve Music Group

iFit

Dialogue Removal for Localization

iFit provides interactive personal training on home exercise equipment. Users can view trainers on screen, and their equipment settings are tailored in real-time to match what’s happening in the video. In the videos, trainers give verbal encouragement and instruction to the user. These videos were recorded using only a single microphone, which delivers the audio of both the instructor’s voice and the sound of their environment. iFit wanted to dub these videos into different languages, while retaining the natural background sound.

Audionamix used our Dialogue Removal service to strip the original speech from the iFit videos, leaving the background ambience. iFit was able to repurpose these recordings and dub them into multiple languages, keeping the original sound of the environment.

“iFit uses Audionamix’s dialogue removal service; extracting dialogue while leaving natural sound on our trainer-led outdoor and studio interactive workouts. We have been thrilled with the results, allowing us to dub the dialogue into multiple languages while maintaining natural sound, giving our foreign language customers a more robust and authentic audio experience.”

Carly Sorensen

Head of Production, iFit

About iFit

iFit pioneered interactive connected fitness and was issued its first of many patents in 1999. Founded with the belief that the majority of consumers would benefit from an interactive personal training experience at home, iFit’s trainer-led streaming workouts are now trusted by millions of consumers around the globe.

iFit offers workout options for every fitness level and interest, from bodyweight training, HIIT cardio workouts and yoga, to connected fitness workouts on NordicTrack and ProForm home equipment, and Freemotion equipment for commercial facilities. Patented interactive technology allows iFit Trainers to create highly personalized workouts for iFit members and Live Adjust™ the user’s incline, speed and resistance instantly during the workout to create the perfect workout for every fitness level. iFit interactive workouts are available on treadmills, stationary bikes, ellipticals, rowers, strength machines, and the iFit app for a range of exercise accessories.

iFit is owned by ICON Health & Fitness, the global leader in home, commercial and connected fitness and holds more than 275 fitness patents, with 138 pending. iFit workouts are available in English, Mandarin Chinese, Spanish, Portuguese, French and German with more languages planned for 2020.

Kubrick by Kubrick

Dialogue Isolation and Restoration

The documentary “Kubrick by Kubrick” reveals previously unheard conversations between Stanley Kubrick and Michel Ciment, a French film critic who recorded their discussions over the course of 20 years.

Because these recordings were made in varying locations, they had differing background noise, quality, and reverberation. In some, they were in a restaurant with clanking silverware and glasses; in others, the voices were distant or distorted.

As these sonic differences distracted from the content, production company Temps Noir asked Audionamix to help make the recordings sound as similar as possible.

Audionamix used our advanced dialogue isolation technology to separate the speech from the background noise and reduce roominess. Then our engineers carefully adjusted the sound of each clip to create a more consistent sonic experience for the viewer.