AudioShake Blog
Get Started
How to Use Real-Time Music Removal in Live Broadcasts and Streaming Workflows
In live environments, like broadcast, sports, or streams, AudioShake can isolate music to avoid copyright infringement.
Introducing AudioShake Speech Recovery for Noisy and Low-Resolution Audio
A new suite of models from AudioShake recovers intelligible speech from degraded recordings, without synthetic processin
AudioShake Copyright Compliance System: Music Detection, Identification, Removal, & Compliance
AudioShake's Copyright Compliance System can detect, remove, and identify commercial music for cue sheets.
AudioShake at NAB 2026: Real-Time Dialogue Isolation, ESPN, and What Broadcast Is Asking For Next
Inside AudioShake's NAB 2026: real-time dialogue isolation at 11ms, the ESPN partnership, and broadcast partner demos.
How ESPN Uses AI Audio Separation to Unlock Sports Content for Rights-Cleared Distribution on Streaming, Digital, and Social Media
From archival recovery to modern media workflows, ESPN uses AudioShake to make its content usable and rights-compliant.
LANDR Upgrades Its Stems Plugin with AudioShake’s Next-Generation Separation — Now Featuring Piano and Guitar
This update brings industry-leading vocals, drums, bass, piano, guitar, and other separation directly to producers' DAWs
AudioShake Debuts Dialogue RT: The First AI Dialogue Isolation Model Built for Live Broadcast
With 11ms of latency, DialogueRT is the first to meet the threshold required for broadcast, captioning, and on-air.
AudioShake Releases Five New Music Instrument Stems
AudioShake introduces new separation models for lead vocals, backing vocals, electric guitar, acoustic guitar, keys.
Four Voices We Helped Bring to Life in 2025
From Maria Callas in an Oscar-nominated film to an ALS patient speaking again—the stories behind 2025 at AudioShake.
The Year Audio Became AI's Next Frontier
In 2025, AudioShake's audio separation powered Oscar films, helped ALS patients, and earned AWS keynote recognition.
The Most Accurate Lyric Transcription Technology: How AudioShake Achieved State-of-the-Art Results
AudioShake holds SOTA benchmarks for lyric transcription + alignment. How we achieve ~90% accuracy + 5x faster speeds.
From Startup Competition Winners to Keynote Feature, AudioShake Returns to AWS re:Invent
AWS CEO Matt Garman spotlighted AudioShake at re:Invent 2025 as we showed how audio separation solves audio problems in
Meta Tested the Leading Audio Separation Models. AudioShake Came Out on Top.
Meta's 2024 audio separation benchmarks rank AudioShake #1 for perceptual quality among all discriminative models tested
Targeted vs. Generative Audio Separation: Reflections on Meta’s SAM Audio Benchmark Results
The release of Meta's segmented audio model (SAM) and how it differs from targeted sound separation models
How CrunchLabs Uses AudioShake to Localize and Repurpose Viral Science Videos
Mark Rober’s CrunchLabs uses AudioShake’s music removal and sound separation tools to localize, remix, and clear content
AudioShake Launches Real-Time Music Removal SDK for Broadcasters, Sports, Film & TV
Real-time music detection and removal helps broadcasters, sports leagues, and studios with copyright compliance.
AI Voice Isolator for Clean Dialogue in Film, TV, and Localization
AudioShake’s newest Dialogue model isolates even cleaner speech from music and effects
AudioShake Launches Effects Separation to Unlock Post-Production Audio
Isolate ambient and foley sounds from dialogue and music for post-production, localization, restoration, and more.
Making Sound as Flexible as Text: How AudioShake Raised $14M to Unlock the World’s Audio
AudioShake announces a $14M Series A backed by Shine Capital, Thomson Reuters Ventures, and Origin Ventures
AudioShake Debuts New Instrument Separation Models
New models for drums, bass, piano, guitar, winds, strings, and other for audio pros and indie artists
From One-Click Audio to Professional Creative Workflows: Why Stem Separation Matters in the Age of Generative AI
Learn how stem separation restores control in gen AI content—powering workflows in music, videos, podcasting, and more.
Leveraging your content for structured audio data
Train custom models with real, separated audio—music, speech, effects, and more—using your own content.
How to Choose the Best Vocal Stem Separation Tool
Expert advice on how to evaluate, test, and understand whats make for the best vocal isolation technology.
AI Helps Musician Restore Vintage Irish Fiddle Music
How AudioShake’s advanced AI helped restore Michael Coleman’s 20th-century fiddle recordings and unlock new creative pos
Unlock Real-Time Sound with AudioShake SDK
AudioShake’s new SDK lets you harness real-time sound separation for apps. For remixing, education, Voice AI, and more.
How to Edit Podcasts with Multiple Speakers—Fast
Learn how podcast editors streamline editing with multi-speaker separation—no more scrubbing through messy, overlapping
Licensing Derivative Works: How AI Is Opening the Door to Legal Remixes and Edits
How AI stem separation tools simplify the licensing process for derivative works, enabling legal remixes and samples at
Andrea Bocelli and Luciano Pavarotti Sing Together Once More
How stems made a 2024 duet between Bocelli and the late Pavarotti possible for both a live audience and Dolby Atmos mix.
AudioShake Voice Model Achieves Highest-Quality, State-of-the-Art Benchmark
AudioShake unveils its highest-quality vocal isolation to date, trusted by top labels, artists, and studios.
New Models from AudioShake to Isolate Strings Instruments + More
Our new model cleanly separates string instruments in any mix—giving producers, editors, and creators more control
Mix Live Albums and Master Live Performances with Stems
Take live recordings and mix them into full albums with the power of stem separation.
Bridging Voice Partners with AudioShake to Empower ALS Patients Through Voice Isolation
Discover how Bridging Voice used AudioShake’s voice isolation tools to help ALS patients reclaim their voices.
Multi-Speaker Separation: The Future of AI-Powered Speech Isolation
Discover uses and opportunities for the latest sound separation breakthrough, multi-speaker separation.
Restoring the Voices of Patients with ALS
Voice cloning is restoring speech for ALS patients. Learn how AudioShake’s tech isolates voices for life-changing impact
Streamlining Podcast Production: Solutions to Common Audio Challenges
How AudioShake’s dialogue and multi-voice separation can help podcasters tackle messy audio issues.
Pushing the Boundaries of Speech AI: Solving High-Fidelity Multi-Speaker Separation
AudioShake’s hi-fi multi-speaker separation isolates voices in film, TV, and AI workflows. Now available via web + API.
Introducing Multi-Speaker Separation from AudioShake
AudioShake’s Multi-Speaker separation isolates voices into distinct tracks, making audio cleaner and more editable.
AI Was In More Oscar-Nominated Films Than You Think
In an era where AI is often blamed for destroying creative work, here's how it's quietly empowering artists.
Remix Your Favorite Tracks with AI: Top Tools for Creators
AudioShake’s AI stem separation empowers artists to remix, create, and stay copyright-compliant for music projects.
Why Music Leaders Are Betting on Stems and Lyrics—and Why You Should Too
Integrating Stem Separation Across Entire Catalogs to Unlock New Revenue and Creative Opportunities for Disney, Downtown
Stems, Eclipsa Audio, and the Rise of Immersive Audio: What to Know
Explore how Eclipsa Audio and AI stem separation solve common issues in spatial audio, offering a flexible solution for
AudioShake Isolations Bring Maria Callas’ Voice to Life in Maria
Warner Classics and partner Maria Callas Estate used stems to isolate her voice to perfect the biopic’s musical elements
A Year in Audio – AudioShake’s 2024 Year in Review
AudioShake's 2024 impact spanned film, sports, TV, and music, empowering artists and creators alike.
AudioShake Wins AWS re:Invent’s Unicorn Tank Startup Competition
AudioShake took home the top prize, recognizing the growing importance of audio infrastructure tools for developers
Solidarity Studios: Stems Serve Emerging & Global Artists
Chicago artists remix global sounds with AudioShake stems at Shake and Bake, blending tradition and modern creativity.
AudioShake Wins LaLiga’s EA Sports Startup Competition: A New Era for Sports Broadcast Audio
AudioShake wins LaLiga's EA Sports Startup Competition, revolutionizing sports audio with AI-driven sound separation.
AudioShake Stems Help Remaster Whitesnake's "Time and Again"
Whitesnake celebrates four decades with box set and vinyl remixes & remasters, thanks to AudioShake’s cutting-edge tech
Breaking Down Audio Barriers in the Sports World
How AudioShake's Sound Separation is Unlocking New Possibilities for Sports and Media Content
How to Get Stems from Any Song: A Practical Guide
The Ultimate Guide for Using AudioShake for Vocal Removal, Karaoke Making, and Instrument Isolation
How do you measure quality in stem separation?
The limitations of SDR scores and the importance of perceptual metrics in sound separation.
8 Ways to Use AI Lyrics to Streamline Your Workflow and Boost Revenue
How AI lyric transcription and time-stamping services help labels and artists improve workflows, revenue, and more.
Four Novel Uses for Advanced Lyric Transcription in the Future of Music Experiences
The impact of AI lyric transcription and alignment on the future of music experiences
"Lyrics transcription for humans": revisiting AudioShake's transcription benchmark
New results from lyrics transcription benchmark showcase AudioShake's state-of-the-art transcription service
Disney Music Group and AudioShake set to collaborate on instrument stem separation technology to add new value for iconic recordings and lyrics
Disney Music Group and AudioShake announced their collaboration to open up Disney’s catalog of music to new uses
How to: Use AudioShake to improve accuracy in localization, transcription, and captioning workflows on AWS
The integration enables customers to leverage multiple AWS services to efficiently process audio assets for distribution
Disney Accelerator Demo Day debuts AudioShake collaborators and use cases
AudioShake expands its deal with Disney Music Group and explores collaborations with Walt Disney Studios, ESPN, and more
New AudioShake models double in transcription accuracy, over 5X in speed
Our new lyric transcription and alignment models nearly double accuracy, and are over 5X faster.
Stems for a wide range of guitar sounds
Latest AudioShake stems pick up different guitar styles, genres, and pedal effects with even better clarity and tone.
How broadcasters can put audio to work (NAB PILOT)
How broadcasters can use stem separation for localization, copyright compliance, and emerging content formats.
Launching Dialogue and Music/Effects Separation on Live
AudioShake’s separation technology for film, television, and content teams comes to AudioShake Live and Indie.
Stems help create something “new” from existing catalogs (A2IM)
How labels can use AudioShake stems to maximize creative, revenue, and engagement opportunities
Is Generative Music Really the Next Napster? (Trapital)
Originally published on Trapital, AudioShake's CEO writes why it’s going to take a lot more than a text prompt to kill music as we know it
AudioShake joins The Disney Accelerator
The business development program brings in innovative companies to gain guidance from senior leadership on the opportunities for its technology.
What makes for higher quality piano stems?
How AudioShake’s piano stems compare to open-source models, including findings from AudioLabs.
Latest models, higher quality stems
AudioShake releases its latest AI stem separation models with improved quality to all instrument stems.
A Year in Audio AI: More Remasters, Interactivity, and a Global Focus in 2024
Winner of TIME Best Inventions, AudioShake stems made their way into projects for De La Soul, SZA, Nina Simone, Doctor Who, Sia, and more.
AudioShake wins Sony Demixing 2023
AudioShake's AI models earn the highest overall SDR scores in Sony challenge across music and film separation.
Tuney and AudioShake team up for the first-ever, AI-powered EP produced by Boi-1da.
BACARDI’s 'Music Liberates Music' program drops new EP: The Concept A.I.bum
Art Official: AI & De La Soul’s Long-Awaited Digital Release
AudioShake stems helped re-master De La Soul’s first six albums in Dolby Atmos for Reservoir Media
Algoriddim debuts AudioShake’s real-time stem separation on djay Pro: the #1 software for performing DJs
For the first time, AudioShake’s industry-leading music separation tech is made available in real-time, on device.
Mastering unreleased performances of the Tomasz Stanko Quintet
Astigmatic Records uses AI stems to master 1970’s broadcast of revered Polish trumpeter
New benchmark for HQ transcriptions
AudioShake paper sets a new direction for high-quality lyrics transcription with a new evaluation benchmark.
Lyric Videos to Help Artists Reach Global Audiences
Downtown Artist & Label Services harnesses LyricSync to create localized marketing assets for Lala Sadii
AudioShake named a TIME Best Invention of 2023
TIME selected AudioShake as one of 2023's inventions changing how we live, work, play, and think about what’s possible.
Introducing Nina Simone’s Debut Album to New Audiences
BMG and Nina Simone’s estate partner with AudioShake on a spatial mix of Little Girl Blue, mixed by Immersive Mixers.
A 1977 song lands in a 20th Century Fox trailer
Wise Music Creative taps AudioShake to land a sync deal for the trailer of 20th Century Fox picture “Amsterdam”
AudioShake Unveils AI Lyric Transcription & Alignment
LyricSync creates clean, time-stamped lyric transcriptions with high accuracy using AudioShake's vocal isolation tech.
Doubling Down on Dubbing
AudioShake helps unblock a long-standing challenge in dubbing, transcription, and captioning technology with new model.
Opening Up The Libertines’ Catalog for Remasters
Using AI stem separation to master a 20th anniversary album for The Libertines with Rough Trade Records.
Mixing the Fast X Soundtrack with AI Stems
Immersive Mixers worked with AudioShake stems to mix the latest movie’s soundtrack in Dolby Atmos.
Building Spatial Formats with AI Stems
The rise of spatial audio and how audio engineers build immersive soundscapes with the help of stems.
Using Stems for Customized, Interactive Music Experiences
Emerging interactive audio formats present new opportunities and new life for audio across fitness, gaming, social apps, and more.
Launching Auto-Instrumental for Sync Licensing
Chordal and AudioShake team up to launch a first-of-it-kind tool for music supervisors and sync licensors, Auto-Instrumental.
Stems for Wind Instruments
AudioShake launches stem support for wind instruments, tackling an industry-wide challenge of isolating these complex tones.
A live broadcast of a jazz legend is brought to life with AI
50 years later, Oscar Peterson’s “Live in Zurich” performance makes its way to digital, vinyl, and CD.
Dubbing Doctor Who into German with AI
Pandastorm Pictures turned to AudioShake to master and dub the original 1975 BBC series.
Stems and the Growing Sync Industry
How labels and artists can use AI to create stems and land sync deals.
The Future of Audio is Interactive
New tools will make editing and transforming audio as easy as photo or video, and more from Jessica Powell’s talk at CODE conference 2022.
Introducing AudioShake Indie
AudioShake Indie, a platform to help indie labels, artists, and producers open up their recordings to new revenue streams
Shred with Green Day, with some help from AudioShake
Green Day's Billie Joe asks fans to play along to "2000 Light Years Away" on TikTok
Houston Kendrick x AudioShake: The World’s First AI Stem Remix Contest!
Indie artist Houston Kendrick has partnered with AudioShake to run the world’s first-ever remix contest powered by AI stems.
AudioShake wins Sony Demixing Challenge
Sony ran a “Demixing Challenge” to find the world’s best song separation technology…and we won.
Launching AudioShake Live
AudioShake Live is a platform that lets labels, publishers, and their partners bring our A.I. technology “in-house,” and create instrumentals and stems on demand.
\ \ How to Use Real-Time Music Removal in Live Broadcasts and Streaming Workflows \ \ In live environments, like broadcast, sports, or streams, AudioShake can isolate music to avoid copyright infringement.](/content/post/how-to-use-real-time-music-removal-in-live-broadcasts-and-streaming-workflows/index.html)
\ \ AudioShake Copyright Compliance System: Music Detection, Identification, Removal, & Compliance \ \ AudioShake's Copyright Compliance System can detect, remove, and identify commercial music for cue sheets.](/content/post/audioshake-copyright-compliance-system-music-detection-identification-removal-compliance/index.html)
\ \ AudioShake at NAB 2026: Real-Time Dialogue Isolation, ESPN, and What Broadcast Is Asking For Next \ \ Inside AudioShake's NAB 2026: real-time dialogue isolation at 11ms, the ESPN partnership, and broadcast partner demos.](/content/post/audioshake-at-nab-2026-real-time-dialogue-isolation-espn-and-what-broadcast-is-asking-for-next/index.html)
\ \ How ESPN Uses AI Audio Separation to Unlock Sports Content for Rights-Cleared Distribution on Streaming, Digital, and Social Media \ \ From archival recovery to modern media workflows, ESPN uses AudioShake to make its content usable and rights-compliant.](/content/post/how-espn-uses-ai-audio-separation-to-unlock-sports-content-for-rights-cleared-distribution-on-streaming-digital-and-social-media/index.html)
\ \ LANDR Upgrades Its Stems Plugin with AudioShake’s Next-Generation Separation — Now Featuring Piano and Guitar \ \ This update brings industry-leading vocals, drums, bass, piano, guitar, and other separation directly to producers' DAWs](/content/post/landr-upgrades-its-stems-plugin-with-audioshakes-next-generation-separation----now-featuring-piano-and-guitar/index.html)
\ \ AudioShake Debuts Dialogue RT: The First AI Dialogue Isolation Model Built for Live Broadcast \ \ With 11ms of latency, DialogueRT is the first to meet the threshold required for broadcast, captioning, and on-air.](/content/post/dialogue-rt-live-dialogue-isolation-launch/index.html)
\ \ AudioShake Releases Five New Music Instrument Stems \ \ AudioShake introduces new separation models for lead vocals, backing vocals, electric guitar, acoustic guitar, keys.](/content/post/audioshake-releases-five-new-music-instrument-stems/index.html)
\ \ Four Voices We Helped Bring to Life in 2025 \ \ From Maria Callas in an Oscar-nominated film to an ALS patient speaking again—the stories behind 2025 at AudioShake.](/content/post/4-voices-we-helped-bring-to-life-in-20254/index.html)
\ \ The Year Audio Became AI's Next Frontier \ \ In 2025, AudioShake's audio separation powered Oscar films, helped ALS patients, and earned AWS keynote recognition.](/content/post/the-year-audio-became-ais-next-frontier/index.html)
\ \ The Most Accurate Lyric Transcription Technology: How AudioShake Achieved State-of-the-Art Results \ \ AudioShake holds SOTA benchmarks for lyric transcription + alignment. How we achieve ~90% accuracy + 5x faster speeds.](/content/post/the-most-accurate-lyric-transcription-technology-how-audioshake-achieved-state-of-the-art-results/index.html)
\ \ From Startup Competition Winners to Keynote Feature, AudioShake Returns to AWS re:Invent \ \ AWS CEO Matt Garman spotlighted AudioShake at re:Invent 2025 as we showed how audio separation solves audio problems in](/content/post/from-startup-competition-winners-to-keynote-feature-audioshake-returns-to-aws-re-invent/index.html)
\ \ Meta Tested the Leading Audio Separation Models. AudioShake Came Out on Top. \ \ Meta's 2024 audio separation benchmarks rank AudioShake #1 for perceptual quality among all discriminative models tested](/content/post/meta-tested-the-leading-audio-separation-models-audioshake-came-out-on-top/index.html)
\ \ Targeted vs. Generative Audio Separation: Reflections on Meta’s SAM Audio Benchmark Results \ \ The release of Meta's segmented audio model (SAM) and how it differs from targeted sound separation models](/content/post/targeted-vs-generative-audio-separation-reflections-on-metas-sam-benchmark-results/index.html)
\ \ How CrunchLabs Uses AudioShake to Localize and Repurpose Viral Science Videos \ \ Mark Rober’s CrunchLabs uses AudioShake’s music removal and sound separation tools to localize, remix, and clear content](/content/post/how-crunchlabs-uses-audioshake-to-localize-and-repurpose-viral-science-videos/index.html)
\ \ AudioShake Launches Real-Time Music Removal SDK for Broadcasters, Sports, Film & TV \ \ Real-time music detection and removal helps broadcasters, sports leagues, and studios with copyright compliance.](/content/post/audioshake-launches-real-time-music-removal-sdk-for-broadcasters-sports-film-tv/index.html)
\ \ AI Voice Isolator for Clean Dialogue in Film, TV, and Localization \ \ AudioShake’s newest Dialogue model isolates even cleaner speech from music and effects](/content/post/audioshake-launches-latest-dialogue-separation-model/index.html)
\ \ AudioShake Launches Effects Separation to Unlock Post-Production Audio \ \ Isolate ambient and foley sounds from dialogue and music for post-production, localization, restoration, and more.](/content/post/audioshake-launches-effects-separation-to-unlock-post-production-audio/index.html)
\ \ Making Sound as Flexible as Text: How AudioShake Raised $14M to Unlock the World’s Audio \ \ AudioShake announces a $14M Series A backed by Shine Capital, Thomson Reuters Ventures, and Origin Ventures](/content/post/series-a-round-raise-14-million-shinecapital-origin-thomson-reuters/index.html)
\ \ AudioShake Debuts New Instrument Separation Models \ \ New models for drums, bass, piano, guitar, winds, strings, and other for audio pros and indie artists](/content/post/audioshake-debuts-new-instrument-separation-models/index.html)
\ \ From One-Click Audio to Professional Creative Workflows: Why Stem Separation Matters in the Age of Generative AI \ \ Learn how stem separation restores control in gen AI content—powering workflows in music, videos, podcasting, and more.](/content/post/from-one-click-audio-to-professional-creative-workflows-why-stem-separation-matters-in-the-age-of-generative-ai-q8wjb/index.html)
\ \ How to Choose the Best Vocal Stem Separation Tool \ \ Expert advice on how to evaluate, test, and understand whats make for the best vocal isolation technology.](/content/post/how-to-choose-the-best-vocal-stem-separation-tool/index.html)
\ \ AI Helps Musician Restore Vintage Irish Fiddle Music \ \ How AudioShake’s advanced AI helped restore Michael Coleman’s 20th-century fiddle recordings and unlock new creative pos](/content/post/ai-helps-musician-restore-vintage-irish-fiddle-music/index.html)
\ \ Unlock Real-Time Sound with AudioShake SDK \ \ AudioShake’s new SDK lets you harness real-time sound separation for apps. For remixing, education, Voice AI, and more.](/content/post/unlock-real-time-sound-with-audioshake-sdk/index.html)
\ \ How to Edit Podcasts with Multiple Speakers—Fast \ \ Learn how podcast editors streamline editing with multi-speaker separation—no more scrubbing through messy, overlapping](/content/post/how-to-edit-podcasts-with-multiple-speakers--fast/index.html)
\ \ Licensing Derivative Works: How AI Is Opening the Door to Legal Remixes and Edits \ \ How AI stem separation tools simplify the licensing process for derivative works, enabling legal remixes and samples at](/content/post/licensing-derivative-works-how-ai-is-opening-the-door-to-legal-remixes-and-edits/index.html)
\ \ Andrea Bocelli and Luciano Pavarotti Sing Together Once More \ \ How stems made a 2024 duet between Bocelli and the late Pavarotti possible for both a live audience and Dolby Atmos mix.](/content/post/andrea-bocelli-and-luciano-pavarotti-sing-together-once-more/index.html)
\ \ AudioShake Voice Model Achieves Highest-Quality, State-of-the-Art Benchmark \ \ AudioShake unveils its highest-quality vocal isolation to date, trusted by top labels, artists, and studios.](/content/post/audioshake-voice-model-achieves-highest-quality-state-of-the-art-benchmark/index.html)
\ \ New Models from AudioShake to Isolate Strings Instruments + More \ \ Our new model cleanly separates string instruments in any mix—giving producers, editors, and creators more control](/content/post/new-models-from-audioshake-to-isolate-strings-instruments-more/index.html)
\ \ Mix Live Albums and Master Live Performances with Stems \ \ Take live recordings and mix them into full albums with the power of stem separation.](/content/post/mix-live-albums-and-master-live-performances-with-stems/index.html)
\ \ Bridging Voice Partners with AudioShake to Empower ALS Patients Through Voice Isolation \ \ Discover how Bridging Voice used AudioShake’s voice isolation tools to help ALS patients reclaim their voices.](/content/post/bridging-voice-partners-with-audioshake-to-empower-als-patients-through-voice-isolation/index.html)
\ \ Multi-Speaker Separation: The Future of AI-Powered Speech Isolation \ \ Discover uses and opportunities for the latest sound separation breakthrough, multi-speaker separation.](/content/post/multi-speaker-separation-the-future-of-ai-powered-speech-isolation/index.html)
\ \ Restoring the Voices of Patients with ALS \ \ Voice cloning is restoring speech for ALS patients. Learn how AudioShake’s tech isolates voices for life-changing impact](/content/post/restoring-the-voices-of-patients-with-als/index.html)
\ \ Streamlining Podcast Production: Solutions to Common Audio Challenges \ \ How AudioShake’s dialogue and multi-voice separation can help podcasters tackle messy audio issues.](/content/post/streamlining-podcast-production-solutions-to-common-audio-challenges/index.html)
\ \ Pushing the Boundaries of Speech AI: Solving High-Fidelity Multi-Speaker Separation \ \ AudioShake’s hi-fi multi-speaker separation isolates voices in film, TV, and AI workflows. Now available via web + API.](/content/post/pushing-the-boundaries-of-speech-ai-solving-high-fidelity-multi-speaker-separation/index.html)
\ \ Introducing Multi-Speaker Separation from AudioShake \ \ AudioShake’s Multi-Speaker separation isolates voices into distinct tracks, making audio cleaner and more editable.](/content/post/introducing-multi-speaker-separation-from-audioshake/index.html)
\ \ AI Was In More Oscar-Nominated Films Than You Think \ \ In an era where AI is often blamed for destroying creative work, here's how it's quietly empowering artists.](/content/post/ai-was-in-more-oscar-nominated-films-than-you-think/index.html)
\ \ Remix Your Favorite Tracks with AI: Top Tools for Creators \ \ AudioShake’s AI stem separation empowers artists to remix, create, and stay copyright-compliant for music projects.](/content/post/remix-your-favorite-tracks-with-ai-top-tools-for-creators/index.html)
\ \ Why Music Leaders Are Betting on Stems and Lyrics—and Why You Should Too \ \ Integrating Stem Separation Across Entire Catalogs to Unlock New Revenue and Creative Opportunities for Disney, Downtown](/content/post/why-music-leaders-are-betting-on-stems-and-lyrics--and-why-you-should-too/index.html)
\ \ Stems, Eclipsa Audio, and the Rise of Immersive Audio: What to Know \ \ Explore how Eclipsa Audio and AI stem separation solve common issues in spatial audio, offering a flexible solution for](/content/post/stems-eclipsa-audio-and-the-rise-of-immersive-audio-what-to-know/index.html)
\ \ AudioShake Isolations Bring Maria Callas’ Voice to Life in Maria \ \ Warner Classics and partner Maria Callas Estate used stems to isolate her voice to perfect the biopic’s musical elements](/content/post/audioshake-isolations-bring-maria-callas-voice-to-life-in-netflix-film-maria/index.html)
\ \ A Year in Audio – AudioShake’s 2024 Year in Review \ \ AudioShake's 2024 impact spanned film, sports, TV, and music, empowering artists and creators alike.](/content/post/a-year-in-audio---audioshakes-2024-year-in-review/index.html)
\ \ AudioShake Wins AWS re:Invent’s Unicorn Tank Startup Competition \ \ AudioShake took home the top prize, recognizing the growing importance of audio infrastructure tools for developers](/content/post/audioshake-wins-aws-re-invents-unicorn-tank-startup-competition/index.html)
\ \ Solidarity Studios: Stems Serve Emerging & Global Artists \ \ Chicago artists remix global sounds with AudioShake stems at Shake and Bake, blending tradition and modern creativity.](/content/post/solidarity-studios-stems-serve-emerging-global-artists/index.html)
\ \ AudioShake Wins LaLiga’s EA Sports Startup Competition: A New Era for Sports Broadcast Audio \ \ AudioShake wins LaLiga's EA Sports Startup Competition, revolutionizing sports audio with AI-driven sound separation.](/content/post/audioshake-wins-laligas-ea-sports-startup-competition-a-new-era-for-sports-broadcast-audio/index.html)
\ \ AudioShake Stems Help Remaster Whitesnake's "Time and Again" \ \ Whitesnake celebrates four decades with box set and vinyl remixes & remasters, thanks to AudioShake’s cutting-edge tech](/content/post/whitesnake-celebrates-four-decades-with-box-set-and-vinyl-remixes-remasters-thanks-to-audioshakes-cutting-edge-technology/index.html)
\ \ Breaking Down Audio Barriers in the Sports World \ \ How AudioShake's Sound Separation is Unlocking New Possibilities for Sports and Media Content](/content/post/breaking-down-audio-barriers-in-the-sports-world/index.html)
\ \ How to Get Stems from Any Song: A Practical Guide \ \ The Ultimate Guide for Using AudioShake for Vocal Removal, Karaoke Making, and Instrument Isolation](/content/post/how-to-separate-your-music-into-stems/index.html)
\ \ How do you measure quality in stem separation? \ \ The limitations of SDR scores and the importance of perceptual metrics in sound separation.](/content/post/what-is-an-sdr-score/index.html)
\ \ 8 Ways to Use AI Lyrics to Streamline Your Workflow and Boost Revenue \ \ How AI lyric transcription and time-stamping services help labels and artists improve workflows, revenue, and more.](/content/post/eight-ways-labels-and-artists-can-use-automated-lyric-transcription-to-streamline-their-workflow-and-boost-revenue/index.html)
\ \ Four Novel Uses for Advanced Lyric Transcription in the Future of Music Experiences \ \ The impact of AI lyric transcription and alignment on the future of music experiences](/content/post/four-novel-uses-for-advanced-lyric-transcription-in-the-future-of-music-experiences/index.html)
\ \ "Lyrics transcription for humans": revisiting AudioShake's transcription benchmark \ \ New results from lyrics transcription benchmark showcase AudioShake's state-of-the-art transcription service](/content/post/lyrics-transcription-for-humans-revisiting-audioshakes-transcription-benchmark/index.html)
\ \ How to: Use AudioShake to improve accuracy in localization, transcription, and captioning workflows on AWS \ \ The integration enables customers to leverage multiple AWS services to efficiently process audio assets for distribution](/content/post/how-to-use-audioshake-to-improve-accuracy-in-localization-transcription-and-captioning-workflows-on-aws/index.html)
\ \ Disney Accelerator Demo Day debuts AudioShake collaborators and use cases \ \ AudioShake expands its deal with Disney Music Group and explores collaborations with Walt Disney Studios, ESPN, and more](/content/post/walt-disney-studios-accelerator-demo-day-audioshake/index.html)
\ \ New AudioShake models double in transcription accuracy, over 5X in speed \ \ Our new lyric transcription and alignment models nearly double accuracy, and are over 5X faster.](/content/post/new-audioshake-models-double-in-transcription-accuracy-over-5x-in-speed/index.html)
\ \ Stems for a wide range of guitar sounds \ \ Latest AudioShake stems pick up different guitar styles, genres, and pedal effects with even better clarity and tone.](/content/post/creating-stems-for-a-wide-range-of-guitar-sounds/index.html)
\ \ How broadcasters can put audio to work (NAB PILOT) \ \ How broadcasters can use stem separation for localization, copyright compliance, and emerging content formats.](/content/post/how-broadcasters-can-put-audio-to-work-nab-pilot/index.html)
\ \ Launching Dialogue and Music/Effects Separation on Live \ \ AudioShake’s separation technology for film, television, and content teams comes to AudioShake Live and Indie.](/content/post/launching-dialogue-and-music-effects-separation-on-live/index.html)
\ \ Stems help create something “new” from existing catalogs (A2IM) \ \ How labels can use AudioShake stems to maximize creative, revenue, and engagement opportunities](/content/post/stems-help-create-something-new-from-existing-catalogs-a2im/index.html)
\ \ Is Generative Music Really the Next Napster? (Trapital) \ \ Originally published on Trapital, AudioShake's CEO writes why it’s going to take a lot more than a text prompt to kill music as we know it](/content/post/trapital-is-generative-music-really-the-next-napster/index.html)
\ \ AudioShake joins The Disney Accelerator \ \ The business development program brings in innovative companies to gain guidance from senior leadership on the opportunities for its technology.](/content/post/audioshake-joins-the-disney-accelerator/index.html)
\ \ What makes for higher quality piano stems? \ \ How AudioShake’s piano stems compare to open-source models, including findings from AudioLabs.](/content/post/piano-stems-research-classical-music-pop/index.html)
\ \ Latest models, higher quality stems \ \ AudioShake releases its latest AI stem separation models with improved quality to all instrument stems.](/content/post/latest-models-higher-quality-stems/index.html)
\ \ A Year in Audio AI: More Remasters, Interactivity, and a Global Focus in 2024 \ \ Winner of TIME Best Inventions, AudioShake stems made their way into projects for De La Soul, SZA, Nina Simone, Doctor Who, Sia, and more.](/content/post/2023-recap-highlights/index.html)
\ \ AudioShake wins Sony Demixing 2023 \ \ AudioShake's AI models earn the highest overall SDR scores in Sony challenge across music and film separation.](/content/post/audioshake-sony-demixing-2023/index.html)
\ \ Tuney and AudioShake team up for the first-ever, AI-powered EP produced by Boi-1da. \ \ BACARDI’s 'Music Liberates Music' program drops new EP: The Concept A.I.bum](/content/post/bacardi-boi1da-concept-album/index.html)
\ \ Art Official: AI & De La Soul’s Long-Awaited Digital Release \ \ AudioShake stems helped re-master De La Soul’s first six albums in Dolby Atmos for Reservoir Media](/content/post/de-la-soul/index.html)
\ \ Algoriddim debuts AudioShake’s real-time stem separation on djay Pro: the #1 software for performing DJs \ \ For the first time, AudioShake’s industry-leading music separation tech is made available in real-time, on device.](/content/post/algoriddim-djaypro-neural-mix/index.html)
\ \ Mastering unreleased performances of the Tomasz Stanko Quintet \ \ Astigmatic Records uses AI stems to master 1970’s broadcast of revered Polish trumpeter](/content/post/astigmatic-records-tomasz-stanko/index.html)
\ \ New benchmark for HQ transcriptions \ \ AudioShake paper sets a new direction for high-quality lyrics transcription with a new evaluation benchmark.](/content/post/new-benchmark-for-higher-quality-lyrics-transcription-from-audioshake-research/index.html)
\ \ Lyric Videos to Help Artists Reach Global Audiences \ \ Downtown Artist & Label Services harnesses LyricSync to create localized marketing assets for Lala Sadii](/content/post/localized-lyric-videos-for-lala-sadii/index.html)
\ \ AudioShake named a TIME Best Invention of 2023 \ \ TIME selected AudioShake as one of 2023's inventions changing how we live, work, play, and think about what’s possible.](/content/post/audioshake-named-a-time-best-invention-of-2023/index.html)
\ \ Introducing Nina Simone’s Debut Album to New Audiences \ \ BMG and Nina Simone’s estate partner with AudioShake on a spatial mix of Little Girl Blue, mixed by Immersive Mixers.](/content/post/introducing-nina-simones-debut-album-to-new-audiences/index.html)
\ \ A 1977 song lands in a 20th Century Fox trailer \ \ Wise Music Creative taps AudioShake to land a sync deal for the trailer of 20th Century Fox picture “Amsterdam”](/content/post/a-1977-song-lands-in-a-20th-century-fox-trailer/index.html)
\ \ AudioShake Unveils AI Lyric Transcription & Alignment \ \ LyricSync creates clean, time-stamped lyric transcriptions with high accuracy using AudioShake's vocal isolation tech.](/content/post/introducing-lyricsync-for-lyric-transcription-alignment/index.html)
\ \ Doubling Down on Dubbing \ \ AudioShake helps unblock a long-standing challenge in dubbing, transcription, and captioning technology with new model.](/content/post/doubling-down-on-dubbing/index.html)
\ \ Opening Up The Libertines’ Catalog for Remasters \ \ Using AI stem separation to master a 20th anniversary album for The Libertines with Rough Trade Records.](/content/post/opening-up-the-libertines-catalog-for-remasters/index.html)
\ \ Mixing the Fast X Soundtrack with AI Stems \ \ Immersive Mixers worked with AudioShake stems to mix the latest movie’s soundtrack in Dolby Atmos.](/content/post/mixing-the-fast-x-soundtrack-with-ai-stems/index.html)
\ \ Building Spatial Formats with AI Stems \ \ The rise of spatial audio and how audio engineers build immersive soundscapes with the help of stems.](/content/post/building-spatial-formats-with-ai-stems/index.html)
\ \ Using Stems for Customized, Interactive Music Experiences \ \ Emerging interactive audio formats present new opportunities and new life for audio across fitness, gaming, social apps, and more.](/content/post/using-stems-for-customized-interactive-music-experiences/index.html)
\ \ Launching Auto-Instrumental for Sync Licensing \ \ Chordal and AudioShake team up to launch a first-of-it-kind tool for music supervisors and sync licensors, Auto-Instrumental.](/content/post/launching-auto-instrumental-for-sync-licensing/index.html)
\ \ Stems for Wind Instruments \ \ AudioShake launches stem support for wind instruments, tackling an industry-wide challenge of isolating these complex tones.](/content/post/stems-for-wind-instruments/index.html)
\ \ A live broadcast of a jazz legend is brought to life with AI \ \ 50 years later, Oscar Peterson’s “Live in Zurich” performance makes its way to digital, vinyl, and CD.](/content/post/a-live-broadcast-of-a-jazz-legend-is-brought-to-life-with-ai/index.html)
\ \ Dubbing Doctor Who into German with AI \ \ Pandastorm Pictures turned to AudioShake to master and dub the original 1975 BBC series.](/content/post/dubbing-doctor-who-into-german-with-ai/index.html)
\ \ Stems and the Growing Sync Industry \ \ How labels and artists can use AI to create stems and land sync deals.](/content/post/stems-and-the-growing-sync-industry/index.html)
\ \ The Future of Audio is Interactive \ \ New tools will make editing and transforming audio as easy as photo or video, and more from Jessica Powell’s talk at CODE conference 2022.](/content/post/the-future-of-audio-is-interactive/index.html)
\ \ Introducing AudioShake Indie \ \ AudioShake Indie, a platform to help indie labels, artists, and producers open up their recordings to new revenue streams](/content/post/introducing-audioshake-indie/index.html)
\ \ Shred with Green Day, with some help from AudioShake \ \ Green Day's Billie Joe asks fans to play along to "2000 Light Years Away" on TikTok](/content/post/shred-with-green-day-with-some-help-from-audioshake/index.html)
\ \ Houston Kendrick x AudioShake: The World’s First AI Stem Remix Contest! \ \ Indie artist Houston Kendrick has partnered with AudioShake to run the world’s first-ever remix contest powered by AI stems.](/content/post/houston-kendrick-audioshake-remix-contest/index.html)
\ \ AudioShake wins Sony Demixing Challenge \ \ Sony ran a “Demixing Challenge” to find the world’s best song separation technology…and we won.](/content/post/audioshake-wins-sony-demixing-challenge/index.html)
\ \ Launching AudioShake Live \ \ AudioShake Live is a platform that lets labels, publishers, and their partners bring our A.I. technology “in-house,” and create instrumentals and stems on demand.](/content/post/launching-audioshake-live/index.html)