Fiedler Audio has released armada, a plug-in wrapper that brings full VST3 processing to Dolby Atmos and other immersive audio formats.

Designed for modern mixing and mastering workflows, armada enables audio professionals to utilize their favorite VST3 plug-ins across virtually any channel configuration—from mono and stereo to complex immersive formats such as 9.1.6, NHK 22.2, Higher Order Ambisonics, Auro-3D, and beyond.

Available as a VST3, AU, AAX, and OBAM plug-in, armada integrates into major DAWs as well as Fiedler Audio's Dolby Atmos Composer and Mastering Console.

Addressing the Biggest Challenges in Immersive Production

Every producer, mixer, and mastering engineer has their go-to tools—a collection of plug-ins that consistently deliver the desired tonal and dynamic results. As immersive audio formats became essential for content delivery, channel counts expanded from 5.1 to up to 128 channels (as in Dolby Atmos), and even more for installations and advanced applications. As a result, many of these trusted tools were no longer usable in their original form.

Those limitations are now a thing of the past with armada. Want to add a touch of character from a favorite vintage limiter? No problem. With armada, controlling multichannel buses in terms of tone and dynamics becomes fast, flexible, and intuitive.

Immersive Processing Without Limits

armada supports up to 128 channels, making it suitable for everything from traditional stereo sessions to full-scale immersive productions. Users can process entire Dolby Atmos mixes within a single instance—an industry-first capability enabled through OBAM integration with the Dolby Atmos Composer and Mastering Console 2.0.

A built-in channel mixer allows precise output configuration, while flexible grouping options enable users to organize channels and apply targeted processing quickly and efficiently.

Global Control

The plug-in introduces global sidechaining, allowing users to link multiple armada instances and define custom sidechain signals via a dedicated internal mixer. Parameter linking across instances further enhances workflow efficiency in large-scale sessions.

Speed, Scalability, and Customization

armada is built on a multithreaded audio engine, ensuring optimized performance when running demanding VST3 plug-ins in high channel-count environments. Users can adjust thread allocation per instance to match session requirements.

Preset-based channel grouping accelerates session setup, and user presets allow engineers to further customize their workflows across projects.

Key Features

• VST3 processing on any channel format (up to 128 channels).
• Full Dolby Atmos mix processing in a single instance (OBAM).
• Global sidechaining across multiple instances.
• Flexible channel grouping.
• Parameter linking across instances.
• Low-latency Dolby Atmos workflows when used as an OBAM plug-in in Dolby Atmos Composer.
• Intuitive workflow, even for the most complex mixing scenarios.
• Integrated channel mixer for maximum flexibility and monitoring.
• Multithreaded processing for high channel counts and CPU-intensive plug-ins.
• Preset system for rapid session setup and channel grouping.

Pricing & Availability

armada is available worldwide through authorized dealers and at www.fiedler-audio.com for USD/EUR 249. A 25% introductory discount on armada and related bundles is available until May 15, 2026.

YouTube.com/watch?v=X8s7TdSQC2s

YouTube.com/watch?v=TVTkmakcqms

Read More

We are very excited to announce the launch of the KVR Developer Challenge 2026, the tenth free-for-all audio plugin / audio application / soundware design event, and 20 years since the first one in 2006.

The "KVR Developer Challenge" is for anyone who develops Audio Plugins or Applications and Soundware. The challenge is to create and release a brand new free audio plugin, application or sound library / pack / set that will benefit the community at large.

Creativity is key, it can be as simple or as complex as you want - KVR members will vote on the entries and pick the eventual winner using whatever criteria they choose to.

Five cash prizes will be awarded to the top entries and a wildcard pick. Prize moneys are sponsored by the community-funded KVR Developer Challenge 2026 donation pool.

The KVR Developer Challenge began in 2006 and has occurred every 2-3 years ever since.

2023 was won by the excellent Solaris reverb plugin by Adam Szabo, with MONSTER OctaChord v1 by Monster DAW, Wave Breaker by Press Play, and Northern Trumpets by VG Trumpet making up the top four and Roundels by XiiixxiQ taking the wildcard prize.

2021 gave us WhispAir by Full Bucket Music, GR-8 by Phuturetone, Virtuosity Drums by Versilian Studios, and FKFX Influx by FKFX.

2018 delivered gems such as ProF.E.T. by Ignite Amps, Deducktion by Dead Duck Software and MPS by Full Bucket Music. We had Youlean Loudness Meter, Lagrange by Ursa DSP and Spaceship Delay from Musical Entropy in 2016, Multiply by Acon Digital, Nova-67P by vladg/sound and Emissary by Ignite Amps in 2014, and so it goes on...

Check out 2012, 2009, 2007, and the original in 2006 when Triple Cheese by u-he won the show!

Read More

Audible Genius has announced an update to its synthesizer training software Syntorial, now offering a full German language option.

Syntorial's unique "learn-by-ear" approach to synthesis has helped thousands of musicians worldwide master the art of sound design. Starting today, German-speaking producers, students, and educators can access the full interactive course in their native language, removing barriers and opening doors for an entire creative community.

German joins English, French, Spanish and Japanese as fully supported languages, allowing more users to build practical sound design skills through hands-on programming.

Germany has played a major role in shaping electronic music, from pioneers like Kraftwerk to innovators across techno and beyond. By adding German language support, we're making it easier for producers and teachers to build on that legacy.

The German release is part of Audible Genius' broader localization effort, aimed at making synthesis education accessible to musicians everywhere. These new languages reinforce the company's mission to build a truly global platform for synthesis training.

Users can instantly switch to German via the Language menu. A "Report Translation Issue" option has been added to the app, which lets the community flag improvements in real time, ensuring the localization continues to evolve with user feedback.

Pricing & Availability

The German language update is available now as a free update for all existing users. New customers can purchase Syntorial for $129.99 USD directly from the Syntorial website. Educational discounts are available for schools and teachers.

Read More

Universal Audio recently released UAD Explore FREE, a new plug‑in bundle delivering the sound of UA's most trusted studio tools to music creators everywhere completely free.

Available for Mac and PC with no UA hardware required, UAD Explore FREE includes the LUNA DAW alongside eight heritage UAD plug‑ins and virtual instruments. The bundle features titles including the 1176 Classic FET Compressor, the Teletronix LA‑2A Tube Compressor, the UA 610 Tube Preamp & EQ Collection, and more.

UAD Explore FREE puts the tools that defined the sound of modern recording within reach of every creator. Whether you're just starting out or expanding your toolkit, this bundle is the most complete free studio we've ever offered...and it costs nothing.

Included in UAD Explore FREE:

• UA 1176 Classic FET Compressor.
• Teletronix LA‑2A Tube Compressor.
• UA 610 Tube Preamp & EQ Collection.
• Pure Plate Reverb.
• Vibe Analog Machines Essentials.
• Showtime '64 Tube Amp.
• Century Tube Channel Strip.
• PolyMAX Synth.
• LUNA Digital Audio Workstation.

UAD Explore FREE is available for download at uaudio.com/products/uad-explore-free

Read More

Electric Smudge has announced the release of version 3.5.0 of SnappySnap and the free SnappySnap Light.

Changes:

• New Morph Engine: Old interpolation replaced with Natural Neighbor Interpolation. No more bull's-eye artifacts. No more distant snaps bleeding into your sound. Only the snaps that should contribute, do.
• Gravity Wells: Every snap now has its own influence radius. Shape exactly how your sounds blend. Saved with your presets.
• Voronoi Territories: The XY pad now shows colored regions for each snap's territory. You'll never guess where the crossover is again: it's right there in front of you.
• Free Snap Placement: Drag snaps anywhere on the pad. Real-time visual feedback. Total control over your morph landscape.
• Motion Recording & Playback: Draw freehand paths at 60Hz or click-to-connect waypoints between snaps. Play back in Forward-Loop or Ping-Pong. Sync to your DAW's BPM from 1/4 note to 32 beats.

YouTube/ixLGFGXbLhE

Read More

NovelSimple has launched LUFS Matrix, a desktop application designed to let producers, podcasters, and content creators hear exactly how their audio will sound on Spotify, YouTube, Apple Music, Instagram, Amazon, and Deezer, all in one LUFS meter.

Every streaming platform normalizes loudness differently. Spotify turns it down. YouTube does something else entirely. Apple Music has its own rules. Producers and creators have always had to upload, check, and re-upload: hoping their mix translates. LUFS Matrix eliminates that cycle by letting you A/B your audio against each platform's target loudness standard before you export.

Key Features:

• Monitor Loudness-Matched Audio for Multiple Platforms: hear your mix as each platform would play it back.
• Load Different Tracks and A/B on the Fly: compare multiple versions in real time with Time-Synced playback.
• Instant Platform Loudness Difference Display: see at a glance how far off you are from each platform's target.
• One-Time Price, Use Locally Forever: no subscription, no cloud dependency.

Built for Your Workflow

• Music Producers & Engineers: Master with confidence. Test against real platform targets before you master. Avoid loudness wars and ensure your mix translates everywhere.
• Podcasters: Balance dialogue levels across multiple episodes. Make sure all your content hits the same loudness target before upload.
• Video Creators: Check your background music and voiceovers against YouTube's standard before publishing. Avoid notes like "turn it up" or "too loud".
• Content Managers: Test entire audio libraries before upload. Ensure consistency across your brand's audio content.

How It Works - 3 Steps

• Load Your Audio: Click Browse or drag a file directly into the app. Supports any common audio and video format. Analysis begins automatically in seconds.
• Pick Your Platform: Click Spotify, Apple, YouTube, Instagram, Amazon, or Deezer. The app instantly shows how your audio compares to that platform's loudness standard.
• Listen and Compare: Click any cell in the platform row to hear your audio adjusted for that platform. Use the Loudness Match toggle to flip between original and adjusted.

Pricing

To celebrate the launch, the first 200 users can get LUFS Matrix for $5. Use code LUFS at checkout at novelsimple.com to apply the intro pricing (Reg. $29).

Read More

Tuva Sample Manager has been updated to v1.4, building upon the previous layout adding new ways of personalizing the workflow while staying true to the original Tuva DNA.

Since the beginning, we have considered minimalism as the core of our design philosophy with Tuva.

Of course, we want Tuva to be aesthetically pleasing, but that is not the point of minimalism in our minds.

What we think of minimalism, is that every feature and interaction should feel obvious regardless of experience with the app, as well as adding great value to your workflow.

However as Tuva has developed, especially since releasing support for project files in 1.3.8, we have realised that multiple workflows and use-cases have appeared which inevitably are of different value for different users.

So we sat down at the desk, and tackled the question: How can we, in the best possible way, make it such that every user feels that Tuva works seamlessly for their workflow?

YouTube Video Overview of Tuva

New features in v1.4 include:

Custom workflows:

One of the first things we discussed, was that the left bar was beginning to feel crammed. And there is still a million (not actually, but figuratively) features to be added. So the natural answer to this was that each user should be able to decide for themselves what they want to include in the left bar. But then we thought, "What if you want to see projects sometimes, and sometimes only samples?". And that is why we added the option to create multiple views of the left bar, such that you can different views that include just what you need for each of your workflows.

Tabs:

Another issue that had been bothering us, was that when we were searching for a specific file, we felt the need of being able to search multiple things in the same session. While the arrows to navigate back and forth between views gave some ability to do this, it was at the same time hard of keeping track of what you were jumping back and forth between. As such, we eventually figured that tabs was the solution we were looking for. We won't go as far taking credit for the invention of tabs, but that is also exactly the reason why we chose it.

Pinned items:

You can now pin collections, folders and previous searches in Tuva. These will appear both in an own section in the left bar, but also alongside quick access-items and recent searches when you open a new tab.

Additional updates:

Other fixes & improvements:

In the last week, we have had a large number of new users, which we are really glad about. With that, we have also gotten a lot of reports of bugs & performance issues that were previously unknown to us. Together with the fixes released in 1.3.11, 1.3.12, and now some additional fixes in 1.4, which we hope should resolve your issues.

Massive thanks to all of you who have reached out about issues so far, we hope that this update should give you a better experience, with both a more stable app and an even better workflow.

Pricing & Availability

Tuva 1.4 is available now for 25€ at Tuva's Webpage.

Read More

Katz Praatz has announced the release of Jazz Sketch version 1.7. This update adds 240 new chord progressions to the previously available 984 in version 1.6, bringing the total to 1,224 jazz chord progressions.

Jazz Sketch (ver. 1.7) is a simple chord sequencer designed to help you create music by arranging 1,224 jazz chord progressions and 168 tension chords. You can export the chord sequence (the chord progressions and chords you've arranged) as a MIDI file to play it or edit it in your DAW. With Jazz Sketch, you can create sophisticated, jazz-infused songs with ease. Additionally, Jazz Sketch allows you to learn jazz harmony by playing it yourself.

Jazz Sketch is a software written in JAVA, and the file extension is .jar. By default, Jazz Sketch runs well on any computer that has JAVA or JRE (Java Runtime Environment) version 8 or later installed, regardless of the operating system. If your computer does not have JAVA or JRE installed, or if JAVA is installed but the version is earlier than 8, please click the link below to download the JAVA 8 compatible with your computer's operating system: java.com/en/download

Features:

• A chord sequencer designed to help you create sophisticated, jazz-infused music by arranging 1,224 jazz chord progressions and 168 tension chords.
• Can also be used for practicing jazz harmony.
• The provided chord progressions incorporate standard 2-5-1 progressions, tritone substitutions, secondary dominants, secondary subdominants, deceptive resolutions, modal interchanges, pivot chords, altered dominants, and turnarounds.
• Can export the chord sequence that you arranged as a MIDI file to play it or edit it in your DAW.
• Written in Java, and requires JAVA or JRE version 8 or higher installed to run.

Jazz Sketch is available for $6.99 USD at jazzsketch.gumroad.com/l/jazz-sketch

YouTube link (Demo): YouTube/eOjwz9WcCUQ

Read More

Wavsen has announced the update of Wavsen, a mix delivery and client approval platform for music producers and engineers, to version 1.0.5.

Custom Branding & Workflow Upgrades

• Increased storage limits: Free: 2 GB; Pro: 24 GB; Studio: 120 GB.
• Improved upload placeholders with clearer descriptions.
• Custom client portal branding - upload your logo and social links (Studio plan).
• Copy all client comments to clipboard for any project version.
• Mark individual client comments as done with a checkmark toggle.
• Share Client Portal button upgraded with link copy, open in new tab, and embed code options.
• Change watermark settings on projects that were already created.
• Search and filter clients, projects, and project status.
• Notification bell icon next to client names shows if clients have notifications enabled.

Intro Pricing

Wavsen is available in the following plans:

• Free: $0.
• Pro: $9/month introductory price (regular $12/month).
• Studio: $19/month introductory price (regular $24/month).

Introductory pricing is available through June 4 at wavsen.com

Read More

Ocean Swift has introduced Sound Creator Suite, an all-in-one desktop environment for advanced sound-design and virtual instrument development workflows.

Serving as a robust, centralized host, this suite equips producers and developers with an powerful arsenal of specialized Ocean Swift tools and utilities.

Generate studio-grade UI components - from photo realistic brushed-metal knobs to glowing LED rings with the GUI Knob Maker, and export complex animations as seamless stitched sprite sheets in seconds. Seamlessly pair this with the Kontakt Performance View tool, an advanced WYSIWYG editing environment that lets you construct complex Kontakt interfaces using a visual, drag-and-drop real-time workflow, entirely eliminating the need to write tedious layout code.

Process audio in bulk, utilize MIR algorithms to surgically align loops, automate your hardware sampling workflows, and generate algorithmic MIDI patterns. Whether you are building and converting custom wavetables, batch-injecting metadata with the NKS preset and sample taggers, monitoring OSC packets, or accessing instant music-calculation tools, the Sound Creator Suite brings an entire development ecosystem into one powerful interface.

Features

• 30+ sound design and instrument development tools.
• Growing toolkit with an comprehensive future roadmap – more tools, more assets.
• Design, Build, Record, Process, Edit, Manipulate, Monitor.
• Automate processes and speed up workflows.
• Innovative, creative, performant and user minded approach.

Price

Sound Creator Suite is available for the introductory price of €60 until May 7, 2026 (Reg. €100).

YouTube.com/watch?v=X_m3pQmdJEc

YouTube/IaamHtV7V9M

Read More

Fanan team has released Sampler Arena, describing it as a modular sampling workshop for Windows and macOS.

Sampler Arena is a focused sampling station that turns VSTi instruments sounds into ready-to-use SFZ patches. The user loads any VST3\VST2 instrument, hit start, and walk away. By using its automatic sampling module, Sampler Arena drives every key, captures every velocity, names every file, and writes a SFZ patch the user then can load into any sampler on any platform. Also, it can automatically sample chord libraries from arpeggiators and sequencers or skip recording entirely and assemble SFZ patches from audio files the user already owns. One tool, three workflows.

The Sampling Methods

The user chooses how they want to build their patch with the mode selector at the top of the sampling tab:

• VSTi Sampling captures audio from any connected virtual instrument across every selected key and velocity layer. helpful for archiving instruments or making lightweight versions of CPU-heavy synths.
• Chord Sampling captures complete chord patterns from instruments like Virtual Guitarist, Strum GS-2, or arpeggio engines. Choose any combination of 18 chord types - Major, Minor, 7th, Dim, Sus, Add9 and more - and Sampler Arena drives each chord at every root note automatically.

Sample Builder skips recording entirely. Drag and drop your own audio files into per-key slots, name them, set velocity layers, and Sampler Arena assembles a complete SFZ patch in seconds.

The Visual Keyboard - Your Control Center

A full 128-note virtual keyboard sits at the heart of the sampling tab. The user clicks keys to toggle them as sample points. Drags-select ranges of notes. Right-click any key to audition the instrument live. The integrated zone graph shows colored bars for every sampled region with draggable yellow boundary markers - including the leftmost and rightmost edges - so the user can fine-tune exactly which keys each sample covers. Velocity is captured by user's click position on the key itself: top of the key for soft, bottom for loud, just like a real piano.

The Unified Edit Button - Everything Per Key, In One Place

Each selected key gets a single golden "E" button that opens a per-key editor with every customization option in one clean popup. Velocity layer overrides, duration overrides, key shift adjustments, custom output names, and sample slot management - all behind one click, organized by mode. The button glows gold when any per-key override is active, so the user always knows which keys have been customized at a glance.

The SFZ Player With Loop Sync - A Sampler Built In

Sampler Arena ships with a complete SFZ playback engine for testing patches before exporting. The user loads any SFZ patch and play it instantly with full polyphony or monophonic portamento, AHDSR amplitude/filter/pitch envelopes, state-variable filter with keyboard tracking, three independent LFOs for vibrato and modulation, and pitch bend with configurable range. The standout feature: Loop Sync mode plays loop-based SFZ patches in accurate tempo lock with pitch fully preserved using high-quality WSOLA time-stretching. Drum loops, guitar strums, rhythmic phrases - all stretch in real time to match user's master tempo or any target BPM.

Auto-Sampling That Just Works

The user has just to press "Start" and Sampler Arena handles the rest:

• Silence Detection automatically trims dead space at the end of each note - no more long tails of silence in your samples.
• Configurable Duration with absolute milliseconds or tempo-synced bars for rhythm-based instruments.
• Automatic Loop Finder analyzes each recording and embeds professional-quality loop points directly into the SFZ.
• Fade-Out On End prevents clicks and pops on note release.
• Multiple Bit Depths from 16 to 24-bit PCM, with sample rate override for upsampling or downsampling.
• Stereo, Mono Left, or Mono Mix capture modes for any source type.

The Node Rack

The Node Rack allows building any signal chain the user needs with the node-based graph canvas inherited from Fanan's Colosseum DNA. The user can drop in VST3 plugins from any folder without scanning. Wire MIDI, audio, and sidechain pins with intuitive drag-and-drop connections. Magnetic snap keeps user's graph tidy. Container nodes let the user group complex chains into clean modules. Right-click anywhere for a tooltip explaining what every button does - the interface teaches itself.

Main Features:

• Three sampling modes: VSTi Sampling, Chord Sampling, Sample Builder.
• 18 chord types with Select All / Clear All for chord library creation.
• Drag-and-drop file loading for Sample Builder mode.
• Full SFZ patch generation with loop points, key zones, and velocity layers.
• Built-in SFZ Player with WSOLA-powered tempo-locked Loop Sync.
• Visual zone editor with draggable boundary markers on every edge.
• Per-key customization for velocity, duration, key shift, and output naming.
• Automatic silence detection and loop point finder.
• Tempo-synced sampling in bars or absolute milliseconds.
• 16 or 24-bit PCM output with stereo, mono left, or mono mix capture.
• Right-click audition with velocity-sensitive playback.
• VST3 plugin hosting with no-scan-needed direct loading.
• ASIO and CoreAudio support with rock-solid low-latency operation.
• Universal Mac build for Apple Silicon and Intel.
• Node-based signal routing inherited from Colosseum.
• MIDI Multi Filter, Monitor, Virtual Keyboard, Stereo Meter, and Container tools.
• Persistent presets including all custom settings and sample slots.
• Crash protection for unstable VSTis and unclean shutdowns.

• Custom dark amber-gold theme designed for long sessions.

Pricing & Availability

Sampler Arena is available for Windows and macOS for $15.

Read More

Forma Labs Audio has announced the public beta of Filament, a real-time MIDI orchestration plugin for composers and producers.

Filament is an instrument plugin that hosts up to 64 VST/AU instruments internally. It splits, revoices, and routes MIDI in real-time across 12 keyswitches with 8 voice layers each.

Key Features:

• Intelligent chord revoicing and note distribution.
• Routing matrix for sending voices to different instruments.
• Arpeggiator per row with per-step articulations.
• MIDI clip launcher per row with piano roll editing per hosted instrument.
• CC modifier per row with 128-point curve editing.
• Built-in mixer with macro controls.

Beta Program:

The beta is free. Participants who provide meaningful feedback will receive a free perpetual v1.0 license.

Technical Specifications:

• Formats: VST3, AU.
• Platforms: macOS, Windows.
• Pricing: Free beta (v1.0 pricing TBA).
• Availability: Now.

Links:

• Learn more at formalabsaudio.com
• Beta signup
• KVR Forum discussion

Demo Video:

YouTube/pCgwBgPCN_A

Read More

MidiStickers has released version 1.2 of its music education software, MidiStickers Pro. The update introduces a new Fretboard widget, expanded Guided Practice content, new tutorials and other improvements.

MidiStickers Pro is a desktop music education software for MIDI visualization, chord analysis and interactive music theory learning, including a Guided Practice mode for practicing scales, chords and progressions with auto-accompaniment.

Highlights of v1.2:

• New widget: Fretboard (displays MIDI input as fretboard positions, including multi-channel MIDI per string).
• New tutorial: Chord Analysis Tools.
• New Guided Practice exercise sets:
  • Major Scale Modes.
  • Melodic Minor Modes.
  • Altered Dominants
• Improved handling of suspensions resolutions in the Figured Bass widget.
• Scale Trainer improvements.

Version 1.2 also introduces a Free 7-Day Trial so you can try it the full version for a limited period of time. It is available for Windows and macOS as a $59 one-time-purchase.

Read More

LALAL.AI has announced an update to Andromeda, the company's flagship neural network for audio separation. The release expands the model's stem isolation capabilities to include Drums and Bass, alongside the previously supported vocal and instrumental stems. Furthermore, the company reports that Andromeda now delivers up to 40% faster processing speeds compared to its prior-generation Perseus model.

According to LALAL.AI, drums are among the top three most frequently processed stems on the platform, accounting for over 5 million splits in 2025. By integrating drums and bass directly into the Andromeda architecture, the system can now isolate the full rhythm section within a single network pass. The updated bass extraction algorithm is designed to capture a broader frequency range, retaining upper-register details, harmonics, and textures that are often attenuated during source separation. Drum isolation has also been modified for improved cross-section stability and bleed reduction, aiming to maintain coherence from the intro to the outro of a track.

Beyond standard remixing and production workflows, LALAL.AI notes the practical applications of high-fidelity separation in archival and restoration contexts. The company cited a recent case where a Nashville-based producer utilized the platform to isolate stems from surviving mixed files following a studio fire, effectively recovering lost performances. The Andromeda update is intended to provide the precision required for these types of critical recovery scenarios.

The platform, currently utilized by over 6 million users globally, has recently received several industry acknowledgements. In December 2025, an independent stem separation benchmark by Meta ranked LALAL.AI as the top commercial technology in the Pro category. Additionally, the software received top scores for vocal and drum extraction from MusicRadar, and was recognized at the 2026 Webby Awards (Top 5 for Best Use of AI and Machine Learning; Honoree in Creator, Creative and Media Tools).

Key Features

• Expanded Stem Support: Drums and Bass isolation added to the primary neural network, joining Vocals and Instrumental extraction.

• Enhanced Bass Reproduction: Captures a wider frequency range to preserve harmonics, texture, and high-end detail.

• Improved Drum Consistency: Advanced bleed reduction and cross-section stability designed to keep non-drum instruments out of the stem throughout the audio file.

• Increased Speed: Up to 40% faster processing times compared to the prior Perseus model without compromising output quality.

• Broad Capability: Can extract vocals, instrumental, drums, bass, guitar, and synth from any audio or video file.

Pricing and Availability

Available now, LALAL.AI utilizes a credit-based pricing model, starting at $15 for a Lite Pack (90 minutes).

Formats include Web, VST plugin, API, macOS, Windows, iOS, and Android.

Read More