NeuTone has announced the release of NeuSynth, an AI instrument-stem generator designed to create new layers from audio supplied within a DAW. Producers can use up to 60 seconds of a track as Context, select one to six instrument layers, and generate four variation sets to audition alongside their original audio.

Each variation set contains a separate WAV file for every selected instrument, with the parts generated to work together. Users can compare the four sets, then drag individual tracks or a complete set into their session.

Generation Workflow

NeuSynth accepts clips dragged from a DAW as Context, with a preview available before generation. Users can guide the output through instrument categories, an audio reference or a text prompt. Context does not consume Generation Credits.

Key features include:

• Up to six instrument layers per generation.

• Four variation sets, each containing separate instrument WAVs.

• Auditioning of generated sets alongside the source Context.

• Drag-and-drop export of individual layers or complete sets.

The developer states that users retain rights to their uploaded music, projects are private by default, and users can opt out of AI model improvement without losing access to the plugin.

Pricing and Availability

NeuTone offers a free trial and two monthly subscription plans. Currently it is macOS only with Windows listed as coming soon:

• Starter - $4.99/month with 150 Credits per Month.
• Creator - $9.99/month with 400 Credits per Month.

One credit covers one instrument variation of up to 30 seconds. Each Generate action returns four variations per instrument, so a single instrument at 30 seconds uses four credits. Longer requests are charged in additional started 30-second blocks.

YouTube/dHlWsePizjw

Read More

discoDSP has released TED-8 1.5, a free update that gives the synth's sequencer a piano roll, along with updates to Discovery Pro and Retromulator.

TED-8 1.5

The new Sequencer Editor lets you edit notes and velocity in a piano roll, and its Bass, Lead, Pad, Keys and Mutate generators write phrases in your chosen key and scale. Sequences can be imported from a .mid file by loading or drag and drop, and dragged straight out to your DAW.

Changes:

• Sequencer Editor with note and velocity editing.
• Bass, Lead, Pad, Keys and Mutate phrase generators with key and scale.
• MIDI file import and drag and drop, plus drag-to-DAW export.
• Lock keeps the arpeggiator or sequence when changing programs.
• New arpeggiator modes from TEO-5 OS 1.2.
• Sound recalibrated against the TEO-5 at 192 kHz.

YouTube.com/watch?v=TkCf5g4H-ew

Discovery Pro 9.10

Version 9.10 add Bliss Core, a Nordic 1 filter and lower CPU use. Any layer can now play Bliss banks, EXS, gig, Kontakt 1-4, Akai, REX and more through the Bliss engine alongside its oscillators.

The Nordic 1 filter comes with Nord Lead 1 SysEx import and export, and new quality modes run each layer at the rate its filter needs, with Ultra using about 40% less CPU than the previous 8x mode.

Retromulator 2.3

Version 2.3 stack up to 8 cores in one instance and adds OB-Xd 2 as a core. Each rack runs its own core in parallel with its own mix, octave and key split, and Rack Presets recall whole stacks. Matrix-1000 no longer needs a ROM and plays 36 voices, Nordic adds MPE and oversampling, the boards get new layouts, and the DSP cores use less CPU.

More information: TED-8 | Discovery Pro | Retromulator

Read More

Tomasz GÅ‚uc has updated TOMiC Drum Synth to Version 0.7.0 (Build e42cb7cf).

The update introduces Sound Match (offline audio-to-synthesizer patch resynthesis), Loop -> Kit (automated drum loop deconstruction into separate synthesizer channels), modulatable Source SCAN knobs for oscillators and noise, Omni Modulators 2.0 (ten generative, physical, and chaotic modulation sources), a vactrol Low-Pass Gate (LPG) filter model, exact z-domain filter response displays, FX tab activity indicators, and the Auto-Randomize rack.

Sound Match: Offline Audio-to-Patch Optimization:

• Acoustic Fingerprinting: Multi-resolution analysis utilizing 3-resolution log-band spectrograms, 1 ms peak-follower loudness envelopes, spectral Earth Mover's Distance (EMD) pitch tracking, and MFCC trajectories ($c_1 \dots c_{12}$) without machine learning or cloud dependencies.
• Optimization Search: Classifies target hits by archetype (Kick, Snare, Hi-Hat, Percussion), evaluates 100 factory presets and Smart Random seeds, and optimizes parameters in parallel via audibility probes, coordinate passes, and CMA-ES with IPOP restarts.
• Performance: Quick mode converges in ~15 seconds; Normal mode completes in ~40 seconds, achieving 80–87% acoustic congruence. Operates on background threads below normal priority.
• Match View: Real-time convergence curves, target vs. result spectral overlays, ranked synth candidates, instant audition, and single-step undo Apply/Restore.

Loop -> Kit: Drum Loop Slicing to Synth Channels:

• Slice & Archetype Detection: Slices 2-bar or 4-bar WAV loops on transient onsets and categorizes slices into Kick, Snare, Hi-Hat, and Percussion classes.
• Parallel Resynthesis: Isolates the highest SNR hit per detected class and runs Sound Match in parallel to generate synthesizer patches.
• Pattern Translation: Rebuilds rhythmic patterns into trigger sequences, writes micro-timing into the bipolar NUDGE lane, maps peak amplitudes to step velocities, and extracts kit tempo and swing.

Modulatable Source SCAN Knobs (OSC & Noise):

• Real-Time Model Scanning: Dedicated SCAN knobs in OSC 1/2 and Noise 1/2 traverse models within any active category or user Favorites group with floating curve previews.
• Modulation Routing (OscScan & NoiseScan): Block-rate modulation targets assignable to LFOs, Mod Envelopes, velocity, and chaos sources for per-hit or continuous waveform and noise model switching.
• SCAN Step Lanes: Sequencer step lanes render as a stepped ladder displaying model names and underlying waveform shapes per cell.

Omni Modulators 2.0: 10 New Modulation Sources:

• Generative & Chaotic Engines: Ported from Omni, including Lorenz Chaos (3D strange attractor), Markov Chains, Marbles (random gate/CV generator), Cellular Automata (1D/2D life-simulations), Tidal dynamics, Orbital mechanics, Chladni resonant plates, and Granular particle clouds.
• REC & XY Performance Pads: 2D vector pad with time-decaying comet trail, and real-time gesture recording (REC) with smoothing, reverse, invert, and tempo sync.
• Display Geometry: Standardized display heights (96–136 px) with single-row knob layouts underneath to preserve sequencer vertical space.

Vactrol Low-Pass Gate (LPG) & Z-Domain Filter Display:

• Vactrol LPG Filter: Emulates optocoupler dynamics where an incoming signal drives a vactrol follower, opening cutoff up to 7 octaves while functioning as an output VCA. Features ~1 ms attack and 40–700 ms non-linear release (slowing as the photocell darkens) with Clean SVF stability.
• True Z-Domain Display: Solves linearized tick equations in the z-domain for each filter topology (SVF, ladder, Korg35, diode, comb, formant, LPG), rendering real resonance peaks, -3 dB bandwidth brackets, and Cutoff/Resonance Warp ghost curves.

Auto-Randomize (AR) Rack, FX Activity & Polish:

• AR Rack Window: Centralized interface with take history, recall ticks, starred favorite takes, Chaos amount, and musical rules (protect downbeats, hits only, TRIG cadence synchronization, pitch leap limits, collision avoidance).
• FX Activity Lamps: FX tab buttons display corner dots when an effect is active (enabled, send > 0, mix > 0) with hover tooltips; mixer tiles reflect full DSP gate states including Dyn and Stutter.
• Envelope Curves & Multi-Lane Editing: Amplitude envelopes feature attack/decay curvature tension and Hold stages; sequencer features an "All Lanes" toggle for simultaneous multi-lane nudging and shifting.

Read More

Davide Perico Audio Tools has released version 1.1.0 of Image to Wavetable, the free standalone Windows app that turns any picture into a Serum-format WAV wavetable for Serum, Vital, Pigments, Phase Plant, Surge XT and other wavetable synths.

The new version adds built-in image editing, so you can shape the source picture without leaving the app:

Changes:

• Crop by dragging on the picture: resize with the edges and corners, double-click to reset.
• Rotate 90° at a time or freely with the Angle slider.
• Flip horizontally or vertically.
• Live audition: hear every edit while you make it, with a smooth crossfade.
• Edited / Original A/B comparison (the export always uses the edited image).

Read More

Acon Digital has released Restoration Suite 3, the next generation of their audio restoration toolkit. The major new feature is the new Restoration Suite 3 plug-in, which takes all the guesswork out of audio repair. Users can just click 'Analyze', play a few seconds of audio, the plug-in then identifies what is wrong and adds the exact modules and settings needed to fix it.

In addition, the new suite brings machine learning–powered 'Automatic' modes to DeNoise 3 and DeHum 3, refreshed interfaces for DeClick 3 and DeClip 3, with one-time perpetual pricing with no subscription. From today, the Restoration Suite 3 plug-in is also part of Acoustica 8, Acon Digital's recently released audio editor.

Analyse - From problem audio to the right fix in seconds

For many, audio restoration has traditionally meant trial and error. Engineers capture noise profiles, guess which tools a recording needs, stack plug-ins and tweak settings while trying not to introduce artefacts. Restoration Suite 3 changes that starting point.

The Restoration Suite 3 plug-in combines DeNoise 3, DeHum 3, DeClick 3 and DeClip 3 in a single interface. Its intelligent analysis works in three steps:

1. Insert the plug-in on a track in any DAW or compatible host, or load it in Acoustica.
2. Click Analyse and press play. The plug-in listens to the recording and learns its problems, whether broadband noise, hum, clicks or clipping.
3. Get a ready-made repair chain. When analysis finishes, the plug-in has added and configured the modules the audio needs, ready to fine-tune at any time.

The result is a solid starting point in seconds rather than several minutes of experimentation.

Restoration Suite 3 targets specific defects and deliberately leaves useful production sound, such as footsteps, Foley and doors, intact. That makes it a complement to Acon Digital's dialogue isolation tool, Extract:Dialogue 2, rather than a replacement.

Four updated modules

• DeNoise 3: A new machine learning–powered Automatic mode removes hiss, broadband noise, wind, buzz and camera noise with no noise profile needed. Manual mode remains for unusual or complex noise.
• DeHum 3: Automatic mode detects and removes hum and buzz from poor grounding or electrical motors. Precision mode follows hum that drifts in pitch, and Notch mode offers a low-CPU, zero-latency option.
• DeClick 3: Removes clicks, pops, surface crackle, data drop-outs and plosive thumps, rebuilding damaged audio from the clean signal around it. Now with a streamlined interface.
• DeClip 3: Reconstructs peaks flattened by analogue or digital clipping while keeping the original tone. One click detects the clipping level, and a level histogram shows what will be restored. Also now with a refreshed UI.

Restoration Suite 3 plug-in joins Acoustica 8

In addition to being available as an individual product, the Restoration Suite 3 plug-in also becomes part of Acoustica 8, the newly updated complete audio editing package that Acon Digital released in September this year.

With an MSRP of $99, to celebrate the launch, Restoration Suite 3 is available with a 30% discount on new licenses and upgrades until November 17th.

{PRODUCT-HEADER-7370-restorationsuite3}.

{PRODUCT-HEADER-1251-acoustica8}.

YouTube.com/watch?v=QVvsPAJi9TY

Read More

Ruhrpott Guitars, a guitar, bass and amplifier workshop in Dortmund, Germany, has released Proberaum, a standalone practice app for musicians, together with eight audio plug-ins for macOS and Windows.

I wanted to practise along to a song without setting up a DAW first, and I couldn't find a tool that did that, so I built one. The plug-ins come from what I hear in the workshop every day: old tape machines, bucket-brigade chips and boutique pedals.

Proberaum

Proberaum is designed for practising along to backing tracks, rehearsal room recordings, fully produced songs, without setting up a DAW. The instrument runs from the audio interface through up to four AU or VST3 plug-ins, a built-in amp simulation or a built-in pedalboard, while the song plays back alongside. The app detects and follows the song's tempo, including recordings without a click track, and places the count-in on the downbeat even in the middle of a song. Loops snap to whole bars and can be played slower, faster or in another key.

Key Features

• Plays WAV, AIFF, MP3, M4A, FLAC and other formats with tempo detection that follows tempo changes in the recording.
• Count-in, loops in whole bars, tempo from 50 to 150% and pitch shift of ±12 semitones.
• Hosts up to four AU or VST3 effect plug-ins, plus a built-in amp simulation and a pedalboard with compressor, drive, modulation and tempo-synced delay.
• Tuner with tunings for 6- to 8-string guitar and 4- to 6-string bass.
• Sets for rehearsing a whole programme, quick recording with instant playback and WAV export, including a dry DI track for re-amping.
• Version 1.1 (4 November 2026) added the pedalboard, the tunings and protection against crashing plug-ins.

Plug-ins

• Doppelspur and Überholspur: artificial double tracking with virtual tape machines, in mono and true stereo.
• Namenlos: flanger, chorus, doubling and optical tremolo based on a BBD delay with feedback.
• Ebb & Flow: BBD modulation with a random LFO and a low pass gate, from tape-stop effects to chorus.
• Kaleidoskop and Kaleidoskop Prisma: a random multi-effect with a single control, plus a version with access to every effect and parameter.
• Spurpolitur: seven mixing effects with one knob each, for vocals, guitar, bass, drums and keys.
• Omnia: a virtual instrument combining string ensemble, synthesizer and bass, modelled on a 1978 string machine.

Pricing & Availability

Proberaum is available now for €29. The plug-ins cost €19 or €29 each (Doppelspur/Überholspur and Kaleidoskop/Kaleidoskop Prisma are sold as pairs). A bundle of all eight plug-ins costs €99, and all plug-ins plus Proberaum cost €119.

All products run on macOS and Windows; the plug-ins are available in AU and VST3 format on macOS and VST3 format on Windows. A free 14-day trial is available for every product.

Read More

FMJ-Software has updated Awave Studio, their editor and format converter for sampled instruments and all types of audio files.

v12.17 is a maintenance release, focusing on bug-fixes for the more then 400 different file formats that it handles. It also improves the stability of the built-in software synthesizer.

Read More

Algoriffix has released Pitch Perfekt V2, a major update to its voice-to-MIDI plug-in and standalone application.

Pitch Perfekt converts sung notes into MIDI in real time and can also convert recorded vocals into MIDI files. V2 adds two premium features: Vocal Transformer, which lets you shape your voice live, and Functional Harmony, which harmonizes a recorded melody in four parts.

Changes in V2

• Improved pitch tracking.
• Key-aware note names.
• Vocal Transformer with pitch correction, pitch and formant shifting, vocal harmony and growl.
• Functional Harmony for four-part melody harmonization during file conversion.
• Mains hum filter.
• Revised GUI.

Pricing & Availability

Pitch Perfekt remains free. Vocal Transformer and Functional Harmony are available as premium features, each with a 7-day free trial.

Pitch Perfekt V2 runs on macOS 12 or later and Windows 10 or later. It is available in VST3, AU and AAX formats, as well as a standalone application.

Read More

Austin Haynes Music has updated Loopsmith, a Windows tool that turns finished game music into seamless loops, adaptive music setups and engine-ready exports, to v1.22.0.

1.22.0 introduces Markers. The game is told each marker's name as the music reaches it, so lights or gameplay can follow the score. This works for a single looping track in Unity, Godot, the web and FMOD Studio. You can now pause the music for a menu and carry on from the same place, or muffle it under a dialog.

Area music, where each part of a level has its own music and it crossfades as the player moves between them, now builds in Unreal Engine as well. Area music sets also get a client review page, and a new portfolio page writes one playable HTML file for a composer's website or itch page. Loopsmith's single file export with the folded tail is now also tested in Defold 1.14.

Read More

Insektiq has released Toniq, a free audio to MIDI plug-in and standalone app. It turns a recording into MIDI: polyphonic, full mix, melodic, vocal and drums, every voice of every chord, with velocity.

Toniq Free

• Audio to MIDI in every mode: polyphonic, full mix, melodic, vocal, drums.
• Every voice of every chord, with velocity.
• No length limit, no watermark, commercial use.
• ARA 2 in Pro Tools, Cubase, Nuendo, Studio One and REAPER: select a clip and Toniq reads it from the timeline.
• The editor, to see every note, and a built-in synth to play them.
• A full mix split into drums, bass, vocals and the rest, as audio stems.
• MIDI export: one file with all the notes, drums and tempo.

Toniq Pro

Toniq Pro is in the same download. It adds detection settings, quantize, vibrato in the MIDI, MIDI per instrument from a full mix, a Pencil for missed notes, and changing notes inside the audio itself: pitch, timing, length, level, vibrato and glides, one note of a chord at a time.

Compare Free vs Pro at: insektiq.com/pricing

New in version 0.7.15:

• Cleaner MIDI from effected parts: delay and echo repeats, and restarts inside a held note, no longer come out as extra notes in Polyphonic and Melodic.
• A new computer can now be activated with just an email address: Insektiq sends a code, and the user types it in. A licence key still works too.
• The one-time "preparing the note engine" step now really happens only once on each Mac.

Pricing & Availability

Toniq is available for macOS and Windows in standalone and AU, VST3 and AAX plugin formats. Toniq Pro is currently available for the introductory price of $129 (Reg. $149). A 14-day trial is available.

Read More

Pi by Saharty has launched a family of "professional tools built by working engineers for live sound, immersive audio and show production".

All run on macOS and Windows, with a free 15-day trial of every feature:

• Pi Live ($199) - A plug-in host for live sound. Run your processing chain natively or on up to four remote processing servers, with scenes, latency compensation, a multitrack recorder and a backup host.
• Pi Tune ($99) - Zero-latency live vocal tuning (AAX, VST3, AU, standalone) with ten scale families including Arabic maqamat, Turkish makamlar and Persian dastgah, key learning from a side-chain, and MIDI/timecode snapshots.
• Pi UpMix ($199) - Stereo to surround and immersive layouts up to 9.1.6 with a downmix-safe engine, optional stem separation and binaural monitoring (AAX, VST3, AU).
• Pi System Align ($249) - Dual-channel measurement and alignment: transfer function, spectrum, impulse response, SPL, delay finder, crossover alignment and a mic placement assistant.
• Pi Stage ($49) - Stage plots, input lists, patch, power and RF in one app, with a 3D stage view and PDF rider export.
• Pi Media Server ($499) - A GPU media server with clips up to 12K, projection and LED mapping, curved LED walls, lasers, AI visuals and complete show control.
• Pi Immersive Live ($499) - Object-based spatial audio for concerts, theatre and installations, with a room model, speaker alignment and console control.
• Pi Immersive Mastering Suite ($249) - Master immersive ADM BWF albums to -18 LKFS and -1 dBTP with linked dynamics that keep every bed and object in balance, then deliver with automatic quality control.

Read More

null.audio has updated Align and Edit, its tools that bring ARA plug-ins to Ableton Live on macOS and Windows, to version 1.1. It's a free update for existing owners.

Edit now opens a whole verse, the doubles on other tracks or an entire track together in Melodyne or another ARA editor. Every track plays through its own effects while it's edited, producers can switch between the edit and the original while the song plays, and one Apply writes every clip back in place.

Align finds a singer's doubles and harmonies by their track names and opens up to eight in VocAlign together. A new Built-in engine (beta) aligns them with no additional plug-in. It doesn't align as well as VocAlign yet, and VocAlign stays fully supported.

Both products have new panels that show the next step, and every button can go on a key or a MIDI control.

I got tired of waiting for ARA in Live, so I built it for the way I work on vocals: open the whole verse, fix it in context, apply, move on,

Pricing and Availability

Both tools need Ableton Live 12.3 or later with Max for Live, which comes with Live Suite. Align costs €39, Edit €49 and Align + Edit €69, including VAT, one-time, with updates included. Introductory prices apply until 8 November: €29, €39 and €55.

Read More

iZotope has announced the release of Photon, a standalone app and ARA plugin for AI-powered stem separation and audio enhancement. Powered by 12 custom-trained models, Photon runs locally on the GPU for fast processing without any uploads.

Whether you're cooking up a remix, adjusting the kick volume, exporting a quick acapella, untangling multiple speakers in a podcast or interview, or cleaning up spoken word, Photon delivers. Choose your model, let the magic happen, export, and you're done. Or use Photon as an ARA plugin in your DAW: perfect for making quick balance upgrades to a stereo stem.

Photon is the first collaboration between the minds at iZotope and Boris FX, bringing together two world-class research teams to create cutting-edge machine-learning models that sound incredible.

Included machine-learning models

Demix - split the mix:

• Music - 4 Stems Ultra: new 4-stem high-quality stem separation model for music.
• Drums - 5 Stems: magically adjust the kick, snare, hi-hat, toms, and cymbals.
• Voice Separator: split up to 6 speakers from one audio file into individual stems.
• Voice - 2 Stems: voice and music, for a quick instrumental or acapella.
• Cinema - 4 Stems: split a video or audio file into dialogue, music, sound effects, and everything else.

Denoise - fast and powerful cleanup:

• Voice Restore: enhances speech and handles noise, levels, mic tone, and reverb.
• Indoor / Indoor Noisy: tames reverb and room noise, enhancing dialogue to production-ready, fast.
• Outdoor / Outdoor Traffic / Outdoor Wind: optimized models for traffic, urban noise, and heavy wind.

Additional features:

• ARA plugin: Tweak stems or fix background noise right in your DAW. Run several models together and switch between them without waiting.
• Local GPU processing: large, custom-trained models run locally on your GPU for fast, private processing without uploads.
• Preview from anywhere: start processing at any point in the clip and hear results in seconds. Very helpful for long files.
• Model Manager: download new and updated models without needing to reinstall.
• Flexible exports: deliver in WAV, FLAC, MP3, or video same-as-source with the original video stream kept.

Pricing & Availability

Photon has an MSRP of $349 and is available now for macOS and Windows. Early cyber deal pricing is available through December 7, 2026, with crossgrade pricing starting at $49. Subscription options are also available.

{PRODUCT-HEADER-39839-photon}.

YouTube.com/watch?v=9dM6onm4fvM

Read More

Sampleson has announced the release of Wavefinder, a local AI-powered audio search tool that lets you find sounds in your library based on how they actually sound, rather than their filenames.

Type "jazzy trumpet solo" or "footsteps on sand"... or, even better, just drop in a sound and it'll find the best matching audios on your computer.

Key Features

• Local Processing: Operates 100% on your machine without requiring cloud uploads or tags.
• Sound-Based Search: Allows you to find audio files in your library by describing how they sound (timbre, texture, and gesture) or by dropping in a reference clip. Wavefinder maps and indexes your audio files locally using its internal AI model, entirely bypassing traditional filename searches.
• Text-to-Sound Prompts: You describe a specific sound quality (e.g., "heavy metallic thud," "crunchy vinyl snare," or "evolving granular pad"), and the engine ranks your local files by sonic similarity.
• Audio Reference Matching: You can drag and drop an existing audio snippet into the interface to find the closest sonic matches hidden within your sample library.

Compatibility & Ecosystem

• Supported Formats: Indexes and reads all standard audio production file types, including WAV, AIFF, FLAC, OGG, and MP3.
• ⁠Plugin & App Ecosystem: Functions both as a standalone utility app for desktop organizational tasks and directly inside your DAW as a VST3 or AU plugin.
• Display Support: Built with a scalable, high-resolution UI that natively handles Retina and 4K monitors.

Privacy, Performance and Pricing

The underlying AI model runs completely on your hardware. No files are ever sent to an external server or uploaded to the cloud, ensuring data privacy and fast, zero-latency retrieval once indexed.

Wavefinder is available now at the introductory price of $29 (regularly $49).

YouTube/HH2709Zcn8A

Read More