ReSing is a breakthrough plug-in and standalone application that brings professional voice modeling to your desktop workflow. At the core of ReSing is advanced AI technology that captures the unique timbre, tone, and expression of real artists, delivering ultra-natural vocal performances that feel indistinguishable from a live session.
Internet connection is required for authorization.
ReSing Modeler Performance
The ReSing Modeler allows you to create a fully functional ReSing Model from a set of vocal or instrument recordings.
This processing known as modeling involves analyzing and learning the unique features of a voice/instrument through a series of machine learning training steps, during which the software processes each recording to extract detailed acoustic information and generate a model capable of reproducing that voice/instrument with high fidelity.
Because the training phase relies on complex deep learning computations, hardware performance plays a crucial role in determining both the speed and quality of the results.
On macOS, Intel-based systems represent the least efficient option for voice modeling, as the process relies exclusively on CPU computation.
Since traditional CPUs are not optimized for the parallel processing required by deep learning, training performance is significantly limited.
In contrast, Apple Silicon architectures (M1, M2, M3, etc.) deliver a major improvement thanks to Metal Performance Shaders (MPS), which allow the Modeler to harness the GPU and Neural Engine for accelerated processing.
On Windows, CPU-only configurations face similar limitations to those seen on Intel-based Macs, however, when equipped with an NVIDIA GPU\* supporting CUDA\*, Windows systems achieve the best overall performance. CUDA acceleration enables massive parallelization, allowing the Modeler to train even complex, high-quality voice models with exceptional speed and stability.
ReSing is a breakthrough plug-in and standalone application that brings professional voice modeling to your desktop workflow. At the core of ReSing is advanced AI technology that captures the unique timbre, tone, and expression of real artists, delivering ultra-natural vocal performances that feel indistinguishable from a live session.
OVERVIEW
ReSing Overview
Total vocal freedom
Any vocal track can become a professional take in any style, mood, or genre, and it doesn’t have to be perfect to get started. You can even import a rough vocal recorded on your phone into your DAW, and ReSing works its magic.
Define the emotion
ReSing allows you to select the vocal delivery intent and customize voices for a variety of musical styles.
- Includes voice models with a variety of go-to styles and options.
- Blend the timbre and accent of two models to create hybrids.
- Import RVC\*\* models from rapidly growing online communities.
Professional results quickly
Thanks to ReSing's ARA (Audio Random Access) mode and built-in effects, vocal editing is intuitive and straightforward. Everything is designed to keep you in the creative zone with consistently high-quality results.
- Process and import vocals directly within your ARA-compatible DAW.
- Mix vocal tracks using ReSing’s custom effects and presets.
- Utilize IK’s award-winning Dynamics, EQ, Reverb, and Pitch Correction.
Create Bigger Vocals with Doubling
Create realistic double-tracked vocals, backing vocals, and vocal stacks automatically from a single performance.
Doubling automatically generates additional vocal performances from a single voice, making it easy to create realistic double-tracked vocals, backing vocals, and choir-style vocal arrangements without having to record multiple takes.
Natural timing and pitch variation help every layer feel unique, while advanced controls give you complete control over the final blend.
ReSing modifies vocal tracks by replacing their timbre and phonetic features with those of high-quality AI voice models of real artists. This technology demands more intensive processing than other methods, which often struggle to capture complex vocal nuances.
ReSing’s engine works smoothly as both a plug-in and a standalone app, performing vocal transformations directly on your computer and eliminating the need to connect to external servers or wait in processing queues.
For instruments, too
Replace any vocal or instrumental track with an instrument from ReSing’s model browser, taking advantage of IK’s extensive experience in virtual instruments. The same controls used for vocal models are available to handle all aspects of the performance, including transposing.
Transpose to perfection
When you transpose a vocal or an instrument, ReSing models continue to behave and sound exactly like a real singer or instrument without any quality loss or strange effects. Change keys, create vocal stacks, layer instruments — anything is possible while sounding completely natural.
What's New
Doubling Add-on
Doubling automatically generates additional vocal performances from a single voice, making it easy to create realistic double-tracked vocals, backing vocals, and choir-style vocal arrangements without having to record multiple takes.
Available as an add-on for all ReSing users.
Singer Showcase
The new ReSing Singer Showcase changes the game, so now you can own your voices forever - letting users browse, purchase, and permanently own individual voice models from a growing collection of singers and narrators across multiple genres, styles, and languages to build personalized voice libraries tailored to their creative needs.
ReSing lets you:
- Instantly replace vocal takes with professional-quality performances
- Adjust vocal energy, tone, and style, even blend and mod voices
- Turn any recording – even from your phone – into a studio-quality vocal
- Sing basslines, riffs, and hooks, then convert them into real instruments
- Create your own voice models to share or license
- Create realistic double-tracked vocals, backing vocals, and vocal stacks automatically
The first truly professional voice replacement
- Up to 25 Voice and 25 Instrument models included
- Supports models in English, Spanish and Japanese, with more to come
- Full DAW integration with ARA support
- Desktop native, so no uploading or internet required
- One-time perpetual license, no subscription or lock-in
- Import voice RVC\*\* models from popular open communities
- Explore a growing catalog of partner voices and “hire” as needed
TECHNOLOGY
Specs
System Requirements
ReSing is a 64-bit application and requires a 64 bit CPU and Operating System.
Mac® (64-bits)
Minimal: Apple M1 or Intel® Core i5 Processor, 8 GB of RAM, macOS® 13.7 or newer.
Internet connection is required for authorization.
ReSing Modeler Performance
The ReSing Modeler allows you to create a fully functional ReSing Model from a set of vocal or instrument recordings.
This processing known as modeling involves analyzing and learning the unique features of a voice/instrument through a series of machine learning training steps, during which the software processes each recording to extract detailed acoustic information and generate a model capable of reproducing that voice/instrument with high fidelity.
Because the training phase relies on complex deep learning computations, hardware performance plays a crucial role in determining both the speed and quality of the results.
On macOS, Intel-based systems represent the least efficient option for voice modeling, as the process relies exclusively on CPU computation.
Since traditional CPUs are not optimized for the parallel processing required by deep learning, training performance is significantly limited.
In contrast, Apple Silicon architectures (M1, M2, M3, etc.) deliver a major improvement thanks to Metal Performance Shaders (MPS), which allow the Modeler to harness the GPU and Neural Engine for accelerated processing.
On Windows, CPU-only configurations face similar limitations to those seen on Intel-based Macs, however, when equipped with an NVIDIA GPU\* supporting CUDA\*, Windows systems achieve the best overall performance. CUDA acceleration enables massive parallelization, allowing the Modeler to train even complex, high-quality voice models with exceptional speed and stability.
Model your voice!
Unlike other voice replacement software or services, ReSing is the first to let you create custom models locally on your computer, giving you complete control over input audio files and the final model.
The creation process guides you through each step. Once finished, your new model appears in the Model Browser within the ReSing app, ready for use. Each model is unique and protected from unauthorized use outside of ReSing.
Unlimited Model Generation Add-on
The Unlimited Model Generation add-on allows ReSing and ReSing MAX owners to create an unlimited number of voice models using the ReSing Modeler. It’s the perfect upgrade for users who want complete freedom to experiment and build as many custom voices as they wish.
Requires a licensed copy of ReSing or ReSing MAX to use.
Build your voice library
The Singer Showcase gives you access to a growing collection of professionally created voice models, available to purchase individually and own permanently.
Build a personalized library with singers and narrators spanning multiple genres, styles, and languages, with new voices added regularly.
Every voice is ethically created with the full participation, consent, and compensation of the original artist.
With built-in vocal processing tools, support for your own voice models, and an ever-expanding collection available through the Singer Showcase, ReSing gives you everything you need to create polished, release-ready vocals and instrumental performances—all within a single creative environment.
MODELS
Discover the full collection of Voice Models available. Each model provides a unique tone, character, and personality.
Transform vocals and instruments with professional AI modeling, right on your desktop.ReSing lets you replace vocal performances with expressive voice models, turn sung ideas into...
ReSing SE is a lighter edition of IK Multimedia's AI-powered vocal modeling technology, letting you transform and personalize vocal performances. Includes 2 voices, 2 instruments,...
Includes 25 voices, 25 instruments, 25 model generations, and unlimited imports.ReSing MAX is the most complete edition of ReSing, IK Multimedia's AI-powered vocal modeling technology,...
Turn one vocal performance into realistic doubles, backing vocals and full vocal stacks.ReSing Doubling automatically generates additional performances from a single vocal, making it easy...
Expand ReSing with 10 native Japanese voices, including eight singers and two narrators.Created from original recordings made specifically for ReSing, this versatile collection ranges from...
Expand ReSing with eight professional Brazilian Portuguese voice models, including six singers and two narrators.Created from original artist recordings, these expressive voices bring natural Brazilian...
Expand ReSing with eight performance-ready voices for modern music production.Created from original recordings of real artists, ReSing Voices Vol 1 Producer's Pack adds a versatile...
10 fresh voices for modern productions Expand your ReSing vocal lineup with 10 new singer models, each offering a distinctive character and style. From soulful...
Discover professional singer and narrator voice models made for ReSing.ReSing Singer Showcase lets you explore and purchase individual voice models across a growing range of...
Trademarks or registered trademark property of IK Multimedia Production Srl. All rights reserved.
Mac, the Mac logo, the Audio Units logo, iPhone®, iPod touch®, iPad® are trademarks of Apple Computer, Inc., registered in the U.S. and other countries. App Store is a service mark of Apple Inc. Windows and the Windows logo are trademarks or registered trademarks of Microsoft Corporation in the United States and/or other countries. VST is a trademark of Steinberg Media Technologies GmbH. AAX, Avid, the Avid logo, Pro Tools, and RTAS are trademarks or registered trademarks of Avid Technology, Inc. in the U.S. and other countries.
All other product names and images, trademarks and artists names are the property of their respective owners, which are in no way associated or affiliated with IK Multimedia. Product names and images are used solely for the purpose of identifying the specific products that were studied during IK Multimedia's sound model development and for describing certain types of tones produced with IK Multimedia's digital modeling technology. Use of these names and images does not imply any cooperation or endorsement.
IK Multimedia disclaims any ownership over content uploaded by users to ToneNET, including but not limited to Tone Models, Presets, and any text or symbols that users upload with their content. IK Multimedia does not endorse or represent any users of ToneNET, and any names, trademarks, or tradenames that users may upload with their content on ToneNET should not be construed as an endorsement, association, or affiliation with IK Multimedia. Users represent and warrant that they own or are licensed to use all intellectual property, including copyrights and trademarks, in any content that they upload. IK Multimedia disclaims that any content uploaded by users is non-infringing. Please see the ToneNET Terms of Use with ways that you can notify us if you believe content on ToneNET infringes your rights.
