BIAB – 2025, Reaper (current), i7-12700F Processor, 32GB DDR4-3200MHz RAM, Motu Audio Express 6x6 - My SoundCloud (Tip: No need to create a SC account to hear music - just hit ESC ).
Another option (which is a lot more work than a simple voice changer) is to use a synthetic voice. Most of them let you convert your voice into that program's internal representation (notes, phonemes, and pitch deviation), and then have the synthetic voice sing it.
There are a lot of downsides to that approach. Using a voice changer is basically loading the source voice, picking a target voice, and getting the results.
With vocal synthesis software, you need to:
* You have to buy/subscribe the software * You have to learn the software (it's like a pitch correction software plus words) * You have to find a voice you like * You have to pay for that voice if you're not on a subscription * You have to fix the import errors (pitch, phonemes) * The performance may be very good, but still to some degree remain synthetic.
On the other hand, you have a lot more control over the voice. Voice conversion software leaves the original performance intact, including issues with timbre. Correcting these in pitch correction software only goes so far, and if you move the voice too far out of range, you'll get artifacts.
With vocal synthesis software, you can completely re-sculpt the performance, and even replace things like vibrato without the timbre going wonky. Changing the gender of the performer is also much more realistic.
I would like to sing on my tunes but I can't stand the sound of my voice.
You have quickly been introduced to two new very powerful tools. But before you go too far down the rabbit hole I would ask you to reconcider these options. I was in your exact position years ago.
What helped me to accept my voice was two things: 1) Vocal Lessons from a pro. There is a lot which can be done to improve how you sing which will improve how you sound. 2) Pre-vocal warm up exercises (see #1) followed by Post vocal processing such as Isotope's Nektar and Neutron.
I still have cringe moments with my vocals which require me to "redo" the performance and I have been accused of overusing the post processing (too much reverb...), but I do get some satisfaction for getting more of me in my music. Think about it.
BIAB – 2025, Reaper (current), i7-12700F Processor, 32GB DDR4-3200MHz RAM, Motu Audio Express 6x6 - My SoundCloud (Tip: No need to create a SC account to hear music - just hit ESC ).
Does anyone have any experience with a plug in voice changer? I would like to sing on my tunes but I can't stand the sound of my voice.
Nobody likes the sound of their own voice. Learn to live with it
Byron Dickens
BIAB. CbB. Mixbus 32C 8 HP Envy. Intel core i7. 16GB RAM W10. Focusrite Scarlett 18i 20. Various instruments played with varying degrees of proficiency.
I am looking for an actual voice changer app that lets me use a voice of my own choosing. I'm tasked with trying to finish a project for a South American client. Unfortunately, the lead singer passed away before some of his tracks were recorded.
BIAB 2024 Audiophile Mac 24Core/60CoreGPU M2 MacStudioUltra/8TB/192GB Sequoia, M1 MBAir, 2012 MBP Digital Performer11, LogicPro, Finale27/Dorico/Encore/SmartScorePro64/Notion6 /Overture5
I am looking for an actual voice changer app that lets me use a voice of my own choosing. I'm tasked with trying to finish a project for a South American client. Unfortunately, the lead singer passed away before some of his tracks were recorded.
I don't have any working expertise here, but I do know that Dae Lims, the guy who made did an AI remake of SMiLE had ten different models of Brian Wilson.
In contrast, there were only two vocals models for Randy Travis' AI song - one used 12 vocal samples from Travis’ career, and the other used 42 samples from more recent songs.
I am looking for an actual voice changer app that lets me use a voice of my own choosing. I'm tasked with trying to finish a project for a South American client. Unfortunately, the lead singer passed away before some of his tracks were recorded.
I don't have any working expertise here, but I do know that Dae Lims, the guy who made did an AI remake of SMiLE had ten different models of Brian Wilson.
In contrast, there were only two vocals models for Randy Travis' AI song - one used 12 vocal samples from Travis’ career, and the other used 42 samples from more recent songs.
I need something more basic such as to know which app and a how-to.
Samples are not the problem—I have them going back 35 years.
BIAB 2024 Audiophile Mac 24Core/60CoreGPU M2 MacStudioUltra/8TB/192GB Sequoia, M1 MBAir, 2012 MBP Digital Performer11, LogicPro, Finale27/Dorico/Encore/SmartScorePro64/Notion6 /Overture5
I need something more basic such as to know which app and a how-to.
Sure.
Perhaps the most popular tool to use is RVC (Retrieval-Based Voice Conversion). The source code is available on GitHub, and there are a many tutorials on how to use it, as well as tools built to make it easy to install and run.
RVC can be installed locally on your computer, but it seems to have the most support on Windows, as opposed to Mac or Linux OSes. Once you've installed the RVC software package, it'll run locally as a web page. You can then do two things:
Create a voice model by training RVC on audio; and
Convert a source audio file using a voice model
It requires a lot of processing power to train a voice, so you're either going to need a computer with a powerful video card (to use the GPUs in the card), have a whole lot of time, run the training on a virtual machine, such as Google Collab, or hire someone to create the file for you.
On the other hand, converting an audio file using RVC can be done with a plain-old CPU. It'll even happen in real time if your computer's processor is fast enough.
There are a lot of tutorials out there, and even a number of forks of the various flavors of RVC. I haven't actually used RVC myself, but I'll supply links to what look like fairly reasonable tutorials. Cavaeat emptor, cave canem, etc.. You're a lawyer, so you love it when people write stuff in Latin, right?
I picked these particular tutorials because they appear to be targeting the most recent versions of RVC.
There is a web interface for RVC, and Google appears to be preventing Collabs with web interfaces from running in their "Free" tier. So there are a number of older RVC Collabs that no longer work in the "Free" tier.
Here's a video tutorial where someone's created a Google Collab for you. The video shows you how to run the Collab. It automatically installs RVC into the Collab. Once you've done that, you can load up training audio, train a voice model, save it to your Google Drive (so it doesn't go away when you close the Collab), and then apply the trained model to a source audio file. You can also retrain a model, and load a prior model:
Notice that he runs only 100 epochs of training to the model, as he's using a free Collab. It takes a lot of processing (and time) to get a high-quality voice. That's where paying Google for the Collab comes in handy.
I also noticed that he didn't split the training data up into a bunch of 10 second files, as most tutorials would have you do. It apparently speeds up the training time to use smaller chunks, but gives less coherent output. (This particular Collab's code seems to only accept one training file anyway).
This one Google Collab is all you need to create a high-quality RVC voice model, and apply that model to target audio. Easy peasy lemon squeezy.
If you want to run things locally, you'll need to install RVC on your machine. And you're likely to have the easiest time using a Windows PC instead of a Mac or Linux machine.
Here's a tutorial (among many) on how to do that. Again, if you don't have a supported GPU card, you might not be able to do any training (because some versions of the packages don't allow that), but you'll be able to perform conversions using a voice model locally:
Here's a tutorial on how to install a web-based RVC Voice Changer Client. It's aimed more for people who what to use RVC as a real-time voice changer, but it supports file input and output:
There's also free program called Replay that's uses RVC, but has a simpler UI. Here's a tutorial on how to install and use it:
Since I posted all those details, I figured I'd have a go a it myself.
I used Spleeter on a set of early songs by America (Daisy Jane, God of the Sun, Ventura Highway, To Each His Own), and split them into vocals and backing track.
In Audacity, I loaded the isolated vocals, and edited together Gerry Beckley's solo parts for 2:15 of medium/low quality vocals.
I used the previously mentioned Google Collab to create a Gerry Beckley vocal model. It took about 25 minutes to run 200 epochs. A high-quality training would be around 1000 epochs, depending on the training data. Audio upload/download times to Google Collab are fairly slow.
I saved the resulting model to my Google Drive (making sure the code didn't do anything malicious to my drive first!).
I used Spleeter to isolate the vocals and backing track on America's "Tin Man", which is sung by Dewey Bunnell.
I used the same Google Collab using the Gerry Beckley model to convert Dewey Bunnell's isolated lead vocals from "Tin Man". The result was as expected from using dirty stems and a low number of epochs. The voice was clearly Gerry Beckley, but with relatively low sound quality and some poorly converted phonemes.
Obviously I can't post the results.
I also downloaded Replay. Recall that at heart, Replay is just a wrapper around RVC:
Since I don't have supported Nvidia video card, it could only run in CPU mode so it was slow.
I needed to watch the video to figure out how to use it. It didn't help that part of the options can't be seen without scrolling the screen.
I tried creating a voice model. It took Google Collab 25 minutes to create the low-quality model. In that same time, Replay only got three epochs completed, so I cancelled that.
I downloaded the RVC voice model I'd created in Google Collab from Google Drive. It was a .gz file, so it required being decompressed several times using 7Zip. The .pth file contains the model, and is found in the \assets\weights folder.
It took about 17 minutes to covert the audio file using the voice model.
So using the Google Collab is an easy way to try out RVC for free. The one I linked to is by no means the only or best one out there, but it is super easy and runs in the Free tier of Google Collab. And if you've got the paid version of Google Collab, you have access to the RVC GUI, where you can see how the training is doing, or restart training on an existing model.
In the other hand, if you've got a supported Nvidia card, it looks pretty easy to run RVC on your machine, especially if you use something pre-packaged like Replay.
Hey, David, this certainly points me in the right direction.
Not doing Windows anymore but my Mac Studio M2 Ultra's 76 Core GPU should be able to do the necessary crunching—if not, there's a 24 Core CPU.
Although I have a few Spleeter based apps plus Steinberg's SpectraLayers Pro 11, none of that should be necessary. I have a few GB of isolated vocal tracks from this and previous projects. In addition, another band member does a spot on impression of this guy's phrasing (usually, I'm saying, "cut that out—sing like yourself!") so all I need to do is to see if I can get a convincing match of his timbre.
I'll update with my progress. Thanks again!
BIAB 2024 Audiophile Mac 24Core/60CoreGPU M2 MacStudioUltra/8TB/192GB Sequoia, M1 MBAir, 2012 MBP Digital Performer11, LogicPro, Finale27/Dorico/Encore/SmartScorePro64/Notion6 /Overture5
Hey, David, this certainly points me in the right direction.
Glad to hear it!
Quote
Not doing Windows anymore but my Mac Studio M2 Ultra's 76 Core GPU should be able to do the necessary crunching—if not, there's a 24 Core CPU.
That's far more than my puny machine! For a moment I considered picking up a Nvidia card with CUDA so I could try running some of this technology locally, but it looks like I'd have to pay a minimum of $250. That's not a huge amount of money, but I've other toys I'd rather buy first.
Quote
Although I have a few Spleeter based apps plus Steinberg's SpectraLayers Pro 11, none of that should be necessary.
Sorry, I was just describing what I'd done, it case anyone was curious. For zero dollars, it's possible to experiment and get interesting results.
With someone that's already able to do a convincing imitations, plenty of training data, and a high-powered machine, it sounds like you should be good to go.
Here is a song I made using musicfy [video:youtube]Stand by Me (capo 3) Cover Song by CooperSync play along with scrolling guitar chords and lyrics [/video]
We’ve expanded the Band-in-a-Box® RealTracks library with 202 incredible new RealTracks (in sets 449-467) across Jazz, Blues, Funk, World, Pop, Rock, Country, Americana, and Praise & Worship—featuring your most requested styles!
Jazz, Blues & World (Sets 449–455):
These RealTracks includes “Soul Jazz” with Neil Swainson (bass), Mike Clark (drums), Charles Treadway (organ), Miles Black (piano), and Brent Mason (guitar). Enjoy “Requested ’60s” jazz, classic acoustic blues with Colin Linden, and more of our popular 2-handed piano soloing. Plus, a RealTracks first—Tango with bandoneon, recorded in Argentina!
Rock & Pop (Sets 456–461):
This collection includes Disco, slap bass ‘70s/‘80s pop, modern and ‘80s metal with Andy Wood, and a unique “Songwriter Potpourri” featuring Chinese folk instruments, piano, banjo, and more. You’ll also find a muted electric guitar style (a RealTracks first!) and “Producer Layered Guitar” styles for slick "produced" sound.
Country, Americana & Praise (Sets 462–467):
We’ve added new RealTracks across bro country, Americana, praise & worship, vintage country, and songwriter piano. Highlights include Brent Mason (electric guitar), Eddie Bayers (drums), Doug Jernigan (pedal steel), John Jarvis (piano), Glen Duncan (banjo, mandolin & fiddle), Mike Harrison (electric bass) and more—offering everything from modern sounds to heartfelt Americana styles
And, if you are looking for more, the 2025 49-PAK (for $49) includes an additional 20 RealTracks with exciting new sounds and genre-spanning styles. Enjoy RealTracks firsts like Chinese instruments (guzheng & dizi), the bandoneon in an authentic Argentine tango trio, and the classic “tic-tac” baritone guitar for vintage country.
You’ll also get slick ’80s metal guitar from Andy Wood, modern metal with guitarist Nico Santora, bass player Nick Schendzielos, and drummer Aaron Stechauner, more praise & worship, indie-folk, modern/bro country with Brent Mason, and “Songwriter Americana” with Johnny Hiland.
Plus, enjoy user-requested styles like Soul Jazz RealDrums, fast Celtic Strathspey guitar, and Chill Hop piano & drums!
With your version 2025 for Mac Pro, MegaPAK, UltraPAK, UltraPAK+, Audiophile Edition or PlusPAK purchase, we'll include a Bonus PAK full of great new Add-ons FREE! Or upgrade to the 2025 49-PAK for only $49 to receive even more NEW Add-ons including 20 additional RealTracks!
These PAKs are loaded with additional add-ons to supercharge your Band-in-a-Box®!
This Free Bonus PAK includes:
The 2025 RealCombos Booster PAK:
-For Pro customers, this includes 33 new RealTracks and 65+ new RealStyles.
-For MegaPAK customers, this includes 29 new RealTracks and 45+ new RealStyles.
-For UltraPAK customers, this includes 20 new RealStyles.
Look Ma! More MIDI 13: Country & Americana
Instrumental Studies Set 22: 2-Hand Piano Soloing - Rhythm Changes
MIDI SuperTracks Set 44: Jazz Piano
Artist Performance Set 17: Songs with Vocals 7
Playable RealTracks Set 4
RealDrums Stems Set 7: Jazz with Mike Clark
SynthMaster Sounds and Styles (with audio demos)
128 GM MIDI Patch Audio Demos.
Looking for more great add-ons, then upgrade to the 2025 49-PAK for just $49 and you'll get:
20 Bonus Unreleased RealTracks and RealDrums with 20 RealStyles,
FLAC Files (lossless audio files) for the 20 Bonus Unreleased RealTracks and RealDrums
Look Ma! More MIDI 14: SynthMaster,
Instrumental Studies Set 23: More '80s Hard Rock Soloing,
MIDI SuperTracks Set 45: More SynthMaster
Artist Performance Set 18: Songs with Vocals 8
RealDrums Stems Set 8: Pop, Funk & More with Jerry Roe
New! Xtra Styles PAK 20 for Band-in-a-Box 2025 and Higher for Mac!
Xtra Styles PAK 20 for Mac & Windows Band-in-a-Box version 2025 (and higher) is here with 200 brand new RealStyles!
We're excited to bring you our latest and greatest in the all new Xtra Styles PAK 20 for Band-in-a-Box! This fresh installment is packed with 200 all-new styles spanning the rock & pop, jazz, and country genres you've come to expect, as well as the exciting inclusion of electronic styles!
In this PAK you’ll discover: Minimalist Modern Funk, New Wave Synth Pop, Hard Bop Latin Groove, Gospel Country Shuffle, Cinematic Synthwave, '60s Motown, Funky Lo-Fi Bossa, Heavy 1980s Metal, Soft Muted 12-8 Folk, J-Pop Jazz Fusion, and many more!
All the Xtra Styles PAKs 1 - 20 are on special for only $29 each (reg $49), or get all 209 PAKs for $199 (reg $399)! Order now!
Note: The Xtra Styles require the UltraPAK, UltraPAK+, or Audiophile Edition of Band-in-a-Box®. (Xtra Styles PAK 20 requires the 2025 or higher UltraPAK, UltraPAK+, or Audiophile Edition. They will not work with the Pro or MegaPAK version because they need the RealTracks from the UltraPAK, UltraPAK+, or Audiophile Edition.
New! XPro Styles PAK 9 for Band-in-a-Box 2025 and higher for Mac!
We've just released XPro Styles PAK 9 for Mac & Windows Band-in-a-Box version 2025 (and higher) with 100 brand new RealStyles, plus 29 RealTracks/RealDrums!
We've been hard at it to bring you the latest and greatest in this 9th installment of our popular XPro Styles PAK series! Included are 75 styles spanning the rock & pop, jazz, and country genres (25 styles each) that fans have come to expect, as well as 25 styles in this volume's wildcard genre: funk & R&B!
If you're itching to get a sneak peek at what's included in XPro Styles PAK 9, here is a small helping of what you can look forward to: Funky R&B Horns, Upbeat Celtic Rock, Jazz Fusion Salsa, Gentle Indie Folk, Cool '60s Soul, Funky '70s R&B, Smooth Jazz Hip Hop, Acoustic Rockabilly Swing, Funky Reggae Dub, Dreamy Retro Latin Jazz, Retro Soul-Rock Fusion, and much more!
Special Pricing! Until July 31, 2024, all the XPro Styles PAKs 1 - 9 are on sale for only $29 ea (Reg. $49 ea), or get them all in the XPro Styles PAK Bundle for only $149 (reg. $299)! Order now!
XPro Styles PAKs require Band-in-a-Box® 2025 or higher and are compatible with ANY package, including the Pro, MegaPAK, UltraPAK, UltraPAK+, and Audiophile Edition.
New! Xtra Styles PAK 20 for Band-in-a-Box 2025 and Higher for Windows!
Xtra Styles PAK 20 for Windows & Mac Band-in-a-Box version 2025 (and higher) is here with 200 brand new RealStyles!
We're excited to bring you our latest and greatest in the all new Xtra Styles PAK 20 for Band-in-a-Box! This fresh installment is packed with 200 all-new styles spanning the rock & pop, jazz, and country genres you've come to expect, as well as the exciting inclusion of electronic styles!
In this PAK you’ll discover: Minimalist Modern Funk, New Wave Synth Pop, Hard Bop Latin Groove, Gospel Country Shuffle, Cinematic Synthwave, '60s Motown, Funky Lo-Fi Bossa, Heavy 1980s Metal, Soft Muted 12-8 Folk, J-Pop Jazz Fusion, and many more!
All the Xtra Styles PAKs 1 - 20 are on special for only $29 each (reg $49), or get all 209 PAKs for $199 (reg $399)! Order now!
Note: The Xtra Styles require the UltraPAK, UltraPAK+, or Audiophile Edition of Band-in-a-Box®. (Xtra Styles PAK 20 requires the 2025 or higher UltraPAK, UltraPAK+, or Audiophile Edition. They will not work with the Pro or MegaPAK version because they need the RealTracks from the UltraPAK, UltraPAK+, or Audiophile Edition.
New! XPro Styles PAK 9 for Band-in-a-Box 2025 and higher for Windows!
We've just released XPro Styles PAK 9 for Windows & Mac Band-in-a-Box version 2025 (and higher) with 100 brand new RealStyles, plus 29 RealTracks/RealDrums!
We've been hard at it to bring you the latest and greatest in this 9th installment of our popular XPro Styles PAK series! Included are 75 styles spanning the rock & pop, jazz, and country genres (25 styles each) that fans have come to expect, as well as 25 styles in this volume's wildcard genre: funk & R&B!
If you're itching to get a sneak peek at what's included in XPro Styles PAK 9, here is a small helping of what you can look forward to: Funky R&B Horns, Upbeat Celtic Rock, Jazz Fusion Salsa, Gentle Indie Folk, Cool '60s Soul, Funky '70s R&B, Smooth Jazz Hip Hop, Acoustic Rockabilly Swing, Funky Reggae Dub, Dreamy Retro Latin Jazz, Retro Soul-Rock Fusion, and much more!
Special Pricing! Until July 31, 2024, all the XPro Styles PAKs 1 - 9 are on sale for only $29 ea (Reg. $49 ea), or get them all in the XPro Styles PAK Bundle for only $149 (reg. $299)! Order now!
XPro Styles PAKs require Band-in-a-Box® 2025 or higher and are compatible with ANY package, including the Pro, MegaPAK, UltraPAK, UltraPAK+, and Audiophile Edition.
Video: Band-in-a-Box® 2025 for Mac®: VST3 Plugin Support
Band-in-a-Box® 2025 for Mac® now includes support for VST3 plugins, alongside VST and AU. Use them with MIDI or audio tracks for even more creative possibilities in your music production.
Band-in-a-Box® 2025 for Macs®: VST3 Plugin Support
Video: Band-in-a-Box® 2025 for Mac®: Using VST3 Plugins
One of our representatives will be happy to help you over the phone. Our hours of operation are from
6:00AM to 6:00PM PST (GMT -8) Monday thru Friday, and 8:00AM to 4:00PM PST Saturday. We are closed Sunday. You can also send us your questions via email.
One of our representatives will be happy to help you on our Live Chat or by email. Our hours of operation are from
6:00AM to 6:00PM PST (GMT -8) Monday thru Friday; 8:00AM to 4:00PM PST (GMT -8) Saturday; Closed Sunday.
Dansk
Deutsch - Windows
Español
Français - Windows
Italiano - Windows
Nederlands
Polski
Português
Svenskt
русский
Japanese
Simplified Chinese
Traditional Chinese
Korean