For those following the progress of this project, I'd hoped that I'd have a final version of my synthetic singer program completed back in March. However, it had a bad case of the mumbles, and I headed back to the drawing board to rewrite it. It's been eating my spare time since then.
I spent far too much time trying to get synthesized plosives and fricatives working. Then I listened to earlier versions of the program, and realized how much better they sounded using samples instead. So all that work got tossed out, and I ended up writing the code from scratch... again.
Just the other day, I got the code to where it is again reading MusicXML files and generating .wav files. There's still a lot of work to do, but the end is (hopefully) in sight.
I've been using Twinkle, Twinkle, Little Star" as my demo song, and here's the most current version, warts and all. For example, I haven't yet figured out why it can't say "world" correctly.
As a change of pace, I decided to do my own version of Daisy Bell, one of the first examples of computer generated singing. It's still missing some phonemes, so I've cheated in spots. For example, the /G/ is actually /D SH/. The lyrics were automatically converted to phonemes, but I did some replacement by hand because the allophonic replacement code isn't working yet.
I also added some compression and reverb because everything sounds better with reverb. Just to let you know, it doesn't sound quite this good out of the box... But it sounds exactly as bad .
Anyway, here's synSinger singing "Daisy", as well as the 1961 version by Max Mathews, John Kelly, and Carol Lochbaum, which I found on Perry Cook's website. To make comparison easier, they're in the same key and tempo:
I've always been curious about what software was used to generate the computer performance 55 years ago. It turns out that the data was hand-coded into the computer. That explains why I was never able to find any references to the text-to-singing program... It never existed!
As always, comments (positive or negative) are always appreciated.
I'll confess - that's one thing I hadn't considered.
But that reminds me that I do need to add another feature - using another sound source instead of a glottal pitch. Remember the cellos voice on the MacInTalk?
I've never heard that original recording, absolutely insane that that was 1961... I also can't believe that you coded this yourself, that's crazy!! Amazing work. Your version is sounding very good. Keep us updated on how you progress with "world"!
Wow. Amazing you coded that yourself. I can't even begin grasping how you did that. Like how do you pick the right sample for a specific part of a word, or did you sample sounds and complete words? Individual letters can sound different when used in combination with other letters...
There are a couple different ways that vocal synthesis can be approached. The method that I'm using is called "formant synthesis", and is one of the oldest techniques that's been used for computer synthesis.
In English, there are approximately 40 distinct "sounds" that make up the language, are referred to as "phonemes".
There are different phonetic systems, but one of the simplest for American English is the "Arpabet", which uses plain text characters to represent phonemes. For example, the word "dictionary" would be written:
I use the CMU Dictionary to convert English into phonemes. If a word isn't found in the dictionary, I fall back to a public domain program called "Reciter" which guesses how to pronounce the word.
Phonemes are turned into sound by simulating the human vocal tract electronically. Before explaining that, let give give a (very simplified) explanation of how we create vocal sounds.
As air passes through the glottal folds, the folds vibrate and create sound. By controlling the tension (which in turn controls the length of the folds' opening), we can raise and lower the pitch we create. This pitch is called the fundamental frequency (F0), which we hear at the pitch of the voice.
This pitched glottal pulse (which resembled a kazoo sound) passes through our mouth. We use our tongue to create one or more resonating chambers that reinforce specific frequencies in the glottal pitch. These reinforced frequencies are called "resonances", and are what distinguishes one phonemes from another.
For example, (borrowing from the SoftVoice website), here are a number of vowel sounds, and the frequencies of resonance for the "average" male speaker in Hz:
In the phoneme /IY/ (as in beet), the first formant (F1) is at 270Hz, the second (F2) is at 2300Hz, and the third (F3) is at 3000Hz. Again, these formants don't alter the fundamental pitch, and remain fixed no matter what pitch you're singing.
Some phonemes are obviously more complex than that. For example, the phonemes /IY/ and /UW/ are diphthongs, and consist of two distinct targets. But I'm digressing...
To do this electronically, I generate a waveform that approximates a glottal pulse at the desired pitch, and pass it through a series of bandpass filters - one for each formant frequeny - to resonate at the desired frequencies. The output is a rough approximation of the sound.
Changing the pitch of the glottal pulse changes the pitch that's being sung. Changing the resonating filters to new values changes the phoneme that's being sung.
Some sounds (like the frication in the /F/ or the plosive in the /T/) are created by means different than described above. I used to synthesize them, but I now use digital samples because they give better results.
Very little work that I've done are my own ideas. I've borrowed heavily from the published work of Dennis Klatt, who wrote one of the first text-to-speech computer programs.
If you're curious, I'd highly recommend downloading this Formant Synthesis Demo. Click and drag in the area marked F1/F2 (formants one and two) and you'll get a good idea how this works.
Thanks for you answer, David. It did bring me more understanding of the subject of vocal synthesis. I will visit the sites you mentioned. Please keep us informed about your progress with this project. I find it very interesting.
The various parameters of vibrato - depth, speed, minimum note length and delay before start - can be specified.
I've also worked on clearing up a number of phonemes, including the /ERL/ in "world", although the main problem with that word is the trailing /D/.
This version of synSinger is written in Lua, and isn't particularly fast - it renders audio about about half the speed of the song. I still haven't been able to spend time to figure out how to create a stand-alone executable. I need to spend some time with the squish documentation.
There are still instances where it will "squelch" when parameters change to quickly, and some of the phonemes still need more attention. But for the most part, the output seems to be fairly acceptable, although not always intelligible. Truth be told, it's only incrementally better than prior versions.
I've also created a "female" voice for synSinger by mapping phonemes formants from average male phoneme space to average female phoneme space. It also modifies some other parameters, such as raising the pitch up an octave (so "she" doesn't sound like a chain smoker), adding more breath noise, altering the glottal pulse, and modifying the formant bandwidths based on a shorter larynx. But it still sounds a bit cheesy, because female voices aren't something formant synthesis does that well:
Band-in-a-Box 2026 Video: The Newly Designed Piano Roll Window
In this video, we explore the updated Piano Roll, complete with a modernized look and exciting new features. You’ll see new filtering options that make it easy to focus on specific note groups, smoother and more intuitive note entry and editing, and enhanced options for zooming, looping, and more.
Band-in-a-Box 2026 Video: AI Stems & Notes - split polyphonic audio into instruments and transcribe
This video demonstrates how to use the new AI-Notes feature together with the AI-Stems splitter, allowing you to select an audio file and have it separated into individual stems while transcribing each one to its own MIDI track. AI-Notes converts polyphonic audio—either full mixes or individual instruments—into MIDI that you can view in notation or play back instantly.
Bonus PAK and 49-PAK for Band-in-a-Box® 2026 for Windows®
With your version 2026 for Windows Pro, MegaPAK, UltraPAK, UltraPAK+, Audiophile Edition or PlusPAK purchase, we'll include a Bonus PAK full of great new Add-ons for FREE! Or upgrade to the 2026 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 2026 RealCombos Booster PAK:
-For Pro customers, this includes 27 new RealTracks and 23 new RealStyles.
-For MegaPAK customers, this includes 25 new RealTracks and 23 new RealStyles.
-For UltraPAK customers, this includes 12 new RealStyles.
MIDI Styles Set 92: Look Ma! More MIDI 15: Latin Jazz
MIDI SuperTracks Set 46: Piano & Organ
Instrumental Studies Set 24: Groovin' Blues Soloing
Artist Performance Set 19: Songs with Vocals 9
Playable RealTracks Set 5
RealDrums Stems Set 9: Cool Brushes
SynthMaster Sounds Set 1 (with audio demos)
Android Band-in-a-Box® App (included)
Looking for more great add-ons, then upgrade to the 2026 49-PAK for just $49 and you'll get:
20 Bonus Unreleased RealTracks and RealDrums with 20 RealStyle.
FLAC Files (lossless audio files) for the 20 Bonus Unreleased RealTracks and RealDrums
MIDI Styles Set 93: Look Ma! More MIDI 16: SynthMaster
MIDI SuperTracks Set 47: More SynthMaster
Instrumental Studies 25 - Soul Jazz Guitar Soloing
Artist Performance Set 20: Songs with Vocals 10
RealDrums Stems Set 10: Groovin' Sticks
SynthMaster Sounds & Styles Set 2 (sounds & styles with audio demos)
Join Tobin as he takes you on a tour of the new user interface in Band-in-a-Box® 2026 for Windows®! This modern GUI redesign offers a sleek new look with updated toolbars, refreshed windows, and a smoother workflow. The brand-new side toolbar puts track selection, the MultiPicker Library, and other essential tools right at your fingertips. Plus, our upgraded Multi-View lets you layer multiple windows without overlap, giving you a highly flexible workspace. Many windows—including Tracks, Piano Roll, and more—have been redesigned for improved usability and a cleaner, more intuitive interface, and more!
Introducing XPro Styles PAK 10 – Now Available for Windows Band-in-a-Box 2025 and Higher!
We've just released XPro Styles PAK 10 for Windows & Mac Band-in-a-Box version 2025 (and higher) with 100 brand new RealStyles, plus 28 RealTracks and RealDrums!
Few things are certain in life: death, taxes, and a brand spankin’ new XPro Styles PAK! In this, the 10th edition of our XPro Styles PAK series, we’ve got 100 styles coming your way! We have the classic 25 styles each from the rock & pop, jazz, and country genres, and rounding out this volume's wildcard slot is 25 styles in the Praise & Worship genre! A wide spanning genre, you can find everything from rock, folk, country, and more underneath its umbrella. The included 28 RealTracks and RealDrums can be used with any Band-in-a-Box® 2026 (and higher) package.
Here’s just a small sampling of what you can look forward to in XPro Styles PAK 10: Soft indie folk worship songs, bumpin’ country boogies, gospel praise breaks, hard rockin’ pop, funky disco grooves, smooth Latin jazz pop, bossa nova fusion, western swing, alternative hip-hop, cool country funk, and much more!
Special offers until December 31st, 2025!
All the XPro Styles PAKs 1 - 10 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.
Introducing Xtra Styles PAK 21 – Now Available for Windows Band-in-a-Box 2025 and Higher!
Xtra Styles PAK 21 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 Xtra Styles PAK installment—the all new Xtra Styles PAK 21 for Band-in-a-Box version 2025 (and higher)!
Rejoice, one and all, for Xtra Styles PAK 21 for Band-in-a-Box® is here! We’re serving up 200 brand spankin’ new styles to delight your musical taste buds! The first three courses are the classics you’ve come to know and love, including offerings from the rock & pop, jazz, and country genres, but, not to be outdone, this year’s fourth course is bro country! A wide ranging genre, you can find everything from hip-hop, uptempo outlaw country, hard hitting rock, funk, and even electronica, all with that familiar bro country flair. The dinner bell has been rung, pickup up Xtra Styles PAK 21 today!
In this PAK you’ll discover: Energetic folk rock, raucous train beats, fast country boogies, acid jazz grooves, laid-back funky jams, a bevy of breezy jazz waltzes, calm electro funk, indie synth pop, industrial synth metal, and more bro country than could possibly fit in the back of a pickup truck!
Special offers until December 31st, 2025!
All the Xtra Styles PAKs 1 - 21 are on special for only $29 each (reg $49), or get all 21 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 21 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.
Introducing XPro Styles PAK 10 – Now Available for Mac Band-in-a-Box 2025 and Higher!
We've just released XPro Styles PAK 10 for Mac & Windows Band-in-a-Box version 2025 (and higher) with 100 brand new RealStyles, plus 28 RealTracks and RealDrums!
Few things are certain in life: death, taxes, and a brand spankin’ new XPro Styles PAK! In this, the 10th edition of our XPro Styles PAK series, we’ve got 100 styles coming your way! We have the classic 25 styles each from the rock & pop, jazz, and country genres, and rounding out this volume's wildcard slot is 25 styles in the Praise & Worship genre! A wide spanning genre, you can find everything from rock, folk, country, and more underneath its umbrella. The included 28 RealTracks and RealDrums can be used with any Band-in-a-Box® 2026 (and higher) package.
Here’s just a small sampling of what you can look forward to in XPro Styles PAK 10: Soft indie folk worship songs, bumpin’ country boogies, gospel praise breaks, hard rockin’ pop, funky disco grooves, smooth Latin jazz pop, bossa nova fusion, western swing, alternative hip-hop, cool country funk, and much more!
Special offers until December 31st, 2025!
All the XPro Styles PAKs 1 - 10 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.
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