Cantai isn’t just another sound library—it’s a breakthrough in vocal synthesis. Powered by advanced machine learning, Cantai captures the subtlety of real human singing, from delicate dynamics to expressive phrasing. Whether you’re writing an intimate solo aria, a soaring choral passage, or a dramatic operatic scene, Cantai delivers voices that sound authentic, emotional, and true to your score. Note: Cantai's voice quality is continually improving, and the refined production versions featured in our online demos will be available soon.

Also included in

MuseSounds Pro

Premium sound libraries for modern scoring inside MuseScore Studio.

Previews

What’s New?

1.0.1

- NEW voices added - Updated menu structure for easier navigation - Improved rendering efficiency and performance NOTE to current users: The new menu structure supports a growing number of voices. As a result, existing scores will need Cantai voices reassigned the next time they are opened. This is a one-time occurrence that shouldn’t be required with future releases.

Description

Cantai isn’t just another sound library—it’s a breakthrough in vocal synthesis. Powered by advanced machine learning and fully integrated into MuseScore Studio, Cantai not only captures the subtlety of real human singing, from delicate dynamics to expressive phrasing, but also sings your lyrics with clarity and emotion. Whether you’re writing an intimate solo aria, a soaring choral passage, or a dramatic operatic scene, Cantai delivers voices that sound authentic, expressive, and true to your score. Cantai is available through subscription and includes Solo Soprano, Alto, Tenor, and Bass voices, as well as full choir ensembles. Rendering is managed intelligently to ensure optimal performance and system availability. Usage Note: Cantai includes up to 180 minutes of rendering time per week, which resets every Monday. Because Cantai renders automatically as you write, your minutes can be used up quickly. Previously rendered sections will still play back even after the limit is reached. To conserve minutes, switch to manual rendering using the steps here: https://handbook.musescore.org/sound-and-playback/musesounds/online-sounds

Voice modeling library integrated into notation
English and Latin lyric support with more languages supported soon
Seamless integrated with MuseScore Studio and Muse Hub
Realistic phrasing and dynamic expression
Natural breath handling and syllable shaping
Includes Choir and Solo soprano, alto, tenor and bass

I really like the choir voices overall. The soloists are hit or miss.

gleek4ever

1.0.1

Probably the only positive outcome of machine learning technology! I have used this for my students who have little experience before a concert as an aural guide. Thanks for this! I wish it could be a single time fee, like the other major notation software, but I will take what I can get!

anymous

1.0.1

The update brings new solo voices compared to 1.0.0. However, the new voices don't sync up in time with the original voices. So in a SATB setting, new voices and old voices are not compatible. I hope this can be fixed quickly as it does affect the functionality. For record, the original voices that are in sync are: Lucia (Soprano), Karolyn (Mezzo), Giovanni Opera (Tenor), Rigoletto (Baritone) Edit: Hi Cantai team, there is a misunderstanding in the response given. I am not talking about menus and reassigning, I am referring to the actual time words are being sung by the various voices. The new and old voices are off by around 200 milliseconds, which causes a real mess when played back together in an SATB setting.

gaseous-fly87

1.0.1

All of these voices are gorgeous! I find myself using them a lot for dramatic or thematic orchestral works. The sound quality is tip top, but there are a few bugs I must work around. One is sometimes the lyrics I type don't match the sound, so I have to artificially get it to resync by removing a word, then readding it, or sometimes I must just remove the word entirely. Also, for a song one of the main words was "Tears" but it registered it as the "tear something apart" one. It would also be very useful to control some of the sounds. For instance, in a song the singer at the end of a dramatic high note kind of did a glissando squeak up, which sounded perfect, but the next time it synced it got rid of it. Just a few things to keep in mind, it's overall a great product and I'm excited to see the future updates! --Edit-- That all said, the Men and Women choir sound very unrealistic and harsh. I think what you tried to do was combine and meld already recorded solo voices into a choir, and that never works. I would highly recommend you record a real choir. I know its expensive, but a real 50-person choir would be awesome and it would easily take a spot in my orchestral palette. Thanks!

Fantasy Legend

1.0.0

As a choir director, this is awesome. I'm just a bit bothered by the fact that Latin text is sung with English pronunciation

Beezart73

1.0.0

I've been waiting for this for awhile, so it's awesome that it's finally hear. I write hymns and score public domain hymns to make them singable, and this helps tremendously. It is so much better than the old "oohs" and "aahs". A few issues/features that I hope will be addressed: 1.) I wish I had the ability to have the program select which verse I want it to sing. As it is, I have to score the music. Put in the lyrics for verse 1. Export the mp3. Delete the lyrics and put in the lyrics for verse 2 and rinse and repeat. It's doable, but a pain. 2.) I hope the program does a better job of singing shortened words. It really struggles with heav'n, and forgiv'n for example in the score I'm currently working on. It seems like when it doesn't know what to do, it just gives sings basically "aahs". This is really annoying as one can probably guess how often words like this show up in hymns :) Regardless, thumbs up for the program. I know it's a work in progress and progress will be made. Thanks!

miniature-corgi566

1.0

As a classical composer with great grandchildren and very little money, the fact that my low-end laptop can sing my music brings me near to tears. I could quibble about a few things, but it seems as though the developer has plans that will address those minor (to me) issues.

sophisticated-eagle827

1.0.0

It's amazing how tools are improving every single day. I've been looking for a tool like this that's compatible with Musescore and I don´t have to export xml, or cut parts, etc... It's kind of dissapointed the only laguages available are english and latín. My native language is spanish and also Irecently write something in italian and I wanted to give it a shot, I gave me an idea but of course with english accent. Also I try with some english songs and it was much better but still need to fix some bugs bc is not recognizing some words... Also, I couldn't export an mp3 file, to show a sample to someone :( I think is promising and definetely I'll keep an eye on updates, but at the moment I don't really think it is worth to pay a monthly subscription at the moment, but if we improve the languages most likely I'll be there :)

repentant-toad987

At the time of this software being released, I just so happened to have completed a choral symphony, and since I unfortunately don’t have singers at my immediate disposal (as with a lot of composers, I’m sure), it’s nice to get some immediate feedback regarding the vocal music composers write. While I’m sure that the voices will be improved upon in due time, my only main gripe is the monthly subscription; I had actually preordered a one-time paid lifetime subscription, so that I wouldn’t have to worry about putting aside money every month; this is quite detrimental, especially for the younger composers who have a specialty in choral music; other than this though, it has delivered quite beautifully for me and I can’t wait for what’s to come in the future!

MaestroHenry18

1.0.0

I’ve always wished for a product like this, so in a way it really caught my attention. Unfortunately, it doesn’t quite deliver. The biggest drawback is the monthly subscription. I might understand a one-time payment, but paying every month for something of this kind simply isn’t worth it. Another problem is the soprano range, which is surprisingly poor. And I can’t overlook the English accent present in all voices. These issues make the product feel unfinished, almost as if it wasn’t tested with real musicians in mind. If these shortcomings were addressed, I genuinely believe it could become one of the best-selling products on MuseScore. But if the developers don’t fix them, I’m certain a better competitor will take its place soon enough.

Kem_cz
Works With
MuseScore Studio
Rating
71%
Version
1.0.1
Released
2026

You May Also Like