New 6-stem model added
UVR Online posts
Finishing up the Audio editor
The audio editor is almost ready!
Latest changes:
- improved UI
- improved tone change when exporting audio
- added a switch in the side menu to select waveform detail
Now we can move on to developing a new version of Vocal remover page. But first, we ask you to check the quali...
2025-08-27 09:23:56 +0000 UTC
View Post
New audio editor test
Right now, we’re finishing work on the Audio editor. This is an improved version of the old pitch shifter: https://uvronline.app/transpose<...
2025-08-04 02:35:20 +0000 UTC
View Post
Coming soon: a new version of the website
We recently started developing a new website. Switching to modern technologies will allow us to implement many features you’ve asked for, as well as make the site faster and more user‑friendly.
Right now, we’re finishing work on the Audio editor. In a couple of days, we’ll publish a link for testing. Once the audio editor is ready, we’ll move on to implementing the main feature – the Vocal remover.
2025-07-28 08:34:13 +0000 UTC
View Post
New feature: Interactive history
The new version is available for testing!
1. History is now interactive.
In the desktop version you will find the history on the right side, in the mobile version at the bottom of the page under comments.
In the desktop version you will find the history on the right side, in the mobile version at the bottom of the page under comments.
2. Now after post-processing you can see both the model name and the ensemble algorithm
Keep in mind that:
- at the very ...
2025-06-06 13:25:42 +0000 UTC
View Post
Weekly report
1. Added a new Lead and Backing vocal separator. Technically, it's not a model, but two models: Karaoke by becruily and Vocal big beta5e by unwa.
2025-05-18 06:05:44 +0000 UTC
New Karaoke model
An improved version of the Mel-RoFormer Karaoke model has been added. This model is designed to extract lead vocals only.
2025-04-17 08:09:53 +0000 UTC
Weekly report
1. A new Mel-RoFormer by unwa v1e+ model has been added. It removes vocals very gently while preserving instruments. It is recommended to use it with correct_phase post-processing.
2. Mel-RoFormer by Kim & unwa ft3 and some other models are hidden. As before you can find them here: https://uvronline.app/ai?hp&test<...
2025-04-06 09:29:17 +0000 UTC
View Post
Weekly report
1. A new vocal model Mel-RoFormer by Kim & unwa ft3 has been added. It's a preview model. The results can be improved. If you like this model, we will keep it.
2. The site administrator will be on vacation for 2 weeks. After that, the site development will continue and you will see even more new models. Please don't miss us 😉
Weekly report
1. Added a new V7 version of the instrumental model by Gabox. Compared to the previous version, it has less muddiness (better inst. fullness).
2. The previous models were hidden. You can find them using this link: https://uvronline.app/ai?hp&test
Weekly report
Added two new models:
1. De-reverb (Mono) - another version of the previous model by anvuew.
2. Mel-RoFormer by Gabox Fv6 - a new version of the vocal removal model.
Weekly report
Two models have been added.
• New BS-RoFormer 4 stems model (bass, drums, other, vocals)
• De-reverb by anvuew
Weekly report
1. A new Other section has been added.
2. New model for male and female vocal separation has been added there. This is still beta version, it will be improved in the future.
3. The Phantom Center Extractor model has been moved to the Other.
2025-01-06 04:50:55 +0000 UTC
Happy new year 🎄🎄🎄
We would like to congratulate you on the coming year 2025!
New audio enhancement model
We have added the Apollo Universal model by Lew. This model is designed to improve low quality audio files of mp3 and other formats. You can find it in the Restoration section.
New vocal model
Added a new model for quality vocal isolation.
Weekly report
1. At subscription levels Standard and above, the maximum song length for RoFormer models has been increased to 20 minutes.
2. Three new models have been added:
• Mel-RoFormer SYHFTV4Force - one of the best models for vocal isolation
• Mel-RoFormer SYHFTV5Beta - next version (beta)
• Mel-RoFormer by unwa v1e - one of the best models for vocal removal....
2024-11-22 05:06:02 +0000 UTC
View Post
New feature: Vocal enhancer
Now you can greatly improve isolated vocals with new post-processing. It is available for most models.
2024-11-09 06:25:28 +0000 UTC
A new model has been added, please test and compare
The Mel-RoFormer model by unwa v2 has just been added! We're asking you to test it out and vote.
New Mel-RoFormer vocal removal model
Introducing the new version of Mel-RoFormer, which can really be called the best vocal removal model in the world. This is a huge step forward from the previous version! The new model removes vocals less aggressively, reminiscent of the sound of the old UVR models, but it does it in a much better way.
2024-10-25 06:18:06 +0000 UTC
Similarity / Phantom Center Extractor model
Added a center channel extraction model. It is very similar to the Center Extract effect in iZotope RX, but works better.
It separates the song into two tracks:
mid refers to the phantom center, meaning the part that contains instruments and vocals perceived in the center.
side refers to everything perceived in stereo.
New Guitar models have been added!
The second model is desi...
2024-09-21 06:51:19 +0000 UTC
View Post
Piano model update
The piano isolation model has been updated. It now works significantly better.
Old version:
piano_test_v1.mp3
New version:piano_test_v2.mp3
New MDX HQ5 model
The new MDX HQ5 beta model is now online! This model is designed to separate music and vocals.
