MSST Bible

Ripple/Capcut/SAMI-Bytedance/Volcengine/BS-RoFormer (2-4 stem)

Page 137 of 228 · Open the original GDoc ↗

(Ripple is discontinued since 31 January 2026)

Output quality in Ripple is: 256kbps M4A (320kbps max) and lossless (introduced later). 50MB upload limit, 4 stems

Min. iOS version: 14.1

Ripple is only for US region (which you can change, more below)

Ripple no longer separates stems (there's an error "couldn't complete processing please try again")

Ripple for iOS: https://apps.apple.com/us/app/ripple-music-creation-tool/id6447522624

Capcut for Android: https://play.google.com/store/apps/details?id=com.lemon.lvoverseas

(separation only for Pro, Indian users sometimes via VPN)

Capcut a.k.a. Jianying (2 stems) works also on Windows (only in Jianying Pro, separation option is available)

Can be used instead of Ripple if you're on unsupported iOS below 14.1 or don’t have iOS. To get Ripple you can also use a virtual machine remotely instead (instructions below). Ripple can also be run on your M1 Mac using app sideloading (instructions below).

 

Ripple = better quality than CapCut as of now (and fullband)

with fixed the click/artifacts using cross-fade technique between the chunks.

 

Capcut = “the results are really low quality but if you export the instrumental and invert it with the lossless track, you will get the vocals with the noise which is easy to remove with mdx voc ft for example, then you can invert the lossless processed vocals with the original and have it in better quality.

The vocals are very clean from cap cut, almost no drum bleed”

 

Ripple and Capcut uses SAMI-Bytadance arch (later known as BS-Roformer), but it’s a different model with worse SDR than on the leaderboard. It was developed by Bytedance (owner of TikTok) for MDX23 competition, and holds the top of our MVSEP leaderboard. It was published on iOS and for the US region as “Ripple - Music Creation Tool” app. Furthermore, it's a multifunctional app for audio editing, which also contains a 4 stem separation model. Similar situation with Capcut (which is 2 stems only IRC). The model itself is not the same as for MDX23 competition (SAMI ByteDance v1.0), as they said, models for apps were trained on 128kbps mp3 files to avoid copyright issues, but it’s the same arch, just scores a bit lower (even when exported losslessly for evaluation). SDR for Ripple is naturally better than for Capcut.

 

Seems like there is no other Pro variant for Capcut Android app, so you need to unlock regular version to Pro.

At least the unlocked version on apklite.me have a link to the regular version, so it doesn't seem to be Pro app behind any regional block. But -

"Indian users - Use VPN for Pro" as they say, so similar situation like we had on PC Capcut before. Can't guarantee that unlocked version on apklite.me is clean. I've never downloaded anything from there.

 

Bleeding

 

Bas Curtiz found out that decreasing volume of mixtures for Ripple by -3dB (sometimes -4dB) eliminates problems with vocal residues in instrumentals in Ripple. Video

 

This is the most balanced value, which still doesn't take too many details out of the song due to volume attenuation.

Other good values purely SDR-wise are -20dB>-8dB>-30dB>-6dB>-4dB> /wo vol. decr.

 

The method might be potentially beneficial for other models, and probably work best for the loudest tracks with brickwalled waveforms.

 

The other stem is gathered from inversion to speed up the separation process. The consequence is bleeding in instrumentals.

- If you suffer from bleeding in other stem of 4 stems Ripple, beside decreasing volume by e.g. 3/4dB also “when u throw the 'other stem' back into ripple 4 track split a second time, it works pretty well [to cancel the bleeding]”

 

The forte of the Ripple is currently vocals - the algo is very good at differentiating what is vocals and what is not, although they can sound “filtered” at times.

 

Currently, the best SDR for public model/AI, but it gives the best results for vocals in general. For instrumentals, it rather doesn’t beat paid Dango.ai (and rather not KaraFan and HQ_3 or 1648/MDX23C fullband too).

 

It's good for vocals, also for cleaning vocal inverts, and surprisingly good for e.g. Christmas songs, (it handled hip-hop, e.g. Drake pretty well). It's better for vocals than instrumentals due to residues in other stem - bass is very good, drums also decent, kicks even one if not the best out of all models, as they said some fine-tuning was applied to drums stem. Vocals can be used for inversion to get instrumentals, and it may sound clean, but rather not as good as what 2 stem option or 3 stem mixdown gives as output is lossy.

 

Capcut (2 stems only)

https://www.capcut.cn/

It is a new Windows and Android app which contains the same arch as Ripple inst/vocal, but lower quality model, and without an option of exporting 4 stems.

 

It normalizes the input, so you cannot use Bas’ trick to decrease volume by -3dB to workaround the issue of bleeding like in Ripple (unless you trick out the CapCut, possibly by adding some loud sound in the song with decreased volume).

 

“At the moment the separation is only available in Chinese version of Windows app which is jianyingpro, download available at capcut.cn [probably here - it’s where you’re redirected after you click “Alternate download link” on the main page, where download might not work at all]

 

Some people cannot find the settings on this screen in order to separate.

Separation doesn't require sign up/login, but exporting does, and requires VIP, which is paid depending on whether you’re from rich or poor country, then it’s free.

 

- There’s a workaround for people not able to split using Capcut for Windows in various regions.

 

- Bas Curtiz' new video on how to install and use Capcut for separation incl. exporting:

https://www.youtube.com/watch?v=ppfyl91bJIw

 

"It's a bit of a hassle to set it up, but do realize:

- This is the only way (besides Ripple on iOS) to run ByteDance's model (best based on SDR).

- Only the Chinese version has these VIP features; now u will have it in English

- Exporting is a paid feature (normally); now u get it for free

 

The instructions displayed in the video are also in the YouTube description."

 

- mitmproxy script allowing to save to FLAC instead of AAC (although it just reencodes from AAC 113kbps with 15.6kHz lowpass filter). It’s a bit more than script. See the full tutorial.

 

- For some people using mitmproxy scripts for Capcut (but not everyone), they “changed their security to reject all incoming packet which was run through mitmproxy. I saw the mitmproxy log said the certificate for TLS not allowed to connect to their site to get their API. And there are some errors on mitmproxy such as events.py or bla bla bla... and Capcut always warning unstable network, then processing stop to 60% without finish.” ~hendry.setiadi

“At 60% it looks like the progress isn't going up, but give it idk, 1 min tops, and it splits fine.” - Bas

 

“in order to install pydub within mitmproxy, you additionally need to:

open up CMD

pip install mitmproxy

pip install pydub”

 

- IntroC created a script for mitmproxy for Capcut allowing fullband output, by slowing down the track. Video

 

 

Older Capcut instruction:

The video demonstration of below:

0. Go offline.

1. Install the Chinese version from capcut.cn

2. Use these files copied over your current Chinese installation in:

C:\Users\(your account)\AppData\Local\JianyingPro

Don’t use English patch provided below (or the separation option will be gone)

3. Now open CapCut, go online after closing welcome screen, happy converting!

4. Before you close the app, go offline again (or the separation option will be gone later).

! Before reopening the app, go offline again, open the app, close welcome screen, go online, separate, go offline, close. If you happen to missed that step, you need to start from the beginning of the instruction.

 

(no longer works after 4.6 to 4.7 update, as it freezes the app) The only thing that seems to enable vocal separation without requiring replacing everything, is to replace that SettingsSDK folder contents inside User Data. It's probably the settings_json file inside responsible for that.

FYI - the app doesn’t separate files locally.

 

The quality of separation vs Capcut is not exactly the same as Ripple. Seeing by spectrograms, there is a bit more information in vocals in Capcut, while Ripple has a bit more information in spectrum in instrumentals.

 

 

Separated vocal file is encrypted and located in C:\Users\yourusername\AppData\Local\JianyingPro\User Data\Cache\audioWave”

 

The unencrypted audio file in AAC format is located at \JianyingPro Drafts\yourprojectname\Resources\audioAlg (ends with download.aac)

 

“To get the full playable audio in mp3 format, a trick that you can do is drag and drop the download.aac file into Capcut and then go to export and select mp3. It will output the original file without randomisation or skipping parts”

 

(although it resulted in VIP option disappearing but Bas somehow managed to integrate it in his new video tutorial, and it started to work, English translation isn't the culprit of the problem, but if you use both language pack and SettingsSDK folder from above)

You can replace the zh-Hans.po file with English one to have English language on Chinese version of the app possessing separation feature in:

jianyingpro/4.6.1.10576/Resources/po

 

 

While you can’t use that language pack, you can always use Google Translate to transform Chinese into your own language on a screen of your smartphone.

https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQwk_qynMHMwquSfQZFrrn30F355Ihta_GHQNo7vhnPUhfjj-kUiqSRBiLQbPlgmB5Gqro&usqp=CAU

https://support.google.com/translate/answer/6142483?hl=en&co=GENIE.Platform%3DDesktop

 

“Trying out capcut, the quality seems the same as the Ripple app (low bitrate mp3 quality)

at least the voice leftover bug is fixed, lol”

 

Random vocal pops from Ripple are fixed here.

Also, it still has the same clicks every 25 seconds as before in Ripple.

Capcut adds 1024 extra samples at the beginning, and 16 extra samples at the end of the file.

 

How to change region to US

in order to make Ripple work on iOS

in Apple App Store to make "Ripple - Music Creation Tool" (SAMI-Bytedance) work.

https://support.apple.com/en-gb/HT201389

 

- Bas' guide to change region to US for Ripple on iOS

 

https://www.bestrandoms.com/random-address-in-us

Or use this Walmart address in Texas, the number belongs to an airport.

Do it in App Store (where you have the person-icon in top right).

You don't have to fill credit cards details, when you are rejected,

reboot, check region/country... and it can be set to the US already.

Although, it can happen for some users that it won't let you download anything forcing your real country.

 

"I got an error because the zip code was wrong (I did enter random numbers) and it got stuck even after changing it.

So I started from the beginning, typed in all the correct info, and voilà"

 

If ''you have a store credit balance; you must spend your balance before you can change stores''.

 

It needs (an old?) a simcard to log your old account out if necessary