MVSEP Logo
  • Home
  • News
  • Plans
  • Demo
  • Tools
  • Create Account
  • Login
  • Theme
    Model Selector
    Language
    • English
    • Русский
    • 中文
    • اَلْعَرَبِيَّةُ
    • Polski
    • Portugues do Brasil
    • Español
    • 日本語
    • Français
    • Oʻzbekcha
    • Türkçe
    • हिन्दी
    • Tiếng Việt
    • Deutsch
    • 한국어
    • Bahasa Indonesia
    • Italiano
    • Svenska
    • suomi
    • български език
    • magyar nyelv
    • עִבְֿרִית
    • ภาษาไทย
    • hrvatski
    • Română
    Server German (Main)
Contents
Get started Regions Separation activity create separation get result get result (remote) cancel separation Site information get separation types get news get queue get demo separations User Authentication register login Profile get user get separation history get purchase history low credit alert enable premium usage disable premium usage enable long filenames disable long filenames Quality Checker get queue get leaderboard create entry get entry delete entry Tools & SDKs

Get started

The MVSEP API provides programmatic access to create a separation, return the results, get site information and control user capabilities.

To use this API, you need an API key. You are not logged in, please login to get your API token.

Note that Premium users can request unlimited concurrent jobs, while non-Premium users can only request 1 concurrent job.

Regions

MVSEP runs regional API endpoints. All regions share one account database, so the same account, API key and job hashes work everywhere:

  • Germany — https://de.mvsep.com/api
  • Germany 2 — https://de2.mvsep.com/api
  • Hong Kong — https://hk.mvsep.com/api

Requests to https://mvsep.com/api are geo-steered: callers in Europe are routed to de, callers in North Asia to hk, and everyone else to de2. For API integrations we recommend calling a regional endpoint explicitly — it keeps the whole job lifecycle on one host regardless of where your requests originate from.

Every separation is processed and stored in the region where it was created, and the download URLs returned in responses always point to that region's host. For best performance, choose the endpoint closest to your servers and use the same host for the whole job lifecycle — create, status polling and file downloads.

You can query the status of any job from any region (the database is shared), but the output files themselves are always served by the region that owns the job.

Separation activity

create separation

To create separation you need to make a POST call to the following url:
https://mirror.mvsep.com/api/separation/create


QUERY PARAMETERS

Field Type Description
api_token String Your API key
audiofile Binary Audiofile to be processed. Not required if url parameter is set or the model does not use file input. For matchering models use target_audiofile and reference_audiofile for input instead of audiofile.
url String Link to the audiofile. Not required if audiofile parameter is set.
remote_type String (optional) Remote type of the audiofile. Defaults to direct. Not required if audiofile parameter is set. Supported types are direct (Direct Download), mega (MEGA), drive (Google Drive), dropbox (Dropbox).
sep_type Integer (optional) Separation Type, defaults to 20. This is the separation type ID, refer to the GET SEPARATION TYPES section for more information. Ignored when <code class="higlighted">preset_id</code> is given.
preset_id Integer (optional) Run one of your saved presets over the file instead of a single algorithm. Give either sep_type or preset_id — a preset defines its own algorithms, options and output formats, so sep_type, the add_opt fields and output_format are all ignored alongside it. The response returns a hash you poll exactly like a separation; the result carries one entry per Output node of the preset. See the preset table below for your ids.
add_opt1 String (optional) Separation Type first additional field
add_opt2 String (optional) Separation Type second additional field
add_opt3 String (optional) Separation Type third additional field
output_format Integer (optional) output format, defaults to 0 (mp3 (320kbps))
is_demo Boolean (optional) should the separation be published to demo page, defaults to false

Separation type (sep_type) and additional fields (add_opt1, add_opt2, ...) values

Name Value Additional fields
Ensemble (vocals, instrum) 26 Key: add_opt1
Name: Output files
Options:
  • 0 - Standard set (default)
  • 1 - Include intermediate results and max_fft, min_fft

Key: add_opt2
Name: Model Type
Options:
  • 1 - SDR Vocals 10.44 (MDX23C, VitLarge23, Demucs4HT)
  • 2 - SDR Vocals 10.75 (MDX23C, BS Roformer (v1), VitLarge23)
  • 3 - SDR Vocals 11.06 (MDX23C, BS Roformer (viperx))
  • 4 - SDR Vocals 11.33 (MDX23C, BS Roformer (finetuned))
  • 5 - SDR Vocals 11.50 (Mel Roformer and BS Roformer)
  • 6 - SDR Vocals 11.61 (Mel Roformer, BS Roformer and SCNet XL)
  • 7 - SDR Vocals 11.93 (Mel Roformer, BS Roformer (x2) and SCNet XL IHF) (default)
  • 8 - High Vocal Fullness (SDR: 11.69, Fullness: 20.46)
  • 9 - High Instrumental Fullness (SDR: 17.69, Fullness: 34.79)
Ensemble (vocals, instrum, bass, drums, other) 28 Key: add_opt1
Name: Output files
Options:
  • 0 - Standard set (default)
  • 1 - Include intermediate results and max_fft, min_fft

Key: add_opt2
Name: Model Type
Options:
  • 1 - SDR average: 11.21 (v. 2023.09.01)
  • 2 - SDR average: 11.87 (v. 2024.03.08)
  • 3 - SDR average: 12.03 (v. 2024.03.28)
  • 4 - SDR average: 12.17 (v. 2024.04.04)
  • 5 - SDR average: 12.34 (v. 2024.05.21)
  • 6 - SDR average: 12.66 (v. 2024.07.14)
  • 7 - SDR average: 12.76 (v. 2024.08.15)
  • 8 - SDR average: 12.84 (v. 2024.10.08)
  • 9 - SDR average: 13.01 (v. 2024.12.20)
  • 10 - SDR average: 13.07 (v. 2024.12.28)
  • 11 - SDR average: 13.67 (v. 2025.06.30) (default)
Ensemble All-In (vocals, bass, drums, piano, guitar, lead/back vocals, other) 30 Key: add_opt1
Name: Output files
Options:
  • 0 - Standard set (default)
  • 1 - Include intermediate results and max_fft, min_fft

Key: add_opt2
Name: Model Type
Options:
  • 1 - SDR average: 11.21 (v. 2023.09.01)
  • 2 - SDR average: 11.87 (v. 2024.03.08)
  • 3 - SDR average: 12.03 (v. 2024.03.28)
  • 4 - SDR average: 12.17 (v. 2024.04.04)
  • 5 - SDR average: 12.32 (v. 2024.05.21)
  • 6 - SDR average: 12.66 (v. 2024.07.14)
  • 7 - SDR average: 12.76 (v. 2024.08.15)
  • 8 - SDR average: 12.84 (v. 2024.10.08)
  • 9 - SDR average: 13.01 (v. 2024.12.20)
  • 10 - SDR average: 13.07 (v. 2024.12.28)
  • 11 - SDR average: 13.67 (v. 2025.06.30) (default)
BS Roformer SW (vocals, bass, drums, guitar, piano, other) 63
Demucs4 HT (vocals, drums, bass, other) 20 Key: add_opt1
Name: Model type
Options:
  • 0 - htdemucs_ft (High Quality, Slow)
  • 1 - htdemucs (Good Quality, Fast) (default)
  • 2 - htdemucs_6s (6 stems, additional piano and guitar)
BS Roformer (vocals, instrumental) 40 Key: add_opt1
Name: Vocal model type
Options:
  • 3 - ver. 2024.02 (SDR vocals: 10.42, SDR instrum: 16.73)
  • 4 - viperx edition (SDR vocals: 10.87, SDR instrum: 17.17)
  • 5 - ver 2024.04 (SDR vocals: 11.24, SDR instrum: 17.55)
  • 29 - ver 2024.08 (SDR vocals: 11.31, SDR instrum: 17.62)
  • 85 - unwa high instrum fullness (SDR instrum: 17.25)
  • 142 - unwa BS Roformer HyperACE v2 instrum (SDR instrum: 17.40)
  • 143 - unwa BS Roformer HyperACE v2 vocals (SDR vocals: 11.39)
  • 81 - ver 2025.07 (SDR vocals: 11.89, SDR instrum: 18.20) (default)
  • 171 - 124 bands (SDR vocals: 12.33, SDR instrum: 18.64)
  • 172 - becruily high instrum fullness 124 bands (SDR instrum: 18.47)

Key: add_opt2
Name: Overlap
Options:
  • 2 - 50% (default)
  • 8 - 87.5%

Key: add_opt3
Name: Set of stems
Options:
  • 0 - Standard (default)
  • 1 - Include fullness stems
BS PolarFormer (vocals, instrumental) 123 Key: add_opt1
Name: Model type
Options:
  • 158 - BS PolarFormer (62 bands, SDR: 11.75)
  • 163 - BS PolarFormer (124 bands, SDR: 12.02) (default)

Key: add_opt2
Name: Overlap
Options:
  • 2 - 50% (default)
  • 8 - 87.5%
MelBand Roformer (vocals, instrumental) 48 Key: add_opt1
Name: Vocal model type
Options:
  • 0 - Kimberley Jensen edition (SDR vocals: 11.01, SDR instrum: 17.32)
  • 1 - ver 2024.08 (SDR vocals: 11.17, SDR instrum: 17.48)
  • 2 - Bas Curtiz edition (SDR vocals: 11.18, SDR instrum: 17.49)
  • 3 - unwa Instrumental v1 (SDR vocals: 10.24, SDR instrum: 16.54)
  • 5 - unwa Instrumental v1e (SDR vocals: 10.05, SDR instrum: 16.36)
  • 6 - unwa big beta v5e (SDR vocals: 10.59, SDR instrum: 16.89)
  • 4 - ver 2024.10 (SDR vocals: 11.28, SDR instrum: 17.59) (default)
  • 7 - becruily instrum high fullness (SDR instrum: 16.47)
  • 8 - becruily vocals high fullness (SDR vocals: 10.55)
  • 9 - unwa Instrumental v1e plus (SDR vocals: 10.33, SDR instrum: 16.64)
  • 10 - gabox Instrumental v7 (SDR vocals: 10.32, SDR instrum: 16.63)
  • 11 - becruily deux (SDR vocals: 11.35, SDR instrum: 17.66)
  • 12 - gabox v10 flowers (SDR vocals: 10.67, SDR instrum: 16.97)

Key: add_opt2
Name: Overlap
Options:
  • 2 - 50% (default)
  • 8 - 87.5%
MDX23C (vocals, instrumental) 25 Key: add_opt1
Name: Vocal model type
Options:
  • 3 - 12K FFT, Large Conv, Hop 1024 (SDR vocals: 9.95, SDR instrum: 16.26)
  • 2 - 12K FFT, Large Conv (SDR vocals: 9.71, SDR instrum: 16.02)
  • 0 - 12K FFT (SDR vocals: 9.68, SDR instrum: 15.99)
  • 1 - 12K FFT, 6 Poolings (SDR vocals: 9.49, SDR instrum: 15.79)
  • 4 - 8K FFT (SDR vocals: 10.17, SDR instrum: 16.48)
  • 7 - 8K FFT (SDR vocals: 10.36, SDR instrum: 16.66) (default)
SCNet (vocals, instrumental) 46 Key: add_opt1
Name: Vocal model type
Options:
  • 0 - SCNet (SDR vocals: 10.25, SDR instrum: 16.56)
  • 1 - SCNet Large (SDR vocals: 10.74, SDR instrum: 17.05)
  • 2 - SCNet XL (SDR vocals: 10.96, SDR instrum: 17.27)
  • 3 - SCNet XL (high fullness)
  • 4 - SCNet XL (very high fullness)
  • 5 - SCNet XL IHF (SDR vocals: 11.11, SDR instrum: 17.41) (default)
  • 6 - SCNet XL IHF (high instrum fullness by becruily)
MDX B (vocals, instrumental) 23 Key: add_opt1
Name: Vocal model type
Options:
  • 7 - MDX Kimberley Jensen v2 2023.05.21 (SDR: 9.60)
  • 0 - MDX UVR 2022.01.01 (SDR: 8.83)
  • 1 - MDX UVR 2022.07.25(SDR: 8.67)
  • 2 - MDX Kimberley Jensen v1 2023.02.12 (SDR: 9.48)
  • 4 - UVR-MDX-NET-Inst_HQ_2 (SDR: 9.12)
  • 5 - UVR_MDXNET_Main (SDR: 8.79)
  • 6 - MDX Kimberley Jensen Inst (SDR: 9.28)
  • 8 - UVR-MDX-NET-Inst_HQ_3 (SDR: 9.38)
  • 9 - UVR-MDX-NET-Voc_FT (SDR: 9.64)
  • 11 - UVR-MDX-NET-Inst_HQ_4 (SDR: 9.71) (default)
  • 12 - UVR-MDX-NET-Inst_HQ_5 (SDR: 9.45)
Ultimate Vocal Remover VR (vocals, music) 9 Key: add_opt1
Name: Model Type
Options:
  • 0 - HP2-4BAND-3090_4band_arch-500m_1 (default)
  • 1 - HP2-4BAND-3090_4band_2
  • 2 - HP2-4BAND-3090_4band_1
  • 3 - HP_4BAND_3090
  • 4 - Vocal_HP_4BAND_3090
  • 5 - Vocal_HP_4BAND_3090_AGG
  • 6 - HP2-MAIN-MSB2-3BAND-3090
  • 7 - HP-4BAND-V2
  • 8 - HP-KAROKEE-MSB2-3BAND-3090 (Karaokee model)
  • 9 - WIP-Piano-4band-129605kb (Piano model)
  • 10 - drums-4BAND-3090_4band (Drums model)
  • 11 - bass-4BAND-3090_4band (Bass model)
  • 12 - karokee_4band_v2_sn (Karaokee model v2)
  • 13 - UVR-De-Echo-Aggressive
  • 14 - UVR-De-Echo-Normal
  • 15 - UVR-DeNoise
  • 16 - UVR-DeEcho-DeReverb
  • 17 - UVR-BVE-4B_SN-44100-1 (Back vocals model)

Key: add_opt2
Name: Agressiveness
Options:
  • 0.3 - 0.3 (default)
  • 0.1 - 0.1
  • 0.2 - 0.2
  • 0.4 - 0.4
  • 0.5 - 0.5
  • 0.6 - 0.6
  • 0.7 - 0.7
  • 0.8 - 0.8
  • 0.9 - 0.9
  • 1.0 - 1.0
Demucs4 Vocals 2023 (vocals, instrum) 27
MVSep Karaoke (lead/back vocals) 49 Key: add_opt1
Name: Karaoke model type
Options:
  • 0 - Model by viperx and aufr33 (SDR: 9.45)
  • 1 - Model by becruily (SDR: 9.61)
  • 2 - Model by gabox (SDR: 9.67)
  • 3 - Model fuzed gabox & aufr33/viperx (SDR: 9.85)
  • 4 - SCNet XL IHF by becruily (SDR: 9.53)
  • 5 - BS Roformer by frazer and becruily (SDR: 10.11)
  • 6 - BS Roformer by MVSep Team (SDR: 10.41) (default)
  • 7 - BS Roformer by anvuew (SDR: 10.22)

Key: add_opt2
Name: Extraction type
Options:
  • 0 - Use as is (default)
  • 1 - Extract vocals first
MDX-B Karaoke (lead/back vocals) 12 Key: add_opt1
Name: Karaoke model type
Options:
  • 0 - Extract directly from mixture (SDR lead vocals: 6.81) (default)
  • 1 - Extract from vocals part (SDR lead vocals: 7.94)
MVSep Crowd removal (crowd, other) 34 Key: add_opt1
Name: Model type
Options:
  • 8 - MDX23C v1 (SDR crowd: 5.57)
  • 9 - MDX23C v2 (SDR crowd: 6.06)
  • 0 - Mel Roformer (SDR crowd: 6.07)
  • 1 - Ensemble MDX23C + Mel Roformer (SDR crowd: 6.27)
  • 2 - BS Roformer (SDR crowd: 7.21) (default)
Medley Vox (Multi-singer separation) 53 Key: add_opt1
Name: Model type
Options:
  • 0 - Apply to original file
  • 1 - Extract vocals first (default)
MVSep Multichannel BS (vocals, instrumental) 43 Key: add_opt1
Name: Model Type
Options:
  • 0 - BS Roformer (SDR: 11.89) (default)
  • 1 - MDX23C (SDR: 10.36)
  • 2 - MelBand Roformer (SDR: 11.17)
  • 3 - MelBand Roformer XL (SDR: 11.28)

Key: add_opt2
Name: Processing Mode
Options:
  • 0 - Per-Channel
  • 1 - Stereo Pairs (default)
MVSep Male/Female separation 57 Key: add_opt1
Name: Model type
Options:
  • 0 - BSRoformer by Sucial (SDR: 6.52)
  • 3 - BSRoformer by aufr33 (SDR: 8.18)
  • 1 - SCNet XL (SDR: 11.83)
  • 2 - MelRoformer (2025.01) (SDR: 13.03) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract vocals first with BS Roformer
MVSep Choir (choir, other) 112 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract vocals first
MVSep SATB Choir (soprano, alto, tenor, bass) 111 Key: add_opt1
Name: Model type
Options:
  • 2 - SCNet Masked (SDR: 4.07)
  • 3 - BS Roformer (SDR: 7.39) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract vocals first
MVSep Drums (drums, other) 44 Key: add_opt1
Name: Drums model type
Options:
  • 0 - HTDemucs (SDR drums: 12.04)
  • 1 - MelBand Roformer (SDR drums: 12.76)
  • 2 - SCNet Large (SDR drums: 13.01)
  • 3 - SCNet XL (SDR drums: 13.42)
  • 4 - Mel + SCNet XL (SDR drums: 13.78)
  • 5 - BS Roformer SW (SDR drums: 14.11)
  • 6 - Mel + SCNet XL + BS Roformer SW (SDR drums: 14.35) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from instrumental part

Key: add_opt3
Name: Output files
Options:
  • 0 - Standard set (default)
  • 1 - Include results of independent models
MVSep Bass (bass, other) 41 Key: add_opt1
Name: Bass model type
Options:
  • 0 - BS Roformer (SDR bass: 12.49)
  • 1 - HTDemucs4 (SDR bass: 12.52)
  • 2 - SCNet XL (SDR bass: 13.81)
  • 3 - BS + HTDemucs + SCNet (SDR bass: 14.07)
  • 4 - BS Roformer SW (SDR bass: 14.62)
  • 5 - BS Roformer SW + SCNet XL (SDR bass: 14.87) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from instrumental part

Key: add_opt3
Name: Output files
Options:
  • 0 - Standard set (default)
  • 1 - Include results of independent models
MVSep Synth (synth, other) 88 Key: add_opt1
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from instrumental part
DrumSep (4-6 stems: kick, snare, cymbals, toms, ride, hh, crash) 37 Key: add_opt1
Name: Model Type
Options:
  • 0 - DrumSep model by inagoy (HDemucs, 4 stems)
  • 1 - DrumSep model by aufr33 and jarredou (MDX23C, 6 stems)
  • 2 - DrumSep SCNet XL (5 stems)
  • 3 - DrumSep SCNet XL (6 stems)
  • 4 - DrumSep SCNet XL (4 stems)
  • 5 - DrumSep Ensemble of 4 models (MDX23C + 3 * SCNet XL, 8 stems)
  • 6 - DrumSep MelBand Roformer (4 stems)
  • 7 - DrumSep MelBand Roformer (6 stems) (default)

Key: add_opt2
Name: Preprocess
Options:
  • 0 - Apply Drums model before (default)
  • 1 - Use as is (audio must contain drums only)
MVSep Piano (piano, other) 29 Key: add_opt1
Name: Piano model type
Options:
  • 0 - mdx23c (2023.08, SDR: 4.79)
  • 1 - mdx23c (2024.09, SDR: 5.59)
  • 2 - MelRoformer (viperx, SDR: 5.71)
  • 3 - SCNet Large (2024.09, SDR: 5.89)
  • 4 - Ensemble (SCNet + Mel, SDR: 6.20)
  • 5 - BS Roformer SW (SDR: 7.83) (default)
MVSep Digital Piano (digital-piano, other) 79 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from piano part
MVSep Keys (keys, other) 106
MVSep Organ (organ, other) 58 Key: add_opt1
Name: Organ model type
Options:
  • 0 - SCNet XL (SDR organ: 2.71)
  • 1 - MelBand Roformer (SDR organ: 2.77)
  • 2 - Mel + SCNet (SDR organ: 3.05)
  • 3 - BS Roformer (SDR organ: 5.08) (default)
MVSep Harpsichord (harpsichord, other) 91
MVSep Accordion (accordion, other) 99
MVSep Vibraphone 129
MVSep Metal Bars 130
MVSep Rhodes 131
MVSep Guitar (guitar, other) 31 Key: add_opt1
Name: Guitar model type
Options:
  • 0 - mdx23c (2023.08, SDR: 4.78)
  • 2 - mdx23c (2024.06, SDR: 6.34)
  • 3 - MelRoformer (2024.06, SDR: 7.02)
  • 5 - BSRoformer (viperx, SDR: 7.16)
  • 6 - Ensemble (BS + Mel, SDR: 7.51)
  • 7 - BS Roformer SW (SDR: 9.05) (default)
MVSep Acoustic Guitar (acoustic-guitar, other) 66 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from guitar part
MVSep Electric Guitar (electric-guitar, other) 81 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from guitar part
MVSep Lead/Rhythm Guitar (lead-guitar, rhythm-guitar) 101 Key: add_opt1
Name: Model type
Options:
  • 0 - Two-stage model (SDR: 9.21) (default)
  • 1 - One-stage model (SDR: 9.02)
MVSep Pedal Steel Guitar 124
MVSep Plucked Strings (plucked-strings, other) 102
MVSep Harp (harp, other) 72
MVSep Mandolin (mandolin, other) 74
MVSep Banjo (banjo, other) 83
MVSep Sitar (sitar, other) 90
MVSep Ukulele (ukulele, other) 96
MVSep Dobro (dobro, other) 97
MVSep Bowed Strings (strings, other) 52 Key: add_opt1
Name: String model type
Options:
  • 0 - MDX23C (SDR strings: 3.84)
  • 1 - BS Roformer (SDR strings: 5.41) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from instrumental part
MVSep Violin (violin, other) 65
MVSep Viola (viola, other) 69 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from strings part
MVSep Cello (cello, other) 70 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from strings part
MVSep Double Bass (double-bass, other) 73 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from strings part
MVSep Wind (wind, other) 54 Key: add_opt1
Name: Wind model type
Options:
  • 0 - MelBand Roformer (SDR wind: 6.73)
  • 1 - SCNet Large (SDR wind: 6.76)
  • 2 - Mel + SCNet (SDR wind: 7.22)
  • 3 - BS Roformer (SDR wind: 9.82) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from instrumental part

Key: add_opt3
Name: Output files
Options:
  • 0 - Standard set (default)
  • 1 - Include results of independent models
MVSep Brass (brass, other) 107 Key: add_opt1
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Woodwind (woodwind, other) 108 Key: add_opt1
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Saxophone (saxophone, other) 61 Key: add_opt1
Name: Model type
Options:
  • 0 - SCNet XL (SDR saxophone: 6.15)
  • 1 - MelBand Roformer (SDR saxophone: 6.97)
  • 2 - Mel + SCNet (SDR saxophone: 7.13)
  • 3 - BS Roformer (SDR saxophone: 9.77) (default)
MVSep Flute (flute, other) 67 Key: add_opt1
Name: Flute model type
Options:
  • 0 - SCNet XL (SDR flute: 6.27)
  • 1 - BS Roformer (SDR flute: 9.46) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Trumpet (trumpet, other) 71 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Trombone (trombone, other) 75 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Oboe (oboe, other) 77 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Clarinet (clarinet, other) 78 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep French Horn (french-horn, other) 82 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Harmonica (harmonica, other) 87 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Tuba (tuba, other) 92
MVSep Bassoon (bassoon, other) 93
MVSep Bagpipes (bagpipes , other) 116 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from wind part
MVSep Whistle 132
MVSep Percussion (percussion, other) 105
MVSep Tambourine (tambourine, other) 76
MVSep Marimba (marimba, other) 84
MVSep Glockenspiel (glockenspiel, other) 85
MVSep Timpani (timpani, other) 86
MVSep Triangle (triangle, other) 89
MVSep Congas (congas , other) 94
MVSep Bells (bells, other) 95
MVSep Wind Chimes (wind-chimes, other) 98
MVSep Xylophone (xylophone, other) 109 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from percussion part
MVSep Celesta (celesta, other) 110 Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from percussion part
MVSep Clap 133
MVSep Cowbell 128
MVSep Demucs4HT DNR (speech, music, effects) 24 Key: add_opt1
Name: Model type
Options:
  • 0 - Single (SDR: 9.62) (default)
  • 1 - Ensemble (SDR: 10.16)
BandIt Plus (speech, music, effects) 36
BandIt v2 (speech, music, effects) 45 Key: add_opt1
Name: Model Type
Options:
  • 0 - Multi language model (default)
  • 1 - English model
  • 2 - German model
  • 3 - French model
  • 4 - Spanish model
  • 5 - Chinese model
  • 6 - Faroese model
MVSep DnR v3 (speech, music, effects) 56 Key: add_opt1
Name: Model type
Options:
  • 0 - SCNet Large (SDR avg: 11.22)
  • 1 - MelBand Roformer (SDR avg: 10.99)
  • 2 - Mel + SCNet (SDR avg: 11.54) (default)

Key: add_opt2
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Use vocals model to help

Key: add_opt3
Name: Output files
Options:
  • 0 - Standard set (default)
  • 1 - Include results of independent models
MVSep Braam 117
MVSep Risers 125
MVSep FX 122
Apollo Enhancers (by JusperLee, Lew, baicai1145) 51 Key: add_opt1
Name: Model type
Options:
  • 0 - MP3 Enhancer (by JusperLee)
  • 1 - Universal Super Resolution (by Lew)
  • 2 - Vocals Super Resolution (by Lew)
  • 3 - Universal Super Resolution (by MVSep Team) (default)
  • 4 - Universal Super Resolution (by baicai1145)

Key: add_opt2
Name: Cutoff (Hz)
Options:
  • 0 - No cutoff (default)
  • 2000 - 2000
  • 3000 - 3000
  • 4000 - 4000
  • 5000 - 5000
  • 6000 - 6000
  • 7000 - 7000
  • 8000 - 8000
  • 9000 - 9000
  • 10000 - 10000
  • 11000 - 11000
  • 12000 - 12000
  • 13000 - 13000
  • 14000 - 14000
  • 15000 - 15000
  • 16000 - 16000
  • 17000 - 17000
  • 18000 - 18000
  • 19000 - 19000
  • 20000 - 20000
  • 21000 - 21000
  • 22000 - 22000
Reverb Removal (noreverb) 22 Key: add_opt1
Name: Model Type
Options:
  • 0 - Reverb removal by FoxJoy (MDX-B)
  • 8 - Reverb removal by aufr33 and jarredou (MDX23C)
  • 1 - Reverb removal by anvuew (MelRoformer)
  • 2 - Reverb removal by anvuew (BSRoformer)
  • 3 - Reverb removal by anvuew v2 (MelRoformer)
  • 4 - Reverb removal by Sucial (MelRoformer)
  • 5 - Reverb removal by Sucial v2 (MelRoformer)
  • 6 - DeReverb room by anvuew (BSRoformer)
  • 7 - DeReverb stereo by anvuew (BSRoformer) (default)
  • 9 - MVSep Team (2026.07, BSRoformer)

Key: add_opt2
Name: Preprocess
Options:
  • 0 - Extract vocals (needed for Mel/BS Roformer)
  • 1 - Use as is (default)
DeNoise by aufr33 and gabox 47 Key: add_opt1
Name: Model type
Options:
  • 0 - aufr33 (Standard) (default)
  • 1 - aufr33 (Aggressive)
  • 2 - gabox
AudioSR (Super Resolution) 59 Key: add_opt1
Name: Cutoff (Hz)
Options:
  • 0 - Automatic (default)
  • 2000 - 2000
  • 3000 - 3000
  • 4000 - 4000
  • 5000 - 5000
  • 6000 - 6000
  • 7000 - 7000
  • 8000 - 8000
  • 9000 - 9000
  • 10000 - 10000
  • 11000 - 11000
  • 12000 - 12000
  • 13000 - 13000
  • 14000 - 14000
  • 15000 - 15000
  • 16000 - 16000
  • 17000 - 17000
  • 18000 - 18000
  • 19000 - 19000
  • 20000 - 20000
  • 21000 - 21000
  • 22000 - 22000
FlashSR (Super Resolution) 60
Stable Audio Open Gen 62 Key: add_opt1
Name: Text prompt
Options:

Key: add_opt2
Name: Length (in seconds)
Options:
  • 3 - 3
  • 5 - 5
  • 8 - 8
  • 10 - 10
  • 12 - 12
  • 15 - 15
  • 20 - 20
  • 25 - 25
  • 30 - 30
  • 35 - 35
  • 40 - 40
  • 45 - 45
  • 47 - 47 (default)
Whisper (extract text from audio) 39 Key: add_opt1
Name: Model type
Options:
  • 0 - Apply to original file
  • 1 - Extract vocals first (default)

Key: add_opt2
Name: Transcription type
Options:
  • 0 - New timestamps by linto-ai
  • 1 - Old version of timestamps by whisper (default)
Parakeet (extract text from audio) 64 Key: add_opt1
Name: Model type
Options:
  • 0 - Apply to original file
  • 1 - Extract vocals first (default)

Key: add_opt2
Name: Version
Options:
  • 0 - Parakeet v2
  • 1 - Parakeet v3 (default)
VibeVoice (Voice Cloning) 103 Key: add_opt1
Name: Model type
Options:
  • 0 - VibeVoce 1.5B (Small)
  • 1 - VibeVoce 7B (Large) (default)

Key: add_opt2
Name: Text prompt
Options:

Key: add_opt3
Name: Extract vocals first
Options:
  • 0 - Use original reference file
  • 1 - Extract vocals first (default)
VibeVoice (TTS) 104 Key: add_opt1
Name: Model type
Options:
  • 0 - VibeVoce 1.5B (Small)
  • 1 - VibeVoce 7B (Large) (default)

Key: add_opt2
Name: Text prompt
Options:
Qwen3-TTS (Custom Voice) 118 Key: add_opt1
Name: Text prompt
Options:

Key: add_opt2
Name: Speaker
Options:
  • aiden - Aiden (English) (default)
  • ryan - Ryan (English)
  • sohee - Sohee (Korean)
  • ono_anna - Ono Anna (Japanese)
  • serena - Serena (Chinese)
  • uncle_fu - Uncle Fu (Chinese)
  • vivian - Vivian (Chinese)
  • dylan - Dylan (Chinese Beijing Dialect)
  • eric - Eric (Chinese Sichuan Dialect)

Key: add_opt3
Name: Language
Options:
  • auto - Auto (default)
  • english - English
  • russian - Russian
  • chinese - Chinese
  • french - French
  • german - German
  • italian - Italian
  • japanese - Japanese
  • korean - Korean
  • portuguese - Portuguese
  • spanish - Spanish

Key: add_opt4
Name: Voice description
Options:
Qwen3-TTS (Voice Design) 119 Key: add_opt1
Name: Text prompt
Options:

Key: add_opt2
Name: Voice description
Options:

Key: add_opt3
Name: Language
Options:
  • auto - Auto (default)
  • english - English
  • russian - Russian
  • chinese - Chinese
  • french - French
  • german - German
  • italian - Italian
  • japanese - Japanese
  • korean - Korean
  • portuguese - Portuguese
  • spanish - Spanish
Qwen3-TTS (Voice Cloning) 120 Key: add_opt1
Name: Text prompt
Options:

Key: add_opt2
Name: Reference text in audio (optional)
Options:

Key: add_opt3
Name: Language
Options:
  • auto - Auto (default)
  • english - English
  • russian - Russian
  • chinese - Chinese
  • french - French
  • german - German
  • italian - Italian
  • japanese - Japanese
  • korean - Korean
  • portuguese - Portuguese
  • spanish - Spanish

Key: add_opt4
Name: Extract vocals first
Options:
  • 0 - Use original reference file (default)
  • 1 - Extract vocals first
Mega 53-stem Model 126
Bark (Speech Gen) 115 Key: add_opt1
Name: Text prompt
Options:

Key: add_opt2
Name: Speaker
Options:
  • en_0 - English Male 1
  • en_1 - English Male 2
  • en_2 - English Male 3
  • en_3 - English Male 4
  • en_4 - English Male 5
  • en_5 - English Male 6 (Grainy)
  • en_6 - English Male 7 (Best) (default)
  • en_7 - English Male 8
  • en_8 - English Male 9
  • en_9 - English Female 1
  • ru_0 - Russian Male 1
  • ru_1 - Russian Male 2 (Echoes)
  • ru_2 - Russian Male 3 (Echoes)
  • ru_3 - Russian Male 4
  • ru_4 - Russian Male 5
  • ru_7 - Russian Male 6
  • ru_8 - Russian Male 7 (Grainy)
  • ru_5 - Russian Female 1
  • ru_6 - Russian Female 2 (Grainy)
  • ru_9 - Russian Female 3 (Grainy)
  • de_0 - German Male
  • de_1 - German Male
  • de_2 - German Male
  • de_3 - German Female
  • de_4 - German Male
  • de_5 - German Male
  • de_6 - German Male
  • de_7 - German Male
  • de_8 - German Female
  • de_9 - German Male
  • es_0 - Spanish Male
  • es_1 - Spanish Male
  • es_2 - Spanish Male (Noise)
  • es_3 - Spanish Male (Noise)
  • es_4 - Spanish Male
  • es_5 - Spanish Male (Noise)
  • es_6 - Spanish Male
  • es_7 - Spanish Male
  • es_8 - Spanish Female
  • es_9 - Spanish Female
  • fr_0 - French Male
  • fr_1 - French Female
  • fr_2 - French Female
  • fr_3 - French Male
  • fr_4 - French Male
  • fr_5 - French Female
  • fr_6 - French Male
  • fr_7 - French Male
  • fr_8 - French Male
  • fr_9 - French Male (Auditorium)
  • hi_0 - Hindi Female
  • hi_1 - Hindi Female (Noise)
  • hi_2 - Hindi Male
  • hi_3 - Hindi Female
  • hi_4 - Hindi Female (Noise)
  • hi_5 - Hindi Male
  • hi_6 - Hindi Male
  • hi_7 - Hindi Male
  • hi_8 - Hindi Male
  • hi_9 - Hindi Female
  • it_0 - Italian Male
  • it_1 - Italian Male
  • it_2 - Italian Female
  • it_3 - Italian Male
  • it_4 - Italian Male (Best)
  • it_5 - Italian Male
  • it_6 - Italian Male
  • it_7 - Italian Female
  • it_8 - Italian Male
  • it_9 - Italian Female
  • ja_0 - Japanese Female
  • ja_1 - Japanese Female (Noise)
  • ja_2 - Japanese Male
  • ja_3 - Japanese Female
  • ja_4 - Japanese Female
  • ja_5 - Japanese Female
  • ja_6 - Japanese Male
  • ja_7 - Japanese Female
  • ja_8 - Japanese Female
  • ja_9 - Japanese Female
  • ko_0 - Korean Female
  • ko_1 - Korean Male
  • ko_2 - Korean Male
  • ko_3 - Korean Male
  • ko_4 - Korean Male
  • ko_5 - Korean Male
  • ko_6 - Korean Male
  • ko_7 - Korean Male
  • ko_8 - Korean Male
  • ko_9 - Korean Male
  • pl_0 - Polish Male
  • pl_1 - Polish Male
  • pl_2 - Polish Male
  • pl_3 - Polish Male
  • pl_4 - Polish Female
  • pl_5 - Polish Male
  • pl_6 - Polish Female
  • pl_7 - Polish Male
  • pl_8 - Polish Male
  • pl_9 - Polish Female
  • pt_0 - Portugues Male
  • pt_1 - Portugues Male
  • pt_2 - Portugues Male
  • pt_3 - Portugues Male
  • pt_4 - Portugues Male
  • pt_5 - Portugues Male
  • pt_6 - Portugues Male (Noise)
  • pt_7 - Portugues Male
  • pt_8 - Portugues Male
  • pt_9 - Portugues Male
  • tr_0 - Turkish Male
  • tr_1 - Turkish Male
  • tr_2 - Turkish Male
  • tr_3 - Turkish Male
  • tr_4 - Turkish Female
  • tr_5 - Turkish Female
  • tr_6 - Turkish Male
  • tr_7 - Turkish Male (Grainy)
  • tr_8 - Turkish Male
  • tr_9 - Turkish Male
  • zh_0 - Chinese Male
  • zh_1 - Chinese Male
  • zh_2 - Chinese Male
  • zh_3 - Chinese Male
  • zh_4 - Chinese Female
  • zh_5 - Chinese Male
  • zh_6 - Chinese Female (Noise)
  • zh_7 - Chinese Female
  • zh_8 - Chinese Male
  • zh_9 - Chinese Female
MVSep MultiSpeaker (MDX23C) 42 Key: add_opt1
Name: Model Type
Options:
  • 0 - Extract directly from mixture
  • 1 - Extract from vocals part (default)
Aspiration (by Sucial) 50 Key: add_opt1
Name: Model type
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract from vocals part
Phantom Centre extraction 55 Key: add_opt1
Name: Model type
Options:
  • 0 - Phantom Centre by wesleyr36 (MDX23C)
  • 1 - Phantom Centre by gilliaan (BSRoformer) (default)
  • 2 - Phantom Centre by gilliaan (mdx23c)
Matchering (by sergree) 68
SOME (Singing-Oriented MIDI Extractor) 80 Key: add_opt1
Name: How to use
Options:
  • 0 - Apply to original file
  • 1 - Extract vocals first (default)
Transkun (Piano -> MIDI) 113 Key: add_opt1
Name: How to extract
Options:
  • 0 - Extract directly from mixture (default)
  • 1 - Extract piano first
Basic Pitch (MIDI Extraction) 114
ADTOF Plus (Drums -> MIDI) 127 Key: add_opt1
Name: How to extract
Options:
  • 0 - Extract directly from mixture
  • 1 - Extract drums first (default)
HeartMuLa (Song Gen) 121 Key: add_opt1
Name: Lyrics
Options:

Key: add_opt10
Name: Topic
Options:
  • --- - --- (default)
  • love - Love
  • heartbreak - Heartbreak
  • romance - Romance
  • breakup - Breakup
  • desire - Desire
  • infatuation - Infatuation
  • betrayal - Betrayal
  • life - Life
  • death - Death
  • friendship - Friendship
  • family - Family
  • growing up - Growing up
  • youth - Youth
  • aging - Aging
  • nostalgia - Nostalgia
  • loneliness - Loneliness
  • grief - Grief
  • mental health - Mental health
  • depression - Depression
  • anxiety - Anxiety
  • hope - Hope
  • motivation - Motivation
  • empowerment - Empowerment
  • self-love - Self-love
  • overcoming - Overcoming
  • success - Success
  • failure - Failure
  • party - Party
  • money - Money
  • wealth - Wealth
  • hustle - Hustle
  • drinking - Drinking
  • drugs - Drugs
  • addiction - Addiction
  • crime - Crime
  • violence - Violence
  • revenge - Revenge
  • cars - Cars
  • fashion - Fashion
  • society - Society
  • politics - Politics
  • protest - Protest
  • rebellion - Rebellion
  • war - War
  • peace - Peace
  • injustice - Injustice
  • freedom - Freedom
  • religion - Religion
  • spirituality - Spirituality
  • faith - Faith
  • nature - Nature
  • space - Space
  • ocean - Ocean
  • summer - Summer
  • winter - Winter
  • spring - Spring
  • autumn - Autumn
  • travel - Travel
  • home - Home
  • storytelling - Storytelling
  • fantasy - Fantasy
  • sci-fi - Sci-fi
  • horror - Horror
  • mythology - Mythology
  • comedy - Comedy
  • parody - Parody
  • instrumental - Instrumental

Key: add_opt2
Name: Tags (optional)
Options:

Key: add_opt3
Name: Genre
Options:
  • --- - --- (default)
  • pop - Pop
  • hip-hop - Hip-hop
  • rock - Rock
  • electronic - Electronic
  • latin - Latin
  • r&b - R&B
  • classical - Classical
  • jazz - Jazz
  • metal - Metal
  • country - Country
  • rap - Rap
  • edm - EDM
  • reggaeton - Reggaeton
  • k-pop - K-pop
  • house - House
  • techno - Techno
  • alternative rock - Alternative rock
  • indie - Indie
  • soul - Soul
  • blues - Blues
  • reggae - Reggae
  • afrobeats - Afrobeats
  • folk - Folk
  • ambient - Ambient
  • lo-fi - Lo-fi
  • trap - Trap
  • dance pop - Dance pop
  • indie pop - Indie pop
  • dubstep - Dubstep
  • drum and bass - Drum and bass
  • trance - Trance
  • synthwave - Synthwave
  • punk - Punk
  • hard rock - Hard rock
  • heavy metal - Heavy metal
  • nu metal - Nu metal
  • grunge - Grunge
  • funk - Funk
  • disco - Disco
  • soundtrack - Soundtrack
  • cinematic - Cinematic
  • orchestral - Orchestral
  • acoustic - Acoustic
  • gospel - Gospel
  • drill - Drill
  • boom bap - Boom bap
  • uk garage - UK garage
  • grime - Grime
  • electro - Electro
  • breakbeat - Breakbeat
  • trip-hop - Trip-hop
  • future bass - Future bass
  • hardstyle - Hardstyle
  • industrial - Industrial
  • idm - IDM
  • hyperpop - Hyperpop
  • vaporwave - Vaporwave
  • pop punk - Pop punk
  • metalcore - Metalcore
  • death metal - Death metal
  • black metal - Black metal
  • symphonic metal - Symphonic metal
  • post-punk - Post-punk
  • psychedelic rock - Psychedelic rock
  • progressive rock - Progressive rock
  • emo - Emo
  • shoegaze - Shoegaze
  • post-rock - Post-rock
  • garage rock - Garage rock
  • math rock - Math rock
  • bossa nova - Bossa nova