Cookies & tracking

We use cookies for essentials, and optionally for analytics. You can change this anytime. Privacy Policy

🎵 Musicfal.ai

Demucs HTDemucs

Demucs HTDemucs splits a finished track into vocals, drums, bass and the rest — the separation behind the stem splitter.

Try it

You can fill this in now — signing in happens when you run it, and your inputs come with you.

How to use Demucs HTDemucs

  1. Fill in Audio file in the form on this page.
  2. Adjust anything in the parameter table below — the defaults are the platform's recommended values.
  3. Run it; signing in starts the charge, and the result (Stem separation) appears above the form, ready to download.

Use it from the API

The same run, as a request. Send your API key as a bearer token; poll the returned request_uid until it is done.

curl -X POST https://api.melunox.com/v1/ai/async/tasks \
  -H "Authorization: Bearer $WISAVEN_API_KEY" \
  -H "X-App-Id: wisaven" -H "Content-Type: application/json" \
  -d '{
  "model": "demucs-htdemucs",
  "task": "stem-separation",
  "input": {
    "prompt": "your prompt here"
  }
}'

At a glance

Developer
fal.ai
Can do
Stem separation
Credits per run
Typical time
~60s
Added
2026-08-11

Parameters

What the model takes. The form above is generated from exactly this list, and the API accepts the same field names.

ParameterTypeDefaultRange / options
audio_urlrequired
Audio file
File upload

What Demucs HTDemucs costs

Demucs HTDemucs costs usage-based pricing, charged at the platform's live rate, usually back in around 60 seconds. Credits are shared across every workspace, new accounts start with free ones, and a failed run is refunded.

Demucs HTDemucs compared with other Music models

Same workspace, different trade-offs — credits, speed and what each one can be asked for.

AI modelsCan doCredits per runTypical time
Demucs HTDemucsStem separation~60s
Basic PitchAudio to MIDI~40s
MiniMax MusicText to music, Audio to music, Humming to song~90s
ACE-StepText to music~90s
Stable Audio OpenText to music~90s

Skills that run on this model

Questions

What can Demucs HTDemucs do?

Stem separation. Fill in the parameters on this page to try it.

How many credits does Demucs HTDemucs cost?

Usage-based, charged at the platform's live price when you run it. One credit balance covers every workspace.

How long does it take?

Around 60 seconds; heavier settings or a queue take longer, and the page shows progress.

Do I need an account, and who owns the output?

Browsing and filling in the form need no account; running it does (new accounts start with free credits). What you generate is yours, personally or commercially, subject to the terms.

Where this model is used: Music·All models