Remove the vocals. Keep the music.
Upload any song and get a clean instrumental or karaoke track in minutes. Or pull it apart into separate stems: vocals, drums, bass. Just ask and download the file.
How it works
No setup, no plugins. Just ask, and get the file back.
Upload your track
Drop in any song: an MP3, WAV, or the audio from a video. No plugins to install and nothing to set up.
Ask for the vocals gone
Tell the chat what you want in plain words. Say "remove the vocals" for a clean instrumental, or "split this into stems" for the separate parts.
Play it and download
Listen right there in the chat, then download your instrumental or the separate stem files whenever you are happy with it.
Hear the difference
See the vocals disappear
Drag the handle to reveal the instrumental, or play each side to hear the difference. This is a synthetic preview of the waveform until a sample track is added.
Vocals removed
Before · Original
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the clean instrumental results you get are kept in one place, so you can come back, compare earlier versions, share a link, or ask across everything you’ve stored, whenever you want.
Recipes
Make a clean instrumental one step in a pipeline you run by name.
Chain it with other steps into a recipe you design once, then run on a single file in chat or on thousands at once.
See it in action
See stem separation in action
Simple, transparent pricing
Only pay for the audio you actually process.
1 token = 1 second of audio, minimum 1 token per job.
More than one trick
Scarleta does a whole lot more.
The same account handles all of it. Here are a few very different things you can do with your audio.
For developers
Do this at scale with the API
Building it into an app or running a whole catalog? Send a batch of files to a remove-vocals recipe and let a webhook call you back when each instrumental is ready.
curl https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer $SCARLETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "rec_0001_remove_vocals",
"audio_urls": [
"https://example.com/song.mp3"
]
}'Get a clean instrumental in minutes
Start on your free tokens. Upload a song, remove the vocals, and download the result. Top up only when you need more.
Frequently asked questions
What do I get back?
An audio file: the song without the vocals (a clean instrumental), just the vocals on their own, or a separate audio file for each stem like vocals, drums, and bass if you split it.
How good is the separation?
It uses modern AI separation, which sounds clean on most tracks. Results vary a little from song to song depending on how the original was mixed.
What does it cost?
You pay by the second of audio: 1 token per second, which works out to $0.10 per minute. Every account starts with 300 free tokens, and top-ups begin at $10. No subscription.
Do I need to install anything?
No. It runs right in the Scarleta chat in your browser. Upload a track, ask for the vocals gone, and download the result.
Can I do this for a whole library or inside my own app?
Yes. The same capability is available over the API, so you can process many files at once or build it into your own product. See the docs to get started.