Build your pipeline once. Run it any time.
Do the same handful of audio steps on every track? Save them as one recipe, give it a name, and run it on a single file or a whole batch. No re-wiring the same steps by hand every time.
How it works
No setup, no plugins. Just ask, and get the file back.
Compose your steps
Put your usual audio steps in order: say, split the stems, then clean up the vocal, then export. Describe it in the chat and Scarleta builds the recipe for you.
Save it with a name
Save the recipe once. It gets a stable ID you can invoke again and again. No rebuilding the same chain every session.
Run it on one file or many
Point the recipe at a single track in the chat, or send a whole batch of files through the API and get called back when every one is done.
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the saved recipe 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 saved recipe 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
Build a pipeline once, run it every time
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
For developers: run one recipe over a whole batch
Submit many files against a saved recipe through the batch API (up to 500 files per batch). Submit once, then we webhook you the moment it is done. No polling.
curl -X POST https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer $SCARLETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "rec_0001_stems_denoise_export",
"audio_urls": [
"https://example.com/track-01.mp3",
"https://example.com/track-02.mp3"
],
"webhook_url": "https://your-app.com/hooks/scarleta"
}'
# 202 { "batch_id": "...", "status": "IN_QUEUE" }
# Poll GET /v1/batch/:id/results, or let the batch_completed webhook call you.Save your pipeline once, run it on everything
Start on your free tokens: build a recipe in the chat, then run it on a single track or a whole batch through the API. Top up only when you need more.
Frequently asked questions
What's a recipe?
A recipe is your usual sequence of audio steps saved as one reusable pipeline, for example: split into stems, then remove noise, then export. You build it once, name it, and run it again whenever you need it.
How do I run it on lots of files at once?
Developers send a batch of files against a saved recipe through our API: up to 500 files per batch. You submit once, and we call your webhook the moment the whole batch finishes, so you never have to sit and poll. See the docs.
How much does it cost?
You pay per second of audio processed: $0.10 per minute, from prepaid tokens (1 token = 1 second). New accounts start with 300 free tokens, and top-ups start at $10. No subscription.
If I run the same file twice, do I pay twice?
No. Within your own account we don't re-analyze or re-charge you for the exact same audio: identical files are recognized and reused. (Reuse stays inside your account; results aren't shared across accounts.)
Do I need to install anything?
No. Build and run recipes right in the Scarleta chat: nothing to download. Developers who want to run at scale use the REST API.