Walk away with the file.
Turn a melody into MIDI, split a song into stems, or process a track and keep the render. Whatever you make in Scarleta, you can take the real file with you, not just a preview.
How it works
No setup, no plugins. Just ask, and get the file back.
Upload and ask
Drop an audio file into the Scarleta chat and ask for what you need: "turn this into MIDI," "split the stems," "clean this up." The AI runs the right job. No settings, no code.
See the result in chat
The result plays and shows up right in the conversation: the stems, the transcribed notes, the processed track. Check it before you take it.
Take the file
Grab the deliverable: MIDI from a transcription, the separated stem files, or your processed-audio render from the library's renders tab. Real files you can drop into your own tools.
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the exported files 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 exported files 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
Walk away with the file: MIDI, stems, or a processed render
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
Running a whole catalog? Send a batch of files to a recipe: transcription, stem separation, or processing. Let a webhook call you back when each deliverable is ready.
curl https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer $SCARLETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "rec_0002_stems_export",
"audio_urls": [
"https://example.com/song.mp3"
]
}'Take the file, not just a preview
Start on your free tokens: upload a track, make what you need, and download the real deliverable. Top up only when you need more.
Frequently asked questions
What files can I export?
MIDI from a melody transcription, separated stem files from stem separation, and processed-audio renders from your library's renders tab. Real deliverable files, not a formatted report.
Where do my processed tracks go?
Every track you process is kept as a render in your library's renders tab, so you can come back and download it whenever you want.
How much does it cost?
You pay by the second of audio, 1 token per second, which works out to $0.10 per minute, from prepaid tokens. New accounts start with 300 free tokens, and top-ups begin at $10. No subscription.
Do I need to install anything?
No. Upload a track in the Scarleta chat and ask. It runs right in your browser, with nothing to download to get started.
Can I produce these files from my own app?
Yes. Developers can run transcription, stem separation, or processing over many files at once through the API and get called back by webhook when each one is ready. See the docs.