See the verse, chorus, and drop mapped on a timeline.
Upload a track and ask where the sections are. Scarleta maps the song into its segments and lays them out on a timeline, with the beat and downbeat grid, right in the chat.
How it works
No setup, no plugins. Just ask, and get the file back.
Upload your song
Drop an audio file into the Scarleta chat: a full track, a mix, or a rough bounce of your session. Nothing to install.
Ask to map the structure
Type it in plain words: "where is the chorus and the drop?" The AI figures out which analysis to run. No settings, no code.
See the song's map
Get the song broken into segments: intro, verse, chorus, drop, on a timeline you can actually read, with the beat and downbeat grid, right in the conversation.
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the structure and rhythm map 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 structure and rhythm map 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 a song's map: intro, verse, chorus, drop
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
Map a whole catalog with the API
Building it into an app or running a whole library? Send a batch of files to a structure recipe and pass a webhook_url to get one callback when the whole batch is done. Batch submits need a paid account; a free key gets 403 batch_paid_only. Replace YOUR_RECIPE_ID with a recipe id from GET /v1/recipe/browse.
curl https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer $SCARLETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "YOUR_RECIPE_ID",
"audio_urls": [
"https://example.com/song.mp3"
],
"webhook_url": "https://your-app.com/hooks/scarleta"
}'See any song's map in minutes
Start on your free tokens: upload a track, ask where the sections are, and read the structure on a timeline. Top up only when you need more.
Frequently asked questions
What do I get back?
The song split into sections: intro, verse, chorus, drop and so on, along with the beat and downbeat grid and the meter. You can see it on a timeline right in the chat, and export the analysis as CSV or JSON to use in your own tools.
What does mapping a song structure cost?
Billed at $0.10 per minute of audio, from prepaid tokens (1 token = 1 second): a 5-minute song is 300 tokens, or $0.50. New accounts start with 300 free tokens, top-ups start at $10, and there is no subscription.
Do I need software to map a song?
No. Upload a track in the Scarleta chat and ask for its sections. Nothing to install.
Can I map the structure of many songs from my own app?
Yes. Developers can send many songs at once through our API to get each song’s sections, and get called back by webhook when the batch is done. See the docs to get started. Batch needs a paid account.