Take the data anywhere. CSV or JSON.
Run audio analysis on Scarleta, then get the results out as structured JSON or CSV and drop them straight into your notebooks, dashboards, and data pipelines. Built for ML teams and researchers who need the raw numbers, not a preview.
How it works
No setup, no plugins. Just ask, and get the file back.
Analyze your audio via the API
Submit your files to the batch API and let Scarleta run the analysis: key, tempo, features, whatever your recipe covers.
Request an export
Ask for the analysis data as JSON or CSV. Export is an account capability we enable for API teams. Talk to us if it isn't switched on yet.
Pull it into your tools
Take the structured file straight into pandas, a spreadsheet, a warehouse, or your own dashboard. Real data, no scraping a UI.
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the structured analysis data 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 structured analysis data 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
Run analysis, take the data: CSV or JSON
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
Run analysis, then take the data
Submit a batch, get called back when it's done, then pull the structured results. Native JSON / CSV export is a gated account capability. Contact us to enable it for your key.
# 1. Submit a batch of audio for analysis
curl -X POST https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer scar_live_your_key" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "rec_0001_analysis",
"audio_urls": ["https://example.com/song.mp3"]
}'
# → 202 { "batch_id": "…", "status": "IN_QUEUE" }
# 2. When it completes (poll or batch_completed webhook), pull the results
curl https://api.scarleta.ai/v1/batch/BATCH_ID/results \
-H "Authorization: Bearer scar_live_your_key"
# → per-item structured analysis you can serialize to JSON / CSV.
# Native JSON/CSV export is a gated account capability.
# Contact us to enable it for your key.Get your analysis data out and into your pipeline
Start on your free tokens: run analysis over the API, then take the numbers anywhere as JSON or CSV. Talk to us to switch on export for your key.
Frequently asked questions
What formats can I export?
Structured JSON or CSV. The analysis numbers in a machine-readable file, not a formatted report.
Is export available on any account?
Data export is a gated capability we enable per account for API teams. If it isn't switched on for your key yet, get in touch and we'll set it up.
How much does it cost?
You pay per second of audio you analyze, $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.
Can I run this over a lot of files?
Yes. Submit many files at once through the batch API and get called back by webhook when every one is done, then take the results out. See the developer docs.