Results play and chart right in the chat.
Upload a track and ask. Scarleta plays the audio back inline and turns the analysis into interactive charts and tables in a side panel, so you hear it and see it in the conversation, not as a wall of numbers.
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 want in plain language. No settings, no code. The AI figures out which analysis to run.
Hear it inline
Your track and any results come back as audio players right in the conversation, so you can press play without leaving the chat.
See it as charts
The analysis renders as interactive charts and tables in a side panel: a chord timeline, a tempo curve, a feature table, something you can actually read.
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the interactive analysis 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 interactive analysis results 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
Ask. It plays. It charts. Right in the chat.
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: get the data behind the charts
The inline players and charts live in the Scarleta chat. If you’re building your own app, pull the same analysis data through the batch API and chart it however you like. Submit, then we call you back when it’s done.
curl https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer $SCARLETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "rec_0001_analyze_song",
"audio_urls": [
"https://example.com/song.mp3"
]
}'
# 202 + batch_id. Poll GET /v1/batch/:id/results, or register a
# webhook and we'll call you when the analysis is done. The JSON
# you get back is the analysis data; chart it in your own app.Hear it and see it, right in the chat
Start on your free tokens. Upload a track, ask, and watch the results play back and chart inline. Top up only when you need more.
Frequently asked questions
What does “inline” actually mean?
Your audio and results show up as players you can press play on, right inside the chat, and the analysis appears as interactive charts and tables in a side panel next to the conversation, instead of raw numbers.
What kinds of charts can I see?
Whatever fits the analysis you asked for: for example a chord timeline, a tempo curve, or a feature table. They render as interactive charts and tables in the chat’s side panel.
Can I get the raw data out?
Yes. You can export the analysis as CSV or JSON to use in your own tools. (Export is files and data only; there’s no PDF report.)
How much does it cost?
You pay per second of audio, $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.
Do I need to install anything?
No. Upload a track in the Scarleta chat and ask. It runs in the browser, nothing to download.
Can I show these results in my own app?
The inline players and charts are part of the Scarleta chat. If you’re a developer, you can pull the analysis data through our API and render it however you like in your own product. See the docs.