Find out what is actually in your audio.
Upload any clip and ask what is in it. Scarleta listens across the whole recording and tells you which sounds it detects, tagged as sound events you can scan at a glance.
How it works
No setup, no plugins. Just ask, and get the file back.
Upload your clip
Drop an audio file into the Scarleta chat: a field recording, a sound-design bounce, or a snippet pulled from a video.
Ask what is in it
Type it in plain words: "what sounds are in this?" The AI figures out which analysis to run. No settings, no code.
Read the detected sounds
Get back the sound events Scarleta detected in the clip, tagged automatically and laid out right there in the conversation.
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the detected sound tags 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 detected sound tags 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
Know every sound in your audio
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
Tag a whole sound library with the API
Running many files at once? Send a batch of clips to a sound-tagging recipe and let a webhook call you back when each one is done.
curl https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer $SCARLETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "rec_0001_identify_sounds",
"audio_urls": [
"https://example.com/clip.wav"
]
}'Find out what is in your audio
Start on your free tokens: upload a clip, ask what sounds are in it, and read the tags right in the chat. Top up only when you need more.
Frequently asked questions
What do I get back?
The sounds Scarleta detected in your clip, returned as tags and sound events. You can view the results in the chat and export the analysis as CSV or JSON to use in your own tools.
What kinds of sounds can it detect?
It is open-ended sound recognition across any content: speech, music, animals, vehicles, machinery, alarms and many more everyday sound events. It picks from its own built-in set of sounds.
Can I search for my own custom label, like a specific product name?
That is a different tool. This page identifies sounds from a built-in vocabulary. If you want to score a clip against your own free-text labels, use the Match audio to your own labels page.
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 begin at $10. No subscription.
Do I need to install anything?
No. Upload a clip in the Scarleta chat and ask. It runs in your browser with nothing to download.
Can I tag a lot of files from my own app?
Yes. Developers can send many files at once through our API and get called back by webhook when every one is done. See the docs.