Studio-clean audio from a noisy take.
Upload a noisy podcast, voice memo, or old recording and ask Scarleta to clean it up. It removes background noise, enhances the voice, and hands you back a processed audio file right in the chat.
How it works
No setup, no plugins. Just ask, and get the file back.
Upload your recording
Drop an audio file into the Scarleta chat: a noisy podcast episode, a phone voice memo, an old tape transfer.
Ask to clean it up
Type it in plain words: "remove the background noise" or "clean up this recording." The AI figures out what to run. No settings, no code.
Download the clean file
Get back a processed audio file with the noise reduced and the voice enhanced, ready to download and use, right in the conversation.
Hear the difference
Hear the difference noise removal makes
The noisy original before, and the cleaned-up file after.
Noise removed
Before · Noisy recording
Built-in storage
Every result is saved to your library, 1 TB free.
The files you bring and the noise-free audio 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 noise-free audio 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 noise removal in action
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
Cleaning up a whole archive? Send a batch of files to a noise-reduction 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.
curl https://api.scarleta.ai/v1/batch \
-H "Authorization: Bearer $SCARLETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe_id": "rec_1003_cat_voice_denoise",
"audio_urls": [
"https://example.com/noisy-episode.mp3"
],
"webhook_url": "https://your-app.com/hooks/scarleta"
}'
# 202 { "data": { "batch_id": "…", "status": "IN_QUEUE" }, "meta": … }
# Poll GET /v1/batch/:id/results, or wait for the one batch_completed
# webhook. Each result carries a download URL for the cleaned file.Turn a noisy take into a clean file
Start on your free tokens. Upload a recording, ask to clean it up, and download the result. Top up only when you need more.
Frequently asked questions
What do I get back?
A processed audio file with the background noise removed and the voice enhanced. You download it straight from the chat and use it anywhere.
What kinds of recordings does this work on?
Noisy podcasts and voice memos, interviews, and old or degraded recordings you want to restore. It is built to remove noise, enhance speech, and clean up audio.
What does cleaning up a recording cost?
Billed at $0.10 per minute of audio, from prepaid tokens (1 token = 1 second): a 2-minute recording is 120 tokens, or $0.20. New accounts start with 300 free tokens, top-ups start at $10, and there is no subscription.
Do I need audio editing software?
No. Upload a recording in the Scarleta chat and ask. It runs right in your browser, nothing to download or set up.
Can I denoise many recordings from my own app?
Yes. Developers can send many recordings at once through our API and get called back by webhook when the batch is done. Batch needs a paid account. See the docs to get started.