New: Studio Sound v4

The Descript API alternative for automated editing.

Descript's API imports media into their editor, where the editing stays manual. The Cleanvoice API removes fillers, silences, breaths, and noise, adds studio sound, and returns the finished file. Python & JS SDKs or REST. EU-hosted.

Um, so today we're like, going to uh, clean up you know, the episode.

Tap for sound
Tap for sound
Tap for sound
Tap for sound

Or drop a file here, or .

Record up to 15 seconds, or drop audio or video up to 20 MB. Free, no account needed.

Read the docs
Veed
bHuman
Altered
Thames College
Teleprompter
Natural Reader
Veed
bHuman
Altered
Thames College
Teleprompter
Natural Reader

Two APIs, two different jobs.

What Descript's API covers, what the Cleanvoice API covers, and where the line between them is.

Every option in the docs →
Descript API scope
Import URLs into the editorPer Descript's developer docs: generate an import URL, upload media, and hand the user over to a Descript project. The editing itself happens in the app.
Cleanvoice API scope
The edit itselfFillers, long silences, mouth sounds, stutters, breaths, noise removal, studio sound, and loudness normalization, applied to the file you send and returned as a file.
Pricing model
Per minute of audioDescript ties API access to per-person editor plans. Cleanvoice bills by processed audio length: pay-as-you-go or subscription, with free credits at sign-up.
Automation
SDKs, REST, webhookspip install cleanvoice-sdk or npm i @cleanvoice/cleanvoice-sdk, or call REST directly. Jobs run async and a webhook fires when the file is ready.
Turnaround
5–10 min per hour of audioA 2–3 minute clip is usually done in about 30 seconds.

The editing pass, as flags.

The cleanup you would do by hand in an editor is a set of flags on one request. Turn on what your files need.

Every option in the docs →
1from cleanvoice import Cleanvoice
2
3client = Cleanvoice.from_env()
4
5result = client.process(
6    "raw-take.wav",
7    fillers=True,
8    breath=True,
9    mouth_sounds=True,
10    long_silences=True,
11)
12
13print(result.audio.url)
$ pip install cleanvoice-sdk

Pricing

From $0.01/ minute of audio

That's $0.60 an hour at enterprise volume, billed monthly or yearly. Self-serve plans from $0.75 an hour, or pay as you go at $1.50.

Compare plans
200 free hours

Startups get up to 200 hours of API credit. Request it from the API Keys page in your dashboard.

Request credits

Why developers trust us

All your data in your control. Each file processed securely.

  • EU-Hosted

    Servers and GPU located in the EU

  • ISO 27001 & GDPR Compliant

    DPA, SLA and on request even on premise deployment

  • No Training on Your Data.

    We record our own dataset in professional studios.

Frequently asked Questions.

Still have a question?

Send it over and a real person will answer.

support@cleanvoice.ai
Ask Now

Descript's developer docs describe an API for generating import URLs: your code uploads media and sends the user into a Descript project, where they edit in the app. There are no public endpoints that perform the edit, export the result, or automate assets. If that import flow is all your pipeline needs, it works fine — the gap appears when you want the editing itself to run without a person.

It replaces the cleanup work: fillers, long silences, mouth sounds, stutters, breaths, noise removal, studio sound, loudness normalization, and transcription all run from one request. It is not a multitrack editor; creative cuts and layout still belong in an editing app. You can run every file through the API first and open an editor only for the ones that need a human pass.

Descript sells API access as part of its editor plans, priced per person per month. Cleanvoice is priced by the audio you process: per-minute pay-as-you-go or a subscription, with no seats. For a pipeline, that means cost scales with volume instead of with the number of people who hold a login. Sign-up comes with free credits, and startups can request up to 200 hours of free API credit from the API Keys page in the app.

Yes. Send MP4, MOV, or WebM and you get the edited video back, with no need to extract and re-attach the audio track yourself.

A 2–3 minute clip is usually done in about 30 seconds, and an hour of audio takes 5–10 minutes. Processing runs in the background: the SDKs poll for you, or you register a webhook and get called when the file is ready.

New accounts start with free credits, so you can run real files before paying anything. There is also a no-signup playground at app.cleanvoice.ai/playground if you first want to hear what the flags do to a file of yours.

Get your API key.

Sign up, copy your key and send your first file.

Get your API keyBook a call