Python · JS · RESTaudio + video in/outEU-hosted · GDPR

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, REST, webhooks. EU-hosted.

Get API keyRead 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.

comparison · v2
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.
docs.cleanvoice.ai — full configuration reference

One request, edited audio back.

01

Get your API key

Sign up and copy a key from the Cleanvoice dashboard. Free credits included.

02

Install the SDK

pip install cleanvoice-sdk or npm i @cleanvoice/cleanvoice-sdk, or call the REST API directly.

03

Send a file with your edit config

The cleanup you would do by hand in an editor (fillers, silences, breaths, noise) is a set of flags on one request.

04

Webhook or poll, then download

Jobs run async: SDKs poll for you, or a webhook fires. The result links to your edited file.

docs.cleanvoice.ai — full configuration reference →
import { Cleanvoice } from '@cleanvoice/cleanvoice-sdk';const client = new Cleanvoice({  apiKey: process.env.CLEANVOICE_API_KEY,});// The manual editing pass, as flagsconst result = await client.process('https://example.com/episode.mp3', {  fillers: true,  long_silences: true,  mouth_sounds: true,  breath: true,});console.log('Edited:', result.audio.url);

Why developers trust us

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

REGION EU-CENTRAL

EU-Hosted

Servers and GPU located in the EU

ISO 27001GDPRAUDITED · ON-PREMISE ON REQUEST

ISO 27001 & GDPR Compliant

DPA, SLA and on request even on premise deployment

YOUR FILESMODEL TRAININGTRAINED ON OUR OWN STUDIO DATA

No Training on Your Data.

We record our own dataset in professional studios.

Simple, transparent pricing

Pay as you go or subscribe. One rate across every capability. Full pricing →

Pay as You Go

  • 5 hours

    $2.20/h

    $11 total

  • 10 hours

    $2.00/h

    $20 total

  • 30 hours

    $1.50/h

    $45 total

  • 200 hours

    $1.00/h

    $200 total

Credits valid for 2 years.

Subscription

  • 10 hours / mo

    $1.10/h

    $11/mo

  • 30 hours / mo

    $0.93/h

    $28/mo

  • 100 hours / mo

    $0.90/h

    $90/mo

  • 200 hours / mo

    $0.88/h

    $175/mo

Unused hours roll over up to 3× your plan.

200+ hours

Custom

From$0.20/ hour

Tailored feature mix and volume pricing for production workloads.

  • Custom API endpoints
  • Priority support
  • Custom billing
Book a call

Uploads are rounded up to the nearest minute.

Enterprise-grade by default

Contractual uptime, audited security, and a team that knows how procurement works.

FORM CV-SLA-01

Uptime SLA

Contractual availability, backed by a public status page.

SIGNED
FORM CV-SUP-02

Dedicated support

A named human, with priority response times.

HUMAN ✓
FORM CV-PRO-03

Procurement-ready

Security questionnaires, DPA review, and vendor onboarding.

FILED
FORM CV-ONB-04

Technical onboarding

Our engineers on the call, from kickoff to production.

SHIPPED
FORM CV-LIC-05

Flexible terms

Pay-as-you-go, subscriptions, or volume agreements.

FAIR
FORM CV-RET-06

Zero retention, optional

Files auto-delete after 7 days by default — or the moment your job finishes.

PURGED

Free credits for baby startups

Building with audio or video on a tight budget? Request up to 200 hours of free Cleanvoice API credit from your dashboard.

Up to 200 hours

of free API credit

Create a free account, open API Keys in the developer dashboard and click Request credits. Tell us your website and use case, and we’ll contact you in a few days.

Request credits

The request form shows on the API Keys page while your account has less than one hour of credit. One request per account.

More Cleanvoice APIs

Same API, other jobs.

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.