Enhance, clean, and edit audio or video. Via API.

Studio sound like Adobe Podcast. Noise removal. Dead air and filler editing. One endpoint — for audio and video files.

Read the docs Get API key

Two products, one endpoint

Send an audio or video file. Pick what you need. Get back the result.

Make the audio sound better

Speech Enhancement API

Like Adobe Podcast Enhance — but via API. Loudness normalization, level balancing across speakers, EQ, and dereverb.

Raw recording — dull and uneven

0:00 / 0:00

Same recording — raw vs. studio-enhanced. Switch mid-playback.

This audio is a part of "Podcast 201 // Your body can heal itself with Osteopath Cole Clayton" by School of Calisthenics licensed under CC BY 3.0, edited from original

Works on .mp3, .wav, .m4a, .flac, .mp4, .mov, .mkv. For video, Cleanvoice processes the audio track and returns cleaned audio plus edit timestamps.

Read the docs

How it works

Get your API key

Create an account and copy your API key from the Cleanvoice dashboard.

Install the SDK

Use the official Python or JavaScript SDK. Alternatively, call the REST API directly.

Submit your file

Use a local file or url of your audio/video we should process.

Poll or Webhook

Jobs run async. SDKs handle polling automatically, alternatively use our webhook to upload the result to your s3 storage.

import { Cleanvoice } from '@cleanvoice/cleanvoice-sdk';

const client = new Cleanvoice({ apiKey: process.env.CLEANVOICE_API_KEY });

// Remove fillers, dead air, mouth sounds + denoise and normalize.
const result = await client.process('https://example.com/episode.mp3', {
  fillers: true,
  long_silences: true,
  mouth_sounds: true,
  remove_noise: true,
  normalize: true,
});

console.log('Cleaned audio:', result.audio.url);
await result.audio.download('cleaned.mp3');

import { Cleanvoice } from '@cleanvoice/cleanvoice-sdk';

const client = new Cleanvoice({ apiKey: process.env.CLEANVOICE_API_KEY });

// Studio-grade polish: denoise, studio sound, and loudness to -16 LUFS.
const result = await client.process('https://example.com/raw-recording.wav', {
  remove_noise: true,
  studio_sound: true,
  normalize: true,
  target_lufs: -16,
});

console.log('Enhanced audio:', result.audio.url);

import { Cleanvoice } from '@cleanvoice/cleanvoice-sdk';

const client = new Cleanvoice({ apiKey: process.env.CLEANVOICE_API_KEY });

// Transcript + chapters + ready-to-post social copy in one call.
const result = await client.process('https://example.com/episode.mp3', {
  transcription: true,
  summarize: true,
  social_content: true,
});

if (result.transcript) {
  console.log(result.transcript.text);
  console.log(result.transcript.chapters);
}

if (result.summarization) {
  console.log(result.summarization.title);
  console.log(result.summarization.key_learnings);
}

# 1. Request a signed upload URL
SIGNED_URL=$(curl -s -X POST "https://api.cleanvoice.ai/v2/upload?filename=episode.wav" \
  -H "X-API-Key: $CLEANVOICE_API_KEY" | jq -r '.signedUrl')

# 2. Upload the local file straight to storage
curl -X PUT "$SIGNED_URL" \
  -H "Content-Type: audio/wav" \
  --data-binary @./recordings/episode.wav

# 3. Submit the edit using the file URL (query string stripped)
FILE_URL="${SIGNED_URL%%\?*}"
curl -X POST https://api.cleanvoice.ai/v2/edits \
  -H "X-API-Key: $CLEANVOICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "files": ["'"$FILE_URL"'"],
      "config": { "fillers": true, "long_silences": true, "normalize": true }
    }
  }'

import { Cleanvoice } from '@cleanvoice/cleanvoice-sdk';

const client = new Cleanvoice({ apiKey: process.env.CLEANVOICE_API_KEY });

// Clean the audio track and get it back in the original video container.
const result = await client.process('https://example.com/interview.mp4', {
  video: true,
  fillers: true,
  long_silences: true,
  remove_noise: true,
});

console.log('Cleaned video:', result.media.url);

import { Cleanvoice } from '@cleanvoice/cleanvoice-sdk';

const client = new Cleanvoice({ apiKey: process.env.CLEANVOICE_API_KEY });

// Submit without blocking and deliver the result straight to your bucket.
const editId = await client.createEdit('https://example.com/episode.mp3', {
  fillers: true,
  normalize: true,
  signed_url: process.env.S3_PUT_URL,
});

// Later - e.g. in a worker or webhook handler - check the status.
const edit = await client.getEdit(editId);
console.log(edit.status); // PENDING -> ... -> SUCCESS

import os
from cleanvoice import Cleanvoice

client = Cleanvoice.from_env()

# Submit without blocking and deliver the result straight to your bucket.
edit_id = client.create_edit(
    "https://example.com/episode.mp3",
    fillers=True,
    normalize=True,
    signed_url=os.environ["S3_PUT_URL"],
)

# Later - e.g. in a worker - check the status.
edit = client.get_edit(edit_id)
print(edit.status)  # PENDING -> ... -> SUCCESS

# Submit the job and capture the edit id
EDIT_ID=$(curl -s -X POST https://api.cleanvoice.ai/v2/edits \
  -H "X-API-Key: $CLEANVOICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "files": ["https://example.com/episode.mp3"],
      "config": { "fillers": true, "normalize": true, "signed_url": "'"$S3_PUT_URL"'" }
    }
  }' | jq -r '.id')

# Poll until status is SUCCESS (Cleanvoice also PUTs the result to your signed_url)
curl https://api.cleanvoice.ai/v2/edits/$EDIT_ID \
  -H "X-API-Key: $CLEANVOICE_API_KEY"

Why developers choose us

Ship audio features faster with APIs built for production workloads.

EU-hosted

Servers and GPU located in the EU

ISO 270001 & GDPR Compliant

DPA, SLA and on request even on premise deployment

No training on your data.

We record our own dataset in professional studios.

Soon

Low-code, no-code, no problem.

Drag-and-drop automations — plug Cleanvoice into your flow with Make or n8n.

Google Drive

Dropbox

FTP server

RSS feed

Google Drive

YouTube

Google Drive

Dropbox

FTP server

RSS feed

Google Drive

YouTube

Get started with Make

n8nComing soon

Simple, transparent pricing

Pay as you go or subscribe. Same rates for every API. 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
$1.00/h
$30/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.

Free credits for baby startups

Early-stage team building with audio? We’ll give you up to 200 hours of Cleanvoice API credits.

200 hours

free API credits

Use them on any Cleanvoice API: transcription, audio cleaning, enhancement, and more. Email us a short note about your startup and what you’re building — we’ll set you up personally.

Apply by email

Include your startup name, what you’re building, and how you’d use Cleanvoice. We usually reply within 1–2 business days.

Pick a model off the shelf — or we’ll build yours.

Every Cleanvoice model can be tailored to your use case. And if what you need isn’t on the shelf yet, we’ll train a brand-new one.

Real-time Enhancer

Cleanvoice

ASRImprover

Speech Series

Cleanvoice

StemSeparation

Vol.1 · Stems

SingingEnhancer

Cleanvoice

musicisolator

Cleanvoice

ForensicAudio

Cleanvoice

Always Listening

Wake-wordDetector

Cleanvoice

Custom model

Your idea

Tell us what to build →

Request a custom model

Enhance, clean, and edit audio or video. Via API.

Two products, one endpoint

Speech Enhancement

Audio Editing

How it works

Get your API key

Install the SDK

Submit your file

Poll or Webhook

EU-hosted

ISO 270001 & GDPR Compliant

No training on your data.

Simple, transparent pricing

Pay as You Go

Subscription

Custom

Free credits for baby startups

Real-time Enhancer

ASRImprover

StemSeparation

SingingEnhancer

musicisolator

ForensicAudio

Wake-wordDetector

Your idea