Noise Reduction API

The Noise Reduction API reduces continuous background noise mixed with one speaker's voice and returns an MP3 or WAV file.

API overview

Item	Value
Base URL	https://api.kitschlabs.com
Authentication	xi-api-key: <API_KEY>
Request	multipart/form-data
Endpoint	POST /v1/audio-isolation
Required field	audio
Default output	mp3_44100_128 (audio/mpeg)
Additional output	wav_48000 (audio/wav)
Maximum input	50 MiB, 60 seconds

How do I authenticate?

Send your issued API key in the xi-api-key header. Store the real key in a server environment variable or secret management service, and do not include it in browsers, app bundles, or logs.

xi-api-key: <API_KEY>

How do I reduce background noise?

Send a regular audio file with file_format=other. Save the response body to a file with the matching extension.

cURL

curl --request POST \
  "https://api.kitschlabs.com/v1/audio-isolation" \
  --header "xi-api-key: <API_KEY>" \
  --form "audio=@sample.wav" \
  --form "file_format=other" \
  --output enhanced.mp3

Python

import os

import requests

with open("sample.wav", "rb") as audio:
    response = requests.post(
        "https://api.kitschlabs.com/v1/audio-isolation",
        headers={"xi-api-key": os.environ["KITSCH_API_KEY"]},
        data={"file_format": "other"},
        files={"audio": audio},
        timeout=120,
    )

response.raise_for_status()

with open("enhanced.mp3", "wb") as output:
    output.write(response.content)

JavaScript

import { readFile, writeFile } from "node:fs/promises";

const form = new FormData();
form.append("audio", new Blob([await readFile("sample.wav")]), "sample.wav");
form.append("file_format", "other");

const response = await fetch("https://api.kitschlabs.com/v1/audio-isolation", {
  method: "POST",
  headers: { "xi-api-key": process.env.KITSCH_API_KEY },
  body: form,
});

if (!response.ok) {
  throw new Error(`${response.status}: ${await response.text()}`);
}

await writeFile("enhanced.mp3", Buffer.from(await response.arrayBuffer()));

For WAV output, set output_format=wav_48000 in the query.

curl --request POST \
  "https://api.kitschlabs.com/v1/audio-isolation?output_format=wav_48000" \
  --header "xi-api-key: <API_KEY>" \
  --form "audio=@sample.wav" \
  --output enhanced.wav

Which fields do I send?

Field	Location	Type	Required	Description
audio	form	file	Yes	Voice audio to process. Up to 50 MiB and 60 seconds
file_format	form	string	No	other for regular files or pcm_s16le_16 for raw PCM
output_format	query	string	No	mp3_44100_128 or wav_48000

pcm_s16le_16 is 16 kHz, mono, little-endian 16-bit raw PCM. Use other for encoded audio such as WAV, MP3, FLAC, and OGG.

Uploaded input files are not stored after processing is complete. Do not log API keys or complete file contents in your application.

Responses and errors

A successful request returns audio binary in the selected format. Use the response's x-kitsch-request-id when contacting support.

Header	Description
x-kitsch-request-id	Request tracking ID

Status	Meaning	Recommended action
401	API key is missing or invalid	Check the key and xi-api-key header
402	Not enough available credits	Check the Billing status
403	Noise Reduction is not enabled	Check the service access for the account
413	File size or input duration exceeded	Reduce it to 50 MiB and 60 seconds or less
422	Corrupted audio, invalid PCM, or unsupported format	Check the file and file_format
429	API key request limit exceeded	Follow Retry-After and apply backoff
503	Temporarily unable to process the request	Record the request ID and retry a limited number of times

Successful requests are billed by rounding the input audio duration up to the next started second. Failed requests and requests rejected during input validation are not charged.