Studio-quality speech from noisy recordings

veed/clean-audio

Studio-quality speech from noisy recordings

Inference

Commercial use

Schema

LLMs

Playground API

About

VEED Clean Audio

Removes background noise from speech recordings. This is the model behind the Clean Audio toggle in the VEED editor, where it has processed every recording since August 2026: MossFormer2 speech enhancement at 48 kHz, followed by VEED's post chain — a speech-gated suppression floor that keeps quiet and distant words instead of cutting them, presence/air EQ, and BS.1770 loudness normalization.

Input

audio_url: any audio or video ffmpeg can decode (wav, mp3, m4a, aac, ogg, mp4, mov, webm, ...). A video's audio track is used; multi-channel input is mixed down to mono.
Up to 30 minutes of audio and 512 MB per file. Public URLs only (private networks and cloud metadata addresses are refused; redirects are not followed) or a data URI.
Processing takes roughly 0.2–0.5× the audio duration: a 10-minute file returns in 2–5 minutes.

Output

48 kHz mono 16-bit PCM in FLAC (default) or WAV, same duration as the input.
Integrated loudness −19 LUFS, true peak ≤ −1.1 dBTP (skip by passing target_lufs = null).

Pricing

1 unit = 1 minute of input audio. The duration is rounded to whole seconds, then up to the next full minute; minimum 1 unit. A 5:00.011 file is 5 units, a 5:01 file is 6. Failed requests are not billed.

Errors

Invalid input returns HTTP 422 with the offending field: unreachable or non-public audio_url, no audio track, more than 30 minutes or 512 MB, undecodable audio.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("veed/clean-audio", {
  input: {
    audio_url: "https://v3b.fal.media/files/b/0aaaa91c/5KspxZ3psz3KmDvSeYVk__noisy_example.m4a"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In an environment where you cannot set environment variables, you can configure the API key manually on the client.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("veed/clean-audio", {
  input: {
    audio_url: "https://v3b.fal.media/files/b/0aaaa91c/5KspxZ3psz3KmDvSeYVk__noisy_example.m4a"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("veed/clean-audio", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("veed/clean-audio", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

audio_url string* required

The recording to clean. Any audio or video ffmpeg can decode (wav, mp3, m4a, aac, ogg, mp4, mov, webm, ...); a video's audio track is used and multi-channel input is mixed down to mono. Up to 30 minutes and 512 MB. A public URL or a data URI.

strength float

How much of the original is allowed to remain under speech: the suppression floor is 1 - strength (the default 0.874 is the validated -18 dB). Lower keeps more room tone behind the voice; silence between words is always fully cleaned. Default value: 0.874

target_lufs float

Integrated loudness of the output (ITU-R BS.1770). The default -19 LUFS is the level the VEED editor delivers; true peak is capped at -1.1 dBTP. Pass null through the API to skip loudness normalization and keep the input level. Default value: -19

output_format OutputformatEnum

Container for the 48 kHz mono 16-bit output. FLAC is lossless at about half the size of WAV. Default value: "flac"

Possible enum values: flac, wav

{
  "audio_url": "https://v3b.fal.media/files/b/0aaaa91c/5KspxZ3psz3KmDvSeYVk__noisy_example.m4a",
  "strength": 0.874,
  "target_lufs": -19,
  "output_format": "flac"
}

Output#

audio Audio* required

The denoised recording: 48 kHz mono 16-bit, same duration as the input, loudness-normalized.

audio_duration float* required

Input duration in seconds. Billing: whole seconds rounded up to full minutes, minimum 1 unit.

{
  "audio": {
    "file_name": "denoised.flac",
    "url": "https://v3b.fal.media/files/b/0aaaa933/tYOEy9H8r67qdQEC33yMe_denoised.flac",
    "content_type": "audio/flac"
  }
}

Other types#

Audio#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

veed/clean-audio, details and endpoints

veed/clean-audio

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

VEED Clean Audio

Input

Output

Pricing

Errors

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

Audio#