Loading API documentation
Studio-quality speech from noisy recordings
veed/clean-audio
Studio-quality speech from noisy recordings
Inference
Commercial use
Loading API documentation
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.
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.
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.
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientSet FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"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);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});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",
});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,
});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);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.
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.
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.
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);Read more about file handling in our file upload guide.
audio_url string* requiredThe 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 (call /video to get the video back with the cleaned track) and multi-channel input is mixed down to mono. Up to 30 minutes and 512 MB. A public URL or a data URI.
strength floatHow 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 floatIntegrated 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 OutputformatEnumContainer 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"
}The denoised recording: 48 kHz mono 16-bit, same duration as the input, loudness-normalized.
audio_duration float* requiredInput duration in seconds. Billing: whole seconds rounded up to full minutes, minimum 1 unit.
{
"audio": {
"url": "https://v3b.fal.media/files/b/0aaaa933/tYOEy9H8r67qdQEC33yMe_denoised.flac",
"content_type": "audio/flac",
"file_name": "denoised.flac"
}
}url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.