ElevenLabs models API

Call 1 ElevenLabs model through one PopNow API key: ElevenLabs Audio Isolation. Prices start at $0.0022 per second.

models: 1
endpoints: 1
starting price, per second: $0.0022

ElevenLabs models

ElevenLabs Audio Isolationelevenlabs/audio-isolation/audio-to-audioNewIsolate clear speech from noisy audio or video, delivered as an MP3AudioFrom$0.0022per second

Choosing ElevenLabs for speech clean-up

One endpoint that keeps the speech and drops the rest

ElevenLabs supplies one entry in the catalog, ElevenLabs Audio Isolation. It takes an audio file or a video of up to one hour, separates speech from everything around it and returns the speech. The request has a single field, audio_url, so there is nothing to tune: no strength, no target loudness and no output format. The result is always an MP3, even when the source is a video, which means a video comes back as its cleaned sound and not as a new video. In testing, a noisy voice message went from a noise floor of about minus 24 dB to about minus 35 dB, and short clips finished in a few seconds.

Pick the right tool for the sound you want to remove

Use Audio Isolation for spoken recordings with fans, traffic, hum or room noise behind them: podcasts, interviews, voice messages and narration recorded on a phone. It is not a stem splitter. To separate a song into vocals and a backing track, use Vocal Isolator. To take a music bed out of a video and keep the picture, use Video Music Remover, which returns a video. Billing is per second of the source, rounded up to whole seconds, with a one second minimum, so clean only the part of a long recording that you need and trim silence before you submit it.

Build the job so the result fits your pipeline

Call /api/v1/jobs/createTask from your backend with a sk-popnow- key and the full public call name from the task reference. Send a direct link to the file, or upload it first and pass the stored reference. Store the taskId with the source URL and the source length. Fetch /api/v1/jobs/recordInfo or verify a completion webhook, then download the MP3 and listen to a passage with quiet speech as well as a passage with loud noise, because that is where artefacts show first. If the source is a video and you need one back, put the MP3 over the original picture in your own editing step, keeping the source file so the two stay in sync.

ElevenLabs API prices

See pricing

Model	Best for	List price	PopNow price	You save
ElevenLabs Audio Isolation`elevenlabs/audio-isolation/audio-to-audio`	Voice Cleaner	—	$0.0022per second

List prices are each maker's own published price for the same output, checked on Nov 3, 2026. Prices shown are starting prices; open a model for every tier.

Latest ElevenLabs additions

Oct 8, 2026ElevenLabs Audio IsolationAudio · From $0.0022 per secondNew

Changelog

Call a ElevenLabs model

The same request works for every model: change the model name and its input.

curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "elevenlabs/audio-isolation/audio-to-audio",
  "input": {
    "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3"
  }
}'

import os, uuid, requests

res = requests.post(
    "https://api.popnow.ai/api/v1/jobs/createTask",
    headers={
        "Authorization": f"Bearer {os.environ['POPNOW_API_KEY']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "model": "elevenlabs/audio-isolation/audio-to-audio",
        "input": {
            "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3"
        }
    },
    timeout=30,
)
body = res.json()
if body["code"] != 200:
    raise RuntimeError(f'{body["code"]} {body["msg"]}')
print(body["data"]["taskId"])  # poll this id, or wait for your callBackUrl

const res = await fetch("https://api.popnow.ai/api/v1/jobs/createTask", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.POPNOW_API_KEY}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    "model": "elevenlabs/audio-isolation/audio-to-audio",
    "input": {
      "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3"
    }
  }),
});
const { code, msg, data } = await res.json();
if (code !== 200) throw new Error(`${code} ${msg}`);
console.log(data.taskId); // poll this id, or wait for your callBackUrl

Frequently asked questions

What can I send to Audio Isolation?

Send one audio_url that points to an audio file or a video of up to one hour. The field is the only input, so there is no prompt and no setting to choose. Files that are longer than the limit should be split into parts and processed one by one.

Does it return a video when I send a video?

No. The result is always an MP3 of the cleaned speech, even when the source is a video. If you need a video back, add the MP3 over the original picture in your own editor, or use Video Music Remover when the goal is to remove music and keep the picture.

Can I set the strength or the loudness?

No. The endpoint has no noise reduction, loudness or format fields, so the result comes out the same way every time. If you need a set loudness for a podcast or a broadcast, measure and adjust the MP3 in your own audio step after the job has finished.

How is Audio Isolation billed?

Billing follows the length of the source, rounded up to whole seconds with a one second minimum, at the per-second rate shown on the model page. A video is billed on its running time. The request holds the amount for the file first and settles it when the job finishes.

Is this the right tool for removing music?

It is built for speech and everyday noise. Music under a voice is not always separated cleanly, so use Video Music Remover for videos with a music bed, and Vocal Isolator when you want to split a song into its vocals and its backing track.

Other model makers

All model makers

Start building in minutes

One key for every model, a USD balance you top up when you need to, and an exact price before every run.

Get API key Try in Playground