# ElevenLabs Audio Isolation

> Audio AI Model by ElevenLabs — available on Layer

Isolate clean voice from noisy recordings by removing background noise and music.

ElevenLabs Audio Isolation uses deep learning to separate vocal signals from background noise, music, and ambient sounds in audio recordings. It transforms noisy recordings into clean, studio-quality speech with minimal artifacts. Supports WAV, MP3, FLAC, OGG, and AAC inputs up to 500 MB and 1 hour in length. Ideal for podcast post-production, interview cleanup, video content, and voice-over extraction.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ElevenLabs |
| Category | Audio |
| Price | 0.1 / second |

## Capabilities

- Auto Duration

## Frequently Asked Questions

### How much does ElevenLabs Audio Isolation cost? Is it free?

Generating assets on Layer requires using Creative Units. This model's current price is 0.1 / second.

### How does Layer's pricing work?

There are no seat fees, feature gates, or plans on Layer. Instead, our platform uses a consumption based system with Creative Units (CUs) with a flexible monthly subscription. Every generation on Layer (image, video, 3D, or audio) consumes a Creative Unit, and you only pay for what you create.

---

[Try ElevenLabs Audio Isolation](https://layer.ai/me/session/new?baseModelId=ELEVEN_LABS_AUDIO_ISOLATION) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)