# VEED Clean Audio 1.0

> Audio AI Model by VEED — available on Layer

Remove background noise from speech while keeping quiet and distant words intact.

VEED Clean Audio is the speech enhancement model behind the Clean Audio toggle in the VEED editor. It pairs MossFormer2 enhancement at 48 kHz with a speech-gated suppression floor, so room noise, hum and hiss drop out while quiet and distant words survive instead of being cut. Output is loudness-normalized to -19 LUFS and keeps the source duration. Accepts any audio or video file up to 30 minutes; a video's audio track is used. Ideal for voice-over, dialogue and interview cleanup in game trailers and cutscenes.

## Specifications

| Property | Value |
|----------|-------|
| Provider | VEED |
| Category | Audio |
| Price | 0.005 / second, minimum 0.3 per run |

## Frequently Asked Questions

### How much does VEED Clean Audio 1.0 cost? Is it free?

Generating assets on Layer requires using Creative Units. This model's current price is 0.005 / second, minimum 0.3 per run.

### 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 VEED Clean Audio 1.0](https://layer.ai/me/session/new?baseModelId=VEED_CLEAN_AUDIO) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)