> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Sonilo Audio Ducking

> Mixes narration over a music bed, dipping the music under the voice automatically so dialogue stays clear without manual automation.

![Sonilo Audio Ducking](https://media.empiriolabs.ai/model-logos/sonilo-audio-ducking.png)

[Sonilo](/providers/sonilo) · Audio Generation

`POST /v1/audio/generations`

Mixes narration over a music bed, dipping the music under the voice automatically so dialogue stays clear without manual automation.

## At a glance

| Field               | Value                                                            |
| ------------------- | ---------------------------------------------------------------- |
| Model id            | `sonilo-audio-ducking`                                           |
| Model release date  | -                                                                |
| Input modalities    | Audio, Video                                                     |
| Output modalities   | Audio                                                            |
| Context window      | -                                                                |
| Weight precision    | -                                                                |
| Features            | audio_in, audio_out, ducking, audio_generation, commercial_ready |
| Native inference    | No                                                               |
| New                 | Yes                                                              |
| Supported endpoints | `POST /v1/audio/generations`                                     |
| Alternate model ids | `sonilo/sonilo-audio-ducking`                                    |

## Pricing

| Charge        | Spec                 | Rate     |
| ------------- | -------------------- | -------- |
| Audio ducking | per generated second | \$0.0012 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/audio/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "sonilo-audio-ducking", "voice_url": "https://example.com/voice.mp3", "music_url": "https://example.com/music.mp3"}'
```

## Parameters

| Parameter   | Type   | Required | Default | Description                                                                                          |
| ----------- | ------ | -------- | ------- | ---------------------------------------------------------------------------------------------------- |
| `voice_url` | string | no       | -       | Narration, dialogue, or a talking video to keep in front. In the playground, attach this file first. |
| `music_url` | string | no       | -       | Music track to duck underneath the voice. In the playground, attach this file second.                |

## Notes

**Inputs**

* A voice track: narration, dialogue, or a talking video
* A music track to sit underneath it

**Controls**

Supports a voice URL and a music URL. In the playground, attach the voice first and the music second.

**Limits**

* Each input up to 300MB
* A talking video as the voice input returns that video with the mixed audio; an audio voice input returns audio

**Billing**

* Charged per generated second at the catalog rate, with a 10 second minimum
* A request rejected before generation is not billed.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/sonilo-audio-ducking`.