The Empty Ace Step 1.5 Latent Audio node creates an empty latent tensor designed for audio processing. It generates a silent audio latent of a specified duration and batch size, which can be used as a starting point for audio generation workflows in ComfyUI. The node calculates the latent length based on the input seconds and a fixed sample rate.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `seconds` | The duration of the audio to generate, in seconds (default: 120.0). | FLOAT | Yes | 1.0 - 1000.0 |
| `batch_size` | The number of latent images in the batch (default: 1). | INT | Yes | 1 - 4096 |

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `LATENT` | An empty latent tensor representing silent audio, with a type identifier of "audio". The output also includes a `downscale_ratio_temporal` value of 1764, which is used for temporal downscaling in audio processing. | LATENT |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAceStep1.5LatentAudio/en.md)

---
**Source fingerprint (SHA-256):** `dc87da02daa14d19afb0a1b421ee87fdcaf53d5a1e5f5175bfcc8e9fbcd7fa48`