# Set Reference Audio

This node sets the reference audio for the "ace step 1.5" process. It takes a conditioning input and optionally a latent representation of audio, then attaches that latent data to the conditioning so later nodes can use it as reference audio timbre latents. This node is marked as experimental.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `conditioning` | The conditioning data to which the reference audio information will be attached. | CONDITIONING | Yes |  |
| `latent` | An optional latent representation of the reference audio (default: None). When provided, its samples are appended to the conditioning as reference audio timbre latents. | LATENT | No |  |

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `conditioning` | The modified conditioning data, now containing the reference audio timbre latents if the optional `latent` input was provided. | CONDITIONING |

> 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/ReferenceTimbreAudio/en.md)

---
**Source fingerprint (SHA-256):** `2ddccb7676fc45a5324ba32dde0cd2f8f24388ceec20c88a475e1aa9d4276be0`
