Transforms existing audio samples into new high-quality compositions using text instructions. This node takes an input audio file and modifies it based on your text prompt to create new audio content.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `model` | The AI model to use for audio transformation | COMBO | Yes | "stable-audio-2.5" |
| `prompt` | Text instructions describing how to transform the audio (default: empty, max length: 10000 characters) | STRING | Yes |  |
| `audio` | Audio must be between 6 and 190 seconds long | AUDIO | Yes |  |
| `duration` | Controls the duration in seconds of the generated audio (default: 190) | INT | No | 1-190 |
| `seed` | The random seed used for generation (default: 0) | INT | No | 0-4294967294 |
| `steps` | Controls the number of sampling steps (default: 8) | INT | No | 4-8 |
| `strength` | Parameter controls how much influence the audio parameter has on the generated audio (default: 1.0) | FLOAT | No | 0.01-1.0 |

**Note:** The input audio must be between 6 and 190 seconds in duration. The prompt text has a maximum length of 10,000 characters.

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `audio` | The transformed audio generated based on the input audio and text prompt | AUDIO |

> 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/StabilityAudioToAudio/en.md)

---
**Source fingerprint (SHA-256):** `4d320c851a58b58d1a744ca64295fe0cf3002455944ea1c5484b0c2df3ecd4d5`