MireloTextToSFX - ComfyUI Built-in Node Documentation - ComfyUI

Generate a sound effect from a text description with Mirelo SFX. Describe the sound itself, not the picture it belongs to, and the node returns a single audio track of the requested length. Use it for foley, ambience, impacts and short musical textures without shooting or uploading video.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	Model to use. Selecting a model reveals the parameters specific to it: `prompt`, `negative_prompt`, `duration` and `seed`.	DYNAMIC_COMBO	Yes	`"sfx-2.0"`
`prompt`	Describe the sound, not the picture. 1 to 2000 characters.	STRING	Yes	1 to 2000 characters
`negative_prompt`	Sounds to avoid, as a short comma-separated list. May be left empty (default: empty). Maximum 1000 characters.	STRING	Yes	Up to 1000 characters
`duration`	Length of the sound in seconds. (default: 5.0)	FLOAT	Yes	0.1 to 600.0 (step 0.1)
`seed`	The seed for the request. Results are non-deterministic, so the same seed does not repeat a sound. (default: 42)	INT	Yes	0 to 4294967295

The node stops with an error when prompt is empty or longer than 2000 characters, and when negative_prompt is longer than 1000 characters.

Outputs

Output Name	Description	Data Type
`AUDIO`	The generated sound effect, as long as `duration`.	AUDIO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): b09a9562cea636702acd9fc50feb38b272a558f8b8509da21f5fada2abd9fd48