> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orisu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Generate Sound Effects

> Create a short sound-effect audio clip from a text description using ElevenLabs.

Generate Sound Effects converts a text prompt into a short audio clip: footsteps, thunder, UI clicks, ambient textures, and more.

This node runs on ElevenLabs and consumes credits when it runs.

## When to use

* Adding foley sound effects to video workflows
* Generating ambient soundscapes for creative projects
* Producing UI or notification sounds from a description

## Inputs

<ParamField body="Text" type="text" required>
  A description of the sound effect to generate. Required. Supports loop mode.
</ParamField>

<Note>
  **Inline prompt.** You don't need a separate Text Prompt node for fixed text —
  type it directly on the node. The inline field appears whenever the text input is
  unconnected and disappears once you wire a text input in. Connect a Text Prompt node
  only when you want to drive the text from upstream or expose it as an app input.
  Type `@` to mention a connected input by name — text inputs insert their content into
  the text, media inputs insert their name.
</Note>

## Outputs

<ParamField body="Audio" type="audio">
  The generated sound-effect clip as an audio file.
</ParamField>

## Configuration

<ParamField body="duration_seconds" type="number" default={0}>
  Duration of the output clip in seconds (0.5 to 30). Set to 0 to let ElevenLabs auto-guess the best duration.
</ParamField>

<ParamField body="prompt_influence" type="number" default={0.3}>
  How closely the output follows the text prompt (0 to 1). Higher values increase prompt adherence; lower values give the model more creative freedom.
</ParamField>

<ParamField body="loop" type="boolean" default={false}>
  When enabled, the output is designed to loop seamlessly.
</ParamField>

## Example

Connect a **Text Prompt** node describing the desired sound (e.g. "deep rolling thunder with distant rain") to the Text input, then wire the Audio output to a **Composer** node or download it directly.

<Note>
  Pricing is flat per generation (\$0.12). See [Audio models](/models/audio) for supported models and [Model settings](/models/settings) for available options.
</Note>