Back to Nodes
ElevenLabs Sound Effects V2

ElevenLabs Sound Effects V2

Official

Generate realistic sound effects from text descriptions, perfect for adding atmosphere to your projects.

Nodespell AI
AI / Audio / Elevenlabs

Generate realistic sound effects from text descriptions, perfect for adding atmosphere to your projects.

Model Overview

This model generates sound effects based on your text descriptions. It's powered by ElevenLabs' advanced sound effects technology, allowing you to create custom audio elements for a wide range of applications.

Best At

Creating unique and specific sound effects for media, games, or any project requiring custom audio. It excels at translating descriptive text into audible sounds.

Limitations / Not Good At

This model is specifically for sound effect generation and is not intended for speech synthesis or music creation.

Ideal Use Cases

  • Adding ambient sounds to videos or films (e.g., "a bustling city street", "a quiet forest at dawn").
  • Generating sound effects for video games (e.g., "footsteps on gravel", "a door creaking open").
  • Creating sound cues for presentations or multimedia projects (e.g., "a success chime", "a warning buzz").
  • Sound design for podcasts and audio dramas.

Input & Output Format

  • Input: Text prompt describing the desired sound effect, with optional parameters for duration, prompt influence, output format, and looping.
  • Output: Audio file (MP3 by default) containing the generated sound effect.

Performance Notes

The model offers flexibility in controlling the output duration and how closely it adheres to the prompt. Various audio codecs and sample rates are supported for output customization.

Inputs (1)

Text

String

The text describing the sound effect to generate

Multi InputMin: 0Max: 100
Parameters (5)

Text

String

The text describing the sound effect to generate

Default:

Loop

Boolean

Whether to create a sound effect that loops smoothly.

Default: false

Prompt Influence

Number

How closely to follow the prompt (0-1). Higher values mean less variation.

Default: 0.3

Output Format

String

Output format of the generated audio. Formatted as codec_sample_rate_bitrate.

Default: mp3_44100_128

Duration Seconds

Number

Duration in seconds (0.5-22). If -1, optimal duration will be determined from prompt.

Default: -1
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

📍 London

Building the future. Join us!

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Audio / Elevenlabs

Input

Text

Output

Audio

Keywords

Sound Effect Generation
Use in Workflow