elevenlabs/sound-effects-v2

Name: Sound Effects V2
Author: ElevenLabs

Sound Effects V2 by ElevenLabs - generate music, sound effects, and audio from text descriptions with AI. Create original compositions, ambient sounds, and audio content for any creative project.

Input

Text(string)

The text describing the sound effect to generate

Prompt Influence(number)

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

Duration (seconds)(number)

0.522

Duration in seconds (0.5-22). If not set, optimal duration will be determined from prompt. Range: 0.5 to 22.

Loop(boolean)

Whether to create a sound effect that loops smoothly.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDelevenlabs/sound-effects-v2

Input Schema

4 parameters · 0 required · 4 optional

Parameter	Type	Required	Description
`loop`	boolean	Optional	Whether to create a sound effect that loops smoothly. · Default: false
`text`	string	Optional	The text describing the sound effect to generate
`duration_seconds`	number	Optional	Duration in seconds (0.5-22). If not set, optimal duration will be determined from prompt. · Min: 0.5 · Max: 22 · Default: 5
`prompt_influence`	number	Optional	How closely to follow the prompt (0-1). Higher values mean less variation. · Min: 0 · Max: 1 · Default: 0.3

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "elevenlabs/sound-effects-v2",
  "loop": false,
  "text": "Spacious braam suitable for high-impact movie trailer moments",
  "duration_seconds": 5,
  "prompt_influence": 0.3,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Sound Effects V2

API README

Sound Effects V2

Sound Effects V2 converts a natural-language sound description into a finished audio effect. It can create isolated impacts, mechanical noises, environmental ambience, interface sounds, transitions, and other non-speech assets for video, games, podcasts, and interactive experiences.

Describe the source, material, environment, distance, intensity, and progression of the sound rather than naming only a category. The route can choose a duration automatically or use an explicit length, control how closely the result follows the prompt, and request a smoothly repeating loop.

Highlights

Text-to-sound design. Generates original sound effects directly from a written acoustic brief.
Loop-ready output. Can blend the ending into the beginning for ambience, game states, and repeating backgrounds.
Adjustable prompt adherence. Balances close interpretation of the brief against greater variation through prompt influence.
Directed timing. Supports compact effects and longer evolving soundscapes with explicit duration control.

Pricing

Configuration	Billing unit	Price
Generated duration	Per second	$0.002

When to Use

✅ Good fit	❌ Consider alternatives
The project needs creating a purpose-built sound effect	The goal is a different media task or endpoint
The available inputs match the required local schema	Required source media or permissions are unavailable
The brief can specify subject, composition, style, and delivery	The result must be deterministic at pixel or sample level
The supported formats and controls match final placement	Delivery requires unsupported dimensions, codecs, or duration
An asynchronous generated result fits the workflow	A live, frame-synchronous, or real-time response is mandatory

Prompt Guide

Write the request as a production brief: identify the main subject or source material, state the intended transformation, describe composition or timing, and finish with style, atmosphere, and delivery constraints. Keep preservation requirements separate from requested changes, and use only fields exposed by this route.

{
  "loop": false,
  "text": "A warm, expressive narration with natural pacing.",
  "duration_seconds": 5
}

Technical Specs

Spec	Value
Model ID	`elevenlabs/sound-effects-v2`
Input fields	`loop` (boolean)<br>`text` (string)<br>`duration_seconds` (number; 0.5–22)<br>`prompt_influence` (number; 0–1)
Required input	None marked required
Output fields	`url`, `content_type`
Execution	Asynchronous job

Related Models

elevenlabs/dubbing