AI Sound Effect Generator - Type a Prompt, Get a Sound

You need a short sound effect for a video, game or podcast. Describe it in plain words and set a length from 0.5 to 30 seconds. No speech, music, transcription or stock-library search. Pay per use: $0.12 per minute, prorated per second, capped at $0.06, from the shared prepaid balance.

Up to 0.072 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

ElevenLabs

AI Sound Effect Generator - Type a Prompt, Get a Sound

You receive

You get one generated sound effect from the description you enter. No speech, music, transcript, voice conversion, or stock-library search. Pay per use, no subscription: $0.12 per minute of requested length, prorated per second, capped at $0.06 on a 30-second clip.

Start with your task

Use the AI sound effect generator to make [a 3-second sound of a door creaking open]. Describe the sound in everyday words and choose a length from 0.5 to 30 seconds. You can ask for it to repeat smoothly; it creates one sound effect, not music or speech.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
body`body`	`object`	Required	Generate a sound effect from a text description Required fields `text, duration_seconds`
loop`body.loop`	`boolean`	Optional	Generate a seamlessly looping effect.
text`body.text`	`string`	Required	Description of the sound effect (e.g. 'Glass shattering on concrete', '90s hip-hop drum loop, 90 BPM'). Sequences and audio terminology (whoosh, braam, drone) work well. Minimum length `1` Maximum length `450` Examples `Thunder rumbling in the distance`
model_id`body.model_id`	`string`	Optional	Sound-effects model. Default `eleven_text_to_sound_v2` Options `eleven_text_to_sound_v2`
duration_seconds`body.duration_seconds`	`number`	Required	Length of the generated effect in seconds (0.5–30). REQUIRED — it is the exact billing basis ($0.12 per minute, prorated per second). Minimum `0.5` Maximum `30`
prompt_influence`body.prompt_influence`	`number`	Optional	0–1 (default 0.3): higher = follows the prompt more literally; lower = more creative variation. Minimum `0` Maximum `1`

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "text",
        "duration_seconds"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "loop": {
          "type": "boolean",
          "description": "Generate a seamlessly looping effect."
        },
        "text": {
          "type": "string",
          "examples": [
            "Thunder rumbling in the distance"
          ],
          "maxLength": 450,
          "minLength": 1,
          "description": "Description of the sound effect (e.g. 'Glass shattering on concrete', '90s hip-hop drum loop, 90 BPM'). Sequences and audio terminology (whoosh, braam, drone) work well."
        },
        "model_id": {
          "enum": [
            "eleven_text_to_sound_v2"
          ],
          "type": "string",
          "default": "eleven_text_to_sound_v2",
          "description": "Sound-effects model."
        },
        "duration_seconds": {
          "type": "number",
          "maximum": 30,
          "minimum": 0.5,
          "description": "Length of the generated effect in seconds (0.5–30). REQUIRED — it is the exact billing basis ($0.12 per minute, prorated per second)."
        },
        "prompt_influence": {
          "type": "number",
          "maximum": 1,
          "minimum": 0,
          "description": "0–1 (default 0.3): higher = follows the prompt more literally; lower = more creative variation."
        }
      },
      "description": "Generate a sound effect from a text description",
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

What you enter

text: a description of the sound effect, for example "glass shattering on concrete" or "90s hip-hop drum loop, 90 BPM". Up to 450 characters.
duration_seconds: the length of the effect, from 0.5 to 30 seconds. This is required and it is the exact billing basis.
Optional loop to generate a seamlessly looping effect.
Optional prompt_influence from 0 to 1 (default 0.3): higher follows the prompt more literally, lower gives more creative variation.
The model is fixed to eleven_text_to_sound_v2.

What you get back

One generated sound effect from the description you enter. Output fields are not published, so read the returned audio result.

Range and limits

Length is 0.5 to 30 seconds; the description is at most 450 characters.
prompt_influence runs from 0 to 1, default 0.3.
One sound effect per run.

What this page will not do

It does not generate speech or voice-over.
It does not generate music, transcribe audio, or convert a voice.
It does not search a stock sound library.

Pay per use

Billing is $0.12 per minute of requested length, prorated per second, so a 30-second clip caps at $0.06 - the verified maximum per run. Charges come from one shared prepaid Toolmu balance, with no subscription.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

It is $0.12 per minute of requested length, prorated per second, and the run is capped at $0.06 on a 30-second clip - the verified maximum per run. Charges come from the shared prepaid balance, with no subscription.

AI Sound Effect Generator - Type a Prompt, Get a Sound

AI Sound Effect Generator - Type a Prompt, Get a Sound

You receive

Start with your task

Inputs & outputs

Input schema

Result schema

What you enter

What you get back

Range and limits

What this page will not do

Pay per use

Make a door sound

Create a soft notification

Make a repeating rain sound

Questions about this tool.

You receive

Start with your task

Inputs & outputs

Input schema

Result schema

What you enter

What you get back

Range and limits

What this page will not do

Pay per use

Make a door sound

Create a soft notification

Make a repeating rain sound

Questions about this tool.

How much does an AI sound effect cost?

How long can the generated sound be?

Can it generate music or speech?

What does prompt_influence change?

Can I make a looping sound?