ElevenLabs Sound Effects v2

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	elevenlabs/sound-effects-v2
Type	Audio generation (text-to-audio)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

ElevenLabs Sound Effects v2 text-to-audio: turn a description into 0.5–22 seconds of sound effects with seamless looping and prompt-influence control, delivered as MP3 for video, games, and app UI.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Video and transition effects

Generate impacts, whooshes, and metallic accents for titles, transitions, logo reveals, and trailer moments, with length matched to the cut.

promptduration_secondsprompt_influence

Ambience and loops

Create rain, wind, and machine-hum beds that can repeat, using loop to join the head and tail smoothly.

promptduration_secondsloop

Game and product feedback

Batch-produce pickup, level-up, hit, button, and notification cues, using short durations and high prompt_influence to hold the sound details.

promptduration_secondsprompt_influence

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "elevenlabs/sound-effects-v2",
  "input": {
    "prompt": "Spacious cinematic braam with a deep sub-bass impact, metallic shimmer and a short reverb tail, suitable for a high-impact movie trailer moment.",
    "duration_seconds": 2,
    "prompt_influence": 0.3,
    "loop": false
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "elevenlabs/sound-effects-v2",
  "input": {
    "prompt": "Spacious cinematic braam with a deep sub-bass impact, metallic shimmer and a short reverb tail, suitable for a high-impact movie trailer moment.",
    "duration_seconds": 2,
    "prompt_influence": 0.3,
    "loop": false
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "elevenlabs/sound-effects-v2",
  "input": {
    "prompt": "Spacious cinematic braam with a deep sub-bass impact, metallic shimmer and a short reverb tail, suitable for a high-impact movie trailer moment.",
    "duration_seconds": 2,
    "prompt_influence": 0.3,
    "loop": false
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value elevenlabs/sound-effects-v2.

example elevenlabs/sound-effects-v2

input object required

Business parameters. Put Sound Effects v2-specific configuration here.

prompt string required

Sound description, 1–450 characters. Name the sound first, then material, action, space, and mood; state directly when music or voices must be excluded.

duration_seconds number required

Effect length from 0.5 to 22 seconds, including fractional values such as 0.5, 2, or 8.5. Required: automatic duration is not offered; billing follows the requested seconds.

default 2

prompt_influence number optional

How strongly the description shapes the result, from 0 to 1. Higher values follow the description more literally; lower values vary more.

default 0.3

loop boolean optional

Set to true to generate an effect whose head and tail join smoothly, for ambience, game loops, and background beds. It does not change the length.

default false example true

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Two-second cinematic braam

Generate a 2-second trailer braam from one description, keeping the low-end drop, metallic shimmer, and short reverb tail.

Request body

{
  "model": "elevenlabs/sound-effects-v2",
  "input": {
    "prompt": "Spacious cinematic braam with a deep sub-bass impact, metallic shimmer and a short reverb tail, suitable for a high-impact movie trailer moment.",
    "duration_seconds": 2,
    "prompt_influence": 0.3,
    "loop": false
  }
}

Eight-second looping rain ambience

Generate 8 seconds of rainy-night forest ambience with seamless loop enabled, excluding birds to keep the bed even.

Request body

{
  "model": "elevenlabs/sound-effects-v2",
  "input": {
    "prompt": "Steady rainy-night forest ambience: fine rain on leaves, a distant soft thunder rumble, no birds, immersive and even.",
    "duration_seconds": 8,
    "prompt_influence": 0.3,
    "loop": true
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, find the type=audio item in output and download the generated MP3 from its url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

What can ElevenLabs Sound Effects v2 generate?

It turns one sound description into a standalone effect, such as a cinematic impact, rainy-night ambience, a game pickup chime, or a UI feedback sound. Each request returns one clip; it does not generate music or speech.

How do I control the duration?

Set duration_seconds explicitly from 0.5 to 22 seconds, including fractional values such as 0.5, 2, or 8.5. Automatic duration is not offered, and billing follows the requested seconds.

What does prompt_influence do?

It controls how strongly the description shapes the result, from 0 to 1 with a default of 0.3. Higher values follow the description more literally; lower values allow more variation when exploring one direction.

What is loop?

Turn on loop to generate an effect whose head and tail join smoothly, for ambience, game loops, and background beds. It does not change the length; duration_seconds still sets that.

Which output format do I get?

The current release returns MP3 at 44.1 kHz and 128 kbps. Each request produces one audio artifact that can be downloaded or stored directly.

How is it billed?

Per requested second of audio: a 2-second request bills as 2 seconds. Failed tasks are refunded; see the pricing page for the live rate. View pricing

How do I call it through the API?

Send an asynchronous task to POST /v1/tasks with model set to elevenlabs/sound-effects-v2 and prompt plus duration_seconds in input, adding prompt_influence and loop as needed. The call returns a taskId immediately; receive the result through callback.url or poll GET /v1/tasks/:id.

Can one request generate several effects?

One request produces one audio clip. Submit separate tasks for more effects; each is billed by its own requested duration.