ElevenLabs
ElevenLabs Sound Effects
elevenlabs/sound-effects-v3
ElevenLabs' text-to-sound-effects series lets you generate sound effects by describing actions, scenes, and atmosphere in natural language, with configurable duration, seamless looping, and prompt adherence—ideal for game sound effects, film previsualization Foley, and ambient beds
Try elevenlabs/sound-effects-v3
Input
Showcases
View all showcasesOutput
Pricing
elevenlabs/sound-effects-v3 per second
| Unit Price | $0.0029 |
|---|
Overview
An audio model that generates sound effects from text descriptions, supporting the specification of actions, environments, atmospheres, and performance styles via prompts. Inputs include a required sound description and duration, with optional seamless looping and prompt influence level. It is suitable for game development, film and video post-production, short video production, and interactive product teams that need to quickly obtain short sound effect assets ready to drop into a project.
Key Highlights
- Prompts up to 450 characters — describe an action, scene, and atmosphere in one sentence, with a limit of 450 characters, leaving enough room to cover finer sound details.
- Duration configurable from 0.5 to 30 seconds — specify the number of seconds per request as needed, covering common asset lengths from brief clicks to half-minute ambience.
- Seamless loop output supported — when seamless looping is enabled, the generated sound effects join seamlessly at start and end, suitable for background or mechanical sounds that need to play continuously.
- Adjustable prompt influence — use a value from 0 to 1 to control adherence; lower values yield more varied results, while higher values stay closer to the description.
Capabilities
Text description to sound effects: submit a sound description of action, scene, atmosphere, and performance style, and the model outputs the corresponding audio; the description is required, cannot contain only whitespace, and is limited to 450 characters.
Custom sound effect duration: each request must specify a duration from 0.5 to 30 seconds; automatic duration is not supported, and both short sound effects and longer ambience are handled within the same set of parameters.
Seamless loop option: when seamless looping is enabled, the generated sound effect is suitable for continuous playback; when disabled, output is a normal single sound effect.
Prompt adherence adjustment: use the prompt influence parameter from 0 to 1 to balance variability and adherence — 0 is more free, 1 follows the description more strictly, and the default is 0.3.
Use Cases
- Game teams creating interactive feedback sound effects — input descriptions of actions such as button clicks or skill triggers and set a short duration to obtain audio assets ready to drop into game events.
- Film and video post-production adding ambient atmosphere — generate ten-plus seconds of ambience from scene and atmosphere descriptions and place it on the editing timeline as a background bed or transitional sound effect.
- Short video creators adding sound accents — describe short sound effects such as transitions or notifications according to the visuals, keep them within one or two seconds, and use them on effect audio tracks in editing software.
- Interactive product design with looping background sound — enable seamless looping and specify a duration to generate continuously playable mechanical or ambient sounds for sound feedback in demos and prototypes.
Limitations and Selection Advice
Prompts are limited to 450 characters; shorten them if exceeded. Each request must specify a duration from 0.5 to 30 seconds; automatic duration is not supported. If the description is too short or the influence parameter leans toward variation, results may differ from expectations and may require multiple attempts to select from. The output is sound effect audio and is not suitable for tasks requiring full music composition or sung vocals.
Frequently asked questions
View all FAQs →-
What is the maximum length of sound effects this model can generate?
The maximum duration supported differs between the current version and the previous generation. elevenlabs/sound-effects-v3 allows 0.5 to 30 seconds per generation, while elevenlabs/sound-effects-v2 allows 0.5 to 22 seconds; both require duration_seconds to be passed explicitly and do not support automatic duration.
-
How can I make the generated result closer to my description?
Simply raise prompt_influence; it controls how closely the output follows the prompt. The value ranges from 0 to 1, with a default of 0.3; the closer to 1, the more strictly it generates according to the literal description, and the closer to 0, the looser and more varied it becomes, which suits scenarios that need unexpected creativity.
-
How can I write effective sound-effect prompts?
It is recommended to organize around four elements—action, environment, atmosphere, and performance—and write them in one coherent paragraph. For example, first describe what action produces the sound, then describe the scene where it occurs and whether the overall mood is tense or quiet, and finally add performance details such as timbre or rhythm; keep the whole paragraph within 450 characters. v3 follows prompts containing multiple instructions more reliably, so clearly separating the elements is more effective than piling up synonyms.
-
How do I generate a looping sound effect?
Set loop to true to generate a seamlessly loopable sound effect. The result has no perceptible start or end point, making it suitable for ambience, environmental textures, and long-running background beds; the default value is false, which generates a normal sound effect with a distinct start and end.
Create a generation task
https://api.hiapi.ai/v1/tasks Headers
AuthorizationstringRequiredAccount API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key
Content-TypestringOptionalThe request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.
Idempotency-KeystringOptionalIdempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.
On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.
Body
modelstringRequiredCurrent fixed value: elevenlabs/sound-effects-v3
routestringOptionalCurrent fixed value: default
inputobjectRequired
Business parameters for elevenlabs/sound-effects-v3 and route default — see the parameter table below.
loopbooleanOptionalDefault: falseControls whether to generate a seamlessly loopable sound effect. Boolean value, default false (no loop).
promptstringRequiredminLength 1maxLength 450pattern \SText describing the desired sound effect; must cover the action, scene, atmosphere, and performance style, with a maximum of 450 characters.
duration_secondsnumberRequiredDefault: 2min 0.5max 30Duration of the generated sound effect in seconds, ranging from 0.5 to 30, default 2; automatic duration is not supported.
prompt_influencenumberOptionalDefault: 0.3min 0max 1Controls how closely the generated result follows the prompt. A value of 0 is more random and varied, while 1 follows the description more strictly; default 0.3.
callbackobjectOptional
Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.
Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.
urlstringRequiredRequired when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.
whenstringOptionalDefault: "final"Only final is supported today — notified on both success and fail.
finalstoragestringOptionalDefault: "temp"Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.
temppersistentRequest examples
# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer $HIAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "elevenlabs/sound-effects-v3",
"input": {
"loop": false,
"prompt": "…",
"duration_seconds": 2,
"prompt_influence": 0.3
}
}' const res = await fetch("https://api.hiapi.ai/v1/tasks", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "elevenlabs/sound-effects-v3",
input: {
"loop": false,
"prompt": "…",
"duration_seconds": 2,
"prompt_influence": 0.3
}
}),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } } import os, requests
res = requests.post(
"https://api.hiapi.ai/v1/tasks",
headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
json={
"model": "elevenlabs/sound-effects-v3",
"input": {
"loop": False,
"prompt": "…",
"duration_seconds": 2,
"prompt_influence": 0.3
}
},
)
print(res.json()) # { code, message, data: { taskId } } 200 OK
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
}
} 400 Bad Request
{
"code": 400,
"message": "invalid request",
"data": null,
"error_code": "INVALID_REQUEST"
} Get task detail
https://api.hiapi.ai/v1/tasks/:id Response fields
taskIdstringRequiredTask ID, always prefixed with tk-hiapi-.
modelstringRequiredResolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.
routestringOptionalPresent only when the task was submitted with an explicit route parameter; echoes the submitted value.
statusstringRequiredTask status.
queued Queued, not started yet.
handling Being processed.
archiving Processing finished, artifacts being prepared.
success Terminal: completed, artifacts available (output returned).
fail Terminal: failed (error returned).
After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.
creatednumberRequiredTask creation time (Unix seconds).
completednumberRequiredUnix seconds when the task reached a terminal state; fixed to 0 while not terminal.
outputarrayOptional
Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).
Array [ object ]
Array items
urlstringRequiredArtifact URL, directly downloadable.
typestringRequiredCurrent possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.
expireAtnumberRequiredUnix seconds until which the artifact remains accessible; download or transfer before it expires.
errorobjectOptional
Present only when status == fail.
codestringRequiredBusiness error code.
messagestringRequiredError description.
Response examples
Success
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
"model": "happyhorse-1-0",
"status": "success",
"created": 1777282033,
"completed": 1777282099,
"output": [
{
"url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
"type": "video",
"expireAt": 1777886899
}
]
}
} Processing (non-terminal)
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "archiving",
"created": 1777282033,
"completed": 0
}
} Failed
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "fail",
"created": 1777282033,
"completed": 1777282099,
"error": {
"code": "TASK_FAILED",
"message": "task failed"
}
}
} Articles
View all articles →-
Guide
ElevenLabs Sound Effects v3 Prompt Guide: Organizing Sound Effect Descriptions with Material, Action, and Distance
-
Guide
ElevenLabs Sound Effects v3 API: 30-Second Sound Effects, Seamless Loops and Moving from v2
Pricing, parameters, example requests and prompting tips in one guide
6 min read -
Guide
ElevenLabs Sound Effects v3 Looping Sound Effects in Practice: From a Stable Bed to Seam Acceptance
Related Models
View all models →Same Type
-
Lyria 3.5 Google $0.090 /song -
MiniMax Music 1.5 MiniMax $0.070 /song -
MiniMax Music 3 MiniMax $0.0026 /second -
ElevenLabs ElevenLabs $0.125 /1,000 characters -
MiniMax Music 2.6 MiniMax $0.210 /song -
Qwen Audio 3.0 TTS Alibaba $0.030 /1,000 characters -
Mirelo SFX 2.0 Mirelo AI $0.021 /second -
Lyria 3 Pro Google $0.140 /song -
Mureka 9.5 Mureka $0.322 per request


