# ElevenLabs Sound Effects V2

> Generate sound effects, Foley, and ambience from a text prompt, returning a hosted MP3.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/elevenlabs/sound-effects`
- **Model ID**: `elevenlabs/sound-effects`
- **Category**: sound
- **Kind**: inference
- **Tags**: elevenlabs, sound-effects, text-to-audio, sfx, foley, audio, sound

## Pricing

- **Price**: $0.002 per output second

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/elevenlabs/sound-effects` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/elevenlabs/sound-effects/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/elevenlabs/sound-effects/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/elevenlabs/sound-effects/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`loop`** (`boolean`, _optional_):
  Generate a sound effect that loops smoothly, for seamless ambience and beds.
  - Default: `false`

- **`text`** (`string`, _required_):
  The text describing the sound effect to generate.

- **`output_format`** (`OutputFormatEnum`, _optional_):
  Output audio format, named as codec_samplerate_bitrate.
  - Default: `"mp3_44100_128"`
  - Options: `"mp3_22050_32"`, `"mp3_44100_32"`, `"mp3_44100_64"`, `"mp3_44100_96"`, `"mp3_44100_128"`, `"mp3_44100_192"`, `"pcm_8000"`, `"pcm_16000"`, `"pcm_22050"`, `"pcm_24000"`, `"pcm_44100"`, `"pcm_48000"`, `"ulaw_8000"`, `"alaw_8000"`, `"opus_48000_32"`, `"opus_48000_64"`, `"opus_48000_96"`, `"opus_48000_128"`, `"opus_48000_192"`

- **`duration_seconds`** (`number | null`, _optional_):
  Length of the generated effect in seconds (0.5–22). Leave unset to let the model choose the optimal duration from the prompt.

- **`prompt_influence`** (`number`, _optional_):
  How closely the output follows the prompt (0–1). Higher is more literal and on-prompt; lower allows more variation.
  - Default: `0.3`
  - Range: `0` to `1`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "loop": false,
  "text": "Bright retro 8-bit arcade power-up chime, short and bouncy",
  "output_format": "mp3_44100_128",
  "duration_seconds": 3,
  "prompt_influence": 0.3
}
```

**Output**

```json
"https://media.modelrunner.ai/x8QOM4FZ7bkGrthid7vvX.mp3"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/elevenlabs/sound-effects \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "loop": false,
  "text": "Bright retro 8-bit arcade power-up chime, short and bouncy",
  "output_format": "mp3_44100_128",
  "duration_seconds": 3,
  "prompt_influence": 0.3
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("elevenlabs/sound-effects", {
  input: {
  "loop": false,
  "text": "Bright retro 8-bit arcade power-up chime, short and bouncy",
  "output_format": "mp3_44100_128",
  "duration_seconds": 3,
  "prompt_influence": 0.3
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "elevenlabs/sound-effects",
        arguments={
  "loop": false,
  "text": "Bright retro 8-bit arcade power-up chime, short and bouncy",
  "output_format": "mp3_44100_128",
  "duration_seconds": 3,
  "prompt_influence": 0.3
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/elevenlabs/sound-effects)
- [OpenAPI Schema](https://modelrunner.ai/models/elevenlabs/sound-effects/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/elevenlabs/sound-effects/llms.txt)