About Eleven Sound Effects v3
Eleven Sound Effects v3 generates sound effects, ambiences, music cues, and vocal sounds from a text description, following several sound instructions in a single prompt.
Describe a layered scene, such as "rain on a tin roof, a dog barking in the distance, and a kettle starting to whistle", and the model renders each element in one clip of up to 30 seconds, or picks a length from the prompt. It produces clean, natural audio, with convincing music and vocals and tonal sounds like gongs, chimes, and whistles. Loop mode produces clips that repeat seamlessly for ambiences and game audio, and a prompt-influence control trades variety for closer adherence to the description. It suits foley for video, game assets, UI sounds, and adding audio to silent video generations.
| Metric | Value |
|---|---|
| Max Output | 30 seconds |
Ready to build with Eleven Sound Effects v3?
Try Eleven Sound Effects v3 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "elevenlabs-sound-effects-v3",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'Request parameters
Every field Eleven Sound Effects v3 accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/chat/completions| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Describe the sound, its source, and the space it is in. |
duration | number | No | 5 | Range: 0.5 – 30 |
loop | boolean | No | false | Make a clip that repeats seamlessly. |
prompt_influence | number | No | 0.3 | Higher values follow the prompt more closely with less variation between generations. Range: 0 – 1 |