Generate a sound effect
elevenlabs/sound_generationGenerate a sound effect from a written description.
- call
- $0.0192
- ElevenLabs
- 5 min
Overview
Turns a written description of a sound into generated audio: ambience, foley, impacts, stings, and any other non-speech effect. A prompt-influence control trades literal fidelity to the description against creative variation. Duration can be pinned within a half-second to thirty-second range, or left unset so the model picks a length that suits the sound described. The response is the encoded audio itself rather than a link.
The generated audio, returned inline with its media type and size in bytes.
Input
These go in the input object of the run request.
| Field | Type | Required | Description |
|---|---|---|---|
| text | string | Yes | The sound to generate, described in words. |
| duration_seconds | number | No | How long the sound should be; omit to let the model choose. |
| prompt_influence | number | No | How closely to follow the description, from loose to literal. |
Requests up to 1 MB.
Example
A call that works, with your own key.
curl https://gateway.agentsky.dev/v1/run \
-H "authorization: Bearer $AGENTSKY_API_KEY" \
-H "content-type: application/json" \
-d '{"provider":"elevenlabs","endpoint":"sound_generation","input":{"text":"A heavy wooden door creaking open in an empty hall","duration_seconds":4}}'Pricing
$0.0192 per call on the default plan. Every run carries its price in the response.