Generate a sound effect

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.

Requests up to 1 MB.

Example

Use your own API key and a saved idempotency key for each new job. Replace image or media placeholders with your own publicly reachable HTTPS URLs. Keep the same key and request body when recovering a timeout.

# Set once per job; reuse this key and the identical body after a timeout.
: "${AGENTSKY_IDEMPOTENCY_KEY:?Set a unique, saved key for this job}"
curl --fail-with-body https://gateway.agentsky.dev/v1/run \
  -H "authorization: Bearer $AGENTSKY_API_KEY" \
  -H "content-type: application/json" \
  -H "Idempotency-Key: $AGENTSKY_IDEMPOTENCY_KEY" \
  -d '{"provider":"elevenlabs","endpoint":"sound_generation","input":{"text":"A heavy wooden door creaking open in an empty hall","duration_seconds":4}}'
# If status is READY/RUNNING, poll GET /v1/runs/{runId} with the same API key.

$0.0192 per call using your plan when signed in. Read the final customer charge from price.amount.value after the run finishes. A RUNNING response is not the final bill.

Questions