Skip to article

Game sound effects

Generate and compare a batch of short sound effects.

Integration status: the web workflow is available. API/MCP submission for this business is not enabled yet; batch persistence setup is still pending. The contract below documents the planned integration.

What you can create

Generate short effects for attacks, interface feedback, movement and environmental events. Request variants across supported models to compare interpretations. Example: produce one three-second magical sword impact, then listen before downloading.

Prepare the sound

Describe one sound clearly in a 3–450-character prompt. Duration is an integer from 1 to 22 seconds. counts chooses how many variants to request from Sonilo v1.1, ElevenLabs V2 and Stable Audio 3 Small SFX. The total must be between 1 and 10. Omitting counts creates one ElevenLabs V2 result.

Generate effects in the workspace

  1. Open Game sound effect generator.
  2. Describe the sound, set duration and choose the number of model variants.
  3. Review the total credits and save destination, then generate.
  4. Listen to each successful item and compare its fit.
  5. Download successful files even if another variant failed.

Choices, limits and cost

Each variant costs ceil(durationSeconds / 5) credits. Three seconds costs 1 per variant; 22 seconds costs 5. Multiply by all selected variants. promptInfluence defaults to 0.3 and loop to false; those controls apply to ElevenLabs V2. Other models use their own prompt expansion and audio controls. Every variant has independent progress and failure/refund handling.

Parameters

These fields are generated from the same input Schema used by REST and MCP. Nested required fields apply when their parent object or selected variant is present. Business conditions described above are validated before submission.

FieldTypeRequiredDefault and limits
characterIdstringNominLength: 1; maxLength: 255
characterTargetobject / objectNoSee the workflow requirements above.
projectIdstringNominLength: 1; maxLength: 255
folderIdstring / nullNoSee the workflow requirements above.
promptstringYesminLength: 3; maxLength: 450
durationSecondsintegerYesminimum: 1; maximum: 22
promptInfluencenumberNoDefault: 0.3; minimum: 0; maximum: 1
loopbooleanNoDefault: false
countsobjectNoDefault: {"sonilo-v1.1":0,"elevenlabs-sound-effects-v2":1,"stable-audio-3-small-sfx":0}
counts.sonilo-v1.1integerYesminimum: 0; maximum: 10
counts.elevenlabs-sound-effects-v2integerYesminimum: 0; maximum: 10
counts.stable-audio-3-small-sfxintegerYesminimum: 0; maximum: 10

API example

This example costs 1 credits. A quote does not reserve balance or bypass subscription requirements. Set SPRITEFLOW_API_KEY in your shell. Replace the placeholder asset ID 00000000-0000-4000-8000-000000000001 with a ready asset you own when present. Use a new idempotency key for each intentional generation; keep it unchanged when retrying.

bash

# Use the same BASE_URL for credentials, uploads and generation.
BASE_URL="https://spriteflow.io"
IDEMPOTENCY_KEY="example-workflow-001"

cat > request.json <<'JSON'
{
  "operation": "generate_sound_effects",
  "input": {
    "prompt": "A magical sword rings against a stone shield",
    "durationSeconds": 3
  }
}
JSON

curl --fail-with-body "$BASE_URL/api/v1/estimates" \
  -H "Authorization: Bearer $SPRITEFLOW_API_KEY" \
  -H "Content-Type: application/json" --data-binary @request.json

curl --fail-with-body "$BASE_URL/api/v1/tasks" \
  -H "Authorization: Bearer $SPRITEFLOW_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" --data-binary @request.json

An accepted request returns HTTP 202, Location and Retry-After headers. Example response (IDs are illustrative):

json
{"taskId":"00000000-0000-4000-8000-000000000002","status":"accepted","statusUrl":"/api/v1/tasks/00000000-0000-4000-8000-000000000002","pollAfterSeconds":10,"replayed":false}

MCP example

Call estimate_cost with the same operation and input, then call generate_sound_effects. The following is a tools/call params object:

json
{
  "name": "generate_sound_effects",
  "arguments": {
    "input": {
      "prompt": "A magical sword rings against a stone shield",
      "durationSeconds": 3
    },
    "idempotencyKey": "example-workflow-001"
  }
}

The tool returns the same task receipt in structuredContent and a JSON text result. Pass taskId to get_task. Tool annotations describe behavior; permissions are still checked on the server.

Completion, download and reuse

Poll the returned statusUrl after pollAfterSeconds. Continue while terminal is false. Read items for per-task results, progress for batch counts and assets for ready files. A batch can be partially_completed: use its successful assets and review each failed item before deciding whether to create a separate retry.

For each returned asset ID, call get_download_url or GET /api/v1/assets/{assetId}/download. Download the temporary URL before it expires. Image assets can be passed into a compatible operation as inputAssetId or a style reference. Do not pass provider task IDs, download URLs or local filesystem paths as asset IDs.

Failures and recovery

  • INVALID_PARAMETERS: fix the field errors before submitting. Check the business conditions and defaults above.
  • INPUT_ASSET_UNAVAILABLE: confirm the upload, check ownership and ensure the asset is ready and not trashed.
  • INSUFFICIENT_CREDITS: add credits before a new request; a cost estimate does not reserve them.
  • A timeout or lost response: resend the identical request with the original idempotency key. Never invent a new key just because the response was lost.
  • A terminal generation failure: inspect the item error and refund information. Refund handling uses the existing generation workflow. Do not assume an in-progress or unknown submission is safe to repeat.

Uploads · Tasks · Credits · Idempotency · Save destinations · Download and export