dLazy AIdLazy AI
Model ReferenceAudio Models

elevenlabs-sfx

ElevenLabs text-to-sound model — generates 1–22s short sound effects from a description. Suitable for foley, ambience, alerts, and game SFX.

ElevenLabs text-to-sound model — generates 1–22s short sound effects from a description. Suitable for foley, ambience, alerts, and game SFX.

Overview

FieldValue
Model IDelevenlabs-sfx
CLIdlazy elevenlabs-sfx
MCPelevenlabs-sfx (Claude Code surfaces this as mcp__dlazy__elevenlabs-sfx)
Typeaudio
ExecutionAsync task; the CLI polls until completion (--no-wait returns generateId immediately)
BatchSupports --batch <n> parallel fan-out

Parameters

ArgTypeRequiredNotes
promptstringYesPrompt
durationstringNoDuration (s); default 5
prompt_influencestringNoPrompt Influence; default 0.3

--input @file.json or --input '{...}' can supply all args at once; flags take precedence over --input keys.

CLI Examples

dlazy elevenlabs-sfx --help
dlazy elevenlabs-sfx --prompt "Write your prompt here"
dlazy elevenlabs-sfx --prompt "Write your prompt here" --dry-run
dlazy elevenlabs-sfx --prompt "Write your prompt here" --no-wait
dlazy elevenlabs-sfx --prompt "Write your prompt here" --batch 4

MCP

MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__elevenlabs-sfx; generic clients (e.g. OpenClaw) call it as elevenlabs-sfx.

See MCP setup for how to add the server.

Output

{
  "outputs": [
    { "type": "audio", "id": "o_...", "url": "https://files.dlazy.com/result.mp3", "mimeType": "audio/mpeg" }
  ]
}

Media tools emit image / video / audio / file outputs. Use --output url to print only the URLs on stdout.

On this page