Speech & TranscriptionDocumentedScanned

sound-fx

Generate short sound effects via ElevenLabs SFX (text-to-sound).

Share:

Installation

npx clawhub@latest install sound-fx

View the full skill documentation and source below.

Documentation

Sound FX (ElevenLabs)

Overview

Generate a sound effect from a text prompt using the ElevenLabs SFX API. Output is MP3 by default; convert to .ogg/opus for WhatsApp mobile playback.

Quick start

1) Set API key:
  • ELEVENLABS_API_KEY (preferred) or XI_API_KEY
  • Or set skills."sound-fx".env.ELEVENLABS_API_KEY in ~/.clawdbot/clawdbot.json
2) Generate SFX (MP3):
scripts/generate_sfx.sh --text "short audience applause" --out "/tmp/applause.mp3" --duration 1.2

3) Convert to WhatsApp-friendly .ogg/opus (if needed):

ffmpeg -y -i /tmp/applause.mp3 -c:a libopus -b:a 48k /tmp/applause.ogg

Script: scripts/generate_sfx.sh

Usage
scripts/generate_sfx.sh --text "canned laughter" --out "/tmp/laugh.mp3" --duration 1.5

Notes

  • Uses POST - Supports optional --duration (0.5–30s). When omitted, duration is auto. - Prints MEDIA: on success for auto-attach. ## Examples - Applause: "short audience applause" - Laughter: "canned audience laughter" - Whoosh: "fast whoosh" - Ambience: "soft rain ambience"`