Audio Conductor

This skill acts as an intelligent, unified dispatcher for all audio generation tasks. It analyzes a user's request and routes it to the most appropriate specialized model, whether it's for Music, Sound Effects (SFX), or Text-to-Speech (TTS).

When to Use

Use this skill as the primary entry point for any audio-related request. Instead of deciding which specific model or skill to call, simply describe the desired audio output.

• User says: "Create a background track for my video."
• User says: "I need a sound effect of a door creaking."
• User says: "Generate a voice-over for this script."

This skill is designed to be called by high-level agent platforms like OpenClaw. It relies on the tools provided by the elevenlabs-mcp-server skill, which must be loaded in the agent's environment.

Core Principles

• Unified Interface: Provides a single, consistent API for all audio generation, simplifying agent-level logic.
• Intelligent Routing: Automatically determines the audio_type (music, sfx, tts) from the user's prompt.
• Model Abstraction: Hides the complexity of individual model APIs (e.g., ElevenLabs Music vs. SFX vs. TTS), allowing for easier maintenance and upgrades.