audio-conductor
от wells1137
Web & Frontend DevelopmentКратко
Intelligently dispatches requests to the appropriate audio generation model (Music, Sound Effects, or TTS)
Описание
Что делает этот навык
Routes audio generation requests to the appropriate specialized model based on prompt analysis. Accepts a single unified request and dispatches to music, sound effects, or text-to-speech generation internally. Depends on the elevenlabs-mcp-server skill being loaded in the agent environment.
Eliminates the need to manually route requests to separate audio models by centralizing classification and delegation behind a single call.
Когда его использовать
- Generating background music for a video without picking a model
- Creating a door creak or ambient noise sound effect
- Producing a voice-over from a written script
- Building audio pipelines without hardcoding model selection logic
- Letting an agent handle mixed audio tasks through one interface
Пример сценария
User asks: Generate a tense cinematic swell for my trailer intro
- 1
Receives the prompt and optional params like duration_ms or instrumental
- 2
Analyzes the prompt for keywords indicating music, sfx, or tts category
- 3
Classifies the request as music based on mood and instrument references
- 4
Delegates to the music-generator sub-skill with a Composition Plan
- 5
Formats the returned audio file into a standard AudioOutput object
AudioOutput with audio_url, duration_ms, audio_type: music, and model_used metadata
Требования
- ElevenLabs API key (required by elevenlabs-mcp-server)
Установка
clawhub install wells1137/audio-conductorВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.