Skills

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

HeartMuLa: Suno-like song generation from lyrics + tags.

Use when you need to generate UI designs, web/mobile mockups, presentations, dashboards, or documents from natural language. 31 composable skills across 129 design systems with image, video, and audio generation.

Audio spectrograms/features (mel, chroma, MFCC) via CLI.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.