What problem does it solve?
This Skill helps AI agents turn dialogue, music, ambience, and sound effects into clear, balanced, technically compliant audio deliverables without relying on loudness normalization alone.
Core Features & Use Cases
- Mixing and Mastering Direction: Plan source repair, dialogue intelligibility, music balance, SFX control, EQ, compression, reverb, limiting, and loudness decisions.
- Delivery and Accessibility Guidance: Select client, broadcaster, or platform targets; prepare stems and M&E versions; protect speech clarity; and apply stereo, mono, surround, and accessibility checks.
- Deterministic QA: Measure integrated loudness, true peak, loudness range, and target compliance with the bundled FFmpeg-based measurement tool, then validate encoded outputs and playback translation.
- Use Case: Create and QA a 60-second social ad with AI narration, generated music, UI clicks, and a logo sting, including a labeled loudness heuristic, intelligibility checks, stems, and final delivery notes.
Quick Start
Use the audio-mixing-mastering skill to mix and QA the attached video, prioritizing dialogue intelligibility, documenting the applicable delivery target, measuring the final audio, and preparing any required stems.