What problem does it solve? Producing the audio layer of a video — voiceover, background music, sound effects, transcription, and captions — normally requires juggling multiple TTS providers, music generators, and transcription tools with inconsistent outputs. This Skill provides one shared audio engine that produces all of these assets from a single request file, with automatic provider fallback when credentials are missing. ## Core Features & Use Cases - Multi-provider TTS: Synthesizes voiceover via HeyGen (with native word timestamps), ElevenLabs, or local Kokoro-82M, selected automatically by available credentials. - BGM and SFX: Retrieves music and sound effects from the HeyGen audio library when credentialed, or falls back to local Lyria/MusicGen generation and a bundled 21-file SFX library. - Transcription and captions: Runs Whisper transcription with language-safe model rules and authors styled, word-timed captions including karaoke and per-word emphasis. - Use Case: Given a storyboard with narration lines and a music mood, write an audio_request.json and run scripts/audio.mjs to produce voice WAVs with word timestamps, a BGM track, and timed SFX cues in one audio_meta.json. ## Quick Start Ask the AI to generate voiceover, background music, and sound effects for your HyperFrames composition by writing an audio_request.json and running the audio engine script.
