What problem does it solve? Producing the audio layer of a video composition — voiceover, background music, sound effects, transcription, and captions — normally requires juggling multiple TTS providers, music generators, and caption tooling with inconsistent word-timing formats. 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: Synthesize voiceovers via HeyGen (with native word timestamps), ElevenLabs, or local Kokoro-82M, selected automatically by available credentials. - BGM and SFX: Retrieve background music and sound effects from the HeyGen audio library, or fall back to local Lyria/MusicGen generation and a bundled 21-file SFX library when offline. - Transcription and captions: Generate word-level timestamps with Whisper, then author styled captions including karaoke, per-word emphasis, and pre-built caption components. - Background removal: Create transparent WebM/ProRes cutouts of subjects for compositing text and graphics behind presenters. - Use Case: Given a storyboard of narration lines, run the audio engine once to produce voice WAVs with word timings, a mood-matched music bed, and synced sound effects, then feed the word data into the caption pipeline for an animated subtitle track. ## Quick Start Ask the assistant to generate a voiceover, background music, and captions for your HyperFrames composition using the hyperframes-media audio engine.
