Reduces prompt approvals from ~30 per batch to 2 (one manifest write,
one batch run). audio-generate --post chains trim+normalize+convert
after generation. audio-batch processes a JSON manifest of multiple
assets sequentially, supporting both SAO generation and harmonic
synthesis methods. Includes --dry-run, --only, and --skip-existing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
audio-generate: Gradio API wrapper with timeout handling (600s default),
sequential-only generation, SSE stream polling. audio-health: API
health check. audio-post: ffmpeg wrapper for convert/normalize/trim/
pipeline operations. All follow existing connector pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
jpmschweitzerandClaude Opus 4.6