paper-aigc-content-factory

Use when aligning voiceover audio and segment text into subtitle files with readability checks.

Use when validating an episode topic and coordinating deterministic local content-factory workflow setup.

Use when creating, updating, or reviewing global DESIGN.md, global FRAME.md, or an episode-level video_script/FRAME.md for AI paper explainer videos.

Use when composing storyboard, assets, audio, and captions into HyperFrames draft outputs.

Use when shaping hooks, cover headlines, storyboard beats, or visual concepts for paper explainer content that needs a stronger advertising idea without losing factual accuracy.

Use when evaluating episode artifacts and reporting pass, partial, or failed production readiness.

Use when converting verified sources and paper notes into grounded claims and a timeline.

Use when drafting platform-aware hooks, voiceover, segments, storyboard, and blog copy from grounded claims.

Use when creating, editing, resizing, reviewing, or exporting short-video cover images for Douyin, Xiaohongshu, Bilibili, YouTube Shorts, or other vertical social platforms.

Use when planning sound effects, audio cues, sonic logos, notification-like prompts, background music, or mix boundaries for AI paper explainer videos before TTS merge, captions, HyperFrames render, or platform review.

Use when reviewing AI paper explainer scripts, voiceover drafts, storyboard narration, or blog-to-video scripts before audio or animation generation.

Use when generating, reviewing, or approving cloned or personal-voice TTS for paper explainer episodes before full audio, captions, or video render.

Use when assigning visual engines and preparing an assets manifest from storyboard scenes and hook variants.

Use when turning segment text and an authorized voice manifest into recording-needed status or audio artifacts.

Use when converting QA, hook, and human-review feedback into auditable improvement candidates.

Use when adjusting TTS delivery, preserving original AI voice character, controlling low-intensity prosody, pacing, emphasis, or optional IndexTTS2/CosyVoice emotion prompts for reusable paper explainer voiceovers.

Use when preparing or validating local cover, video, caption, and metadata variants for multiple publishing platforms without auto-publishing.

Use when applying a Chinese-native readability pass to approved AI paper scripts before spoken_text is locked for TTS.

Use when generating or scoring platform-aware opening hooks for AI paper short videos before storyboard or FRAME lock.

Use when turning an episode topic or local research report into source records and paper notes inputs.