Setting the file. One moment.
Direction Catalog · Embedded Captions · heygen-com/hyperframes · Skills Docs
10 distinct aesthetic directions the skill can express. Each is a complete look: font, motion, color, placement, rhetorical defaults. The agent picks by content tone × shot type × platform , not preset name.
Current shipped templates (modes/cinematic/*) cover about 30% of this catalog. The rest are future ship-ready aesthetics.
Classification matrix — pick direction by intersection:
Back to the top of the page 14.42
Hershey Script1
Poetic lyrical-poem-on-wall (portrait) lyrical-poem-on-wall chapter-card
Keynote/tech — (9:16 not ideal) tech-keynote-confident tech-keynote-confident
Investigative — investigative-typewriter investigative-typewriter
Music video k-pop-lyric k-pop-lyric k-pop-lyric
Family : Söhne Mono OR GT Sectra for name cards; Inter for bodyWeights : 500 body, 700 name cardColor : bone #F5EFE6 on charcoal, OR charcoal #1A1A1A on bone. No accent.Motion : burn-in (no animation). Held 0.5s past last word.Placement : bottom-left block, 10% margin, locked position for whole interview.Rules : 2-line max. Speaker name card once at first utterance + after each cut. No emphasis styling — gravitas IS the style.Rhetorical : aggressive filler suppression. Every word is chosen.
Family : Distressed serif (Hoefler Text) + tight mono for detailWeights : 700 mostly; thin italic ONLY for whispersColor : off-white #E8E0D0 with deep red #8B0000 single-word accent for menaceMotion : typewriter with 10% chance of 1px jitter on entry; scratched etch for chapter beatsPlacement : off-axis — avoid dead-center, slightly high-left or low-rightRules : no emoji, no rounded corners, everything hand-feeling
Family : SF Pro Display OR Inter, nothing elseWeights : 800 headline keyword, 400 contextColor : pure white on any bg; mix-blend-mode: difference fallback for bright scenesMotion : swipe-reveal from bottom via clip-path (400ms); exit fades 400msPlacement : dead center, large. NOT lower-third.Rules : one caption on screen at a time. 2–5 words per caption. Long held silences between. Feels like slides.
Family : Serif with personality — EB Garamond / GT Sectra / Caslon ItalicWeights : 400–500 only. This direction rejects bold. Color : picks up wall via mix-blend-mode: overlay, opacity 0.85, no strokeMotion : etch in 600ms, hold 1.5–3s, etch outPlacement : always on a surface in the scene (back wall, foam, whiteboard). Uses matte pipeline.Rules : captions are fewer than spoken text — 40–60%. Intentional silences. No other tool does this; strong differentiation.
Family : Inter ExtraBold, uppercaseWeights : 900 alwaysColor : white body + ONE accent (#FFD600 or #00E676) + narrow 2px dark strokeMotion : word-pop with elastic, 60ms stagger; active word scales 1.15× on speech onsetPlacement : center-frame, ~35% from topRules : max 3 words per frame. Hard break at breath pauses. Accent color on ~15% of words. One full silence every 10s (what Hormozi imitators miss).
Family : Futura Bold (modern) / Archer (warm) / Bodoni (formal)Weights : 700 chapter title, 400 attributionColor : pastel hue sampled from sceneMotion : full-frame static card between interview segmentsPlacement : centered card for chapters; lower-left name card during speechRules : chapter cards get their own beat (0.8s silence before, 0.4s after). Feels authored.
Family : IBM Plex Mono OR JetBrains MonoWeights : 500Color : white with 3px shadow, no strokeMotion : typewriter char-by-char 25ms/char; cursor blink 600ms after last charPlacement : bottom band with 40% opacity gradient up — NOT a hard box Rules : one line only, two-line max. Every caption ends with 1-frame cursor-hold before next enters.
Family : oversized display serif (Playfair Display / GT Super) + tiny mono detail lineWeights : display 900, mono 400Color : deep saturated single hue per song/segmentMotion : cascade entries alternating sides; words cross subject with mix-blendPlacement : intentionally LARGE — sometimes bigger than the faceRules : emotional/musical moments only. Never informational content. Breaks rule #1 (subject wins) on purpose — that’s the whole point.
Family : Helvetica Now / Neue Haas GroteskWeights : 500 body, 700 nameColor : white on 40% black gradient pill (not hard box, not plain shadow — gradient is the signature)Motion : 200ms fade-up, 150ms fade-downPlacement : bottom-center, 10% margin, title-safe lockedRules : strict BBC — 160–180wpm, 32–34 chars/line, 2 lines max, 1.5s min gap. “Export to broadcast” mode. Boring on purpose. Never wrong.
Family : GT America / Aktiv GroteskWeights : dual-weight name card — role 400, name 700, same sizeColor : scene-sampled accent on name, white on roleMotion : name card swipes in from left 400ms on first appearance only; subsequent staticPlacement : lower-left card + active-word highlight inline in dialogue aboveRules : mode for podcast clips, founder interviews, keynote pulls. Sophisticated without being arty.
Current templates: memory-wall (roughly direction #4), champion (roughly a mix of #5 and #9), portrait-header (default vertical).
Priority ship order based on competitive gap:
documentary-dignified — no one else does this well; Errol Morris aesthetic is an unserved nichelyrical-poem-on-wall (as distinct template) — the one that most uses our matte-embed moathigh-energy-vlog — matches but out-designs Hormozi/Submagic presetstech-keynote-confident — big for product launch videosinvestigative-typewriter — niche but highly distinctive
Classify the clip: tone × shot × platform (see matrix above)
Look up direction in matrix
Read that direction’s spec in this file
Translate spec into plan.json parameters OR clone the canonical HTML from examples/
Tune layout per scene (agent judgment, see aesthetic-principles.md §1–18)
If no direction fits cleanly → Standard mode . Don’t fake-fit an ill-matched direction.
