Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.
TypeScript agentic-aiaiai-agentsai-videocompilerdslffmpeggenerative-aillmmarkup-languagemonorepoplugin-systemprogramming-languagetext-to-videotypescriptvideovideo-automationvideo-clonevideo-editingvideo-generation
fix(hypit): a voiceover-led stretch is a speaking take the B-roll covers
rponecf48430ad603
diff --git a/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md b/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.mdindex a9fa0af7..0ef225b0 100644--- a/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md+++ b/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md@@ -148,6 +148,15 @@ Decide, for each thing you place, which of three kinds it is:- **Genuinely coming and going** — an insert that appears for one phrase and leaves. A plain Selectionis exactly right, and the gap is the point.+**Where the base is meant to stay hidden, the covering Selections tile the Segment.** A voiceover-led+stretch still has a speaking take under it — that is where the speech comes from — and the reference+never shows it, so every word of that Segment is inside one covering Selection or the next, with the+markers above joining them. A gap does not read as black there; it reads as a presenter appearing for+half a second in a program that has none.++This is settled in the Script rather than by looking: mark the covering ranges, read them back, and+confirm the Segment's first word opens one and its last word closes one with nothing between.+The same question decides a component you write yourself. A Program scheduled from occurrences drawsonly inside them unless you give it a span of its own, so a page built from one occurrence per rowvanishes on the words between two rows. `@hypit/local-notebook-ranking` does that deliberately anddiff --git a/.agents/skills/hypit/references/playbooks/formats/mass-tarot.md b/.agents/skills/hypit/references/playbooks/formats/mass-tarot.mdindex 35e55f69..4e60a62a 100644--- a/.agents/skills/hypit/references/playbooks/formats/mass-tarot.md+++ b/.agents/skills/hypit/references/playbooks/formats/mass-tarot.md@@ -7,13 +7,20 @@ ordered reveals and interpretations.- Write one authoritative Script with Selections/Moments for the question, choice window, each reveal,and the close.-- Use one continuous narration take whenever the reading is voiceover-led. Generate it with- `mimo:Preset`, `mimo:VoiceDesign`, or `mimo:VoiceClone`, then use an audio-only Speech Take:+- Take the voice sample once with `mimo:Preset` or `mimo:VoiceDesign`. The reading is spoken by a+ take, and that take is the base under the whole Segment — the cards and the spread cover it, and+ the speech and the picture stay one generation. `../craft/generated-dependencies.md` says why.+ Cut the Segment to fit one generation.```svml<program:Clock id="clock" frame-rate="30"/>-<pipeline:Normalize id="narration-media" source={narration.audio}- video="none" audio="default" span-authority="audio" clock={clock}/>+<seedance:ReferenceVideo id="narration-take" model="mini" prompt={reading-prompt}+ duration={reading-duration.duration} generate-audio="true">+ <seedance:Reference image={reader.image}/>+ <seedance:Reference audio={reading-voice.audio}/>+</seedance:ReferenceVideo>+<pipeline:Normalize id="narration-media" source={narration-take.video}+ video="primary-moving" audio="default" span-authority="video" clock={clock}/><whisperx:SemanticTake id="narration-semantic" narrative={story}segment={story.segment.reading} media={narration-media.media}/><speech:Track id="speech"@@ -66,3 +73,8 @@ Read `../craft/b-roll.md`, `../craft/captions.md`, `../craft/overlays.md`, andThat list is complete: `../index.md` does not repeat it, and the craft its required loadorder marks always-read is required regardless of format.++- The base is meant to stay hidden, so the covering Selections tile the Segment: its first word+ opens one, its last word closes one, and nothing falls between. Join them with the Script's+ absorbing markers — `../craft/generated-dependencies.md` holds the table. A gap shows the+ speaker for half a second in a program that has none.diff --git a/.agents/skills/hypit/references/playbooks/formats/mixcut.md b/.agents/skills/hypit/references/playbooks/formats/mixcut.mdindex b16bd5ab..7f2e977d 100644--- a/.agents/skills/hypit/references/playbooks/formats/mixcut.md+++ b/.agents/skills/hypit/references/playbooks/formats/mixcut.md@@ -31,11 +31,15 @@ A crop of the same image is not a new beat.## Author timing, text, and sound-- Lock the delivery SemanticTrack before laying out Items. For a voice-led cut, an audio-only Take- supplies program time and semantic anchors. For a music-only cut, keep the `whisperx:SemanticTake`+- Lock the delivery SemanticTrack before laying out Items. For a voice-led cut, the speaking take+ supplies program time and semantic anchors, and sits under the cut as the base the Items cover. For a music-only cut, keep the `whisperx:SemanticTake`and `speech:Track` declarations and satisfy `<track>.semantic` in `.svrun` with `build-record` and`satisfy`, then author explicit `start`/`end` windows against it — `../index.md` says why thedeclarations stay. Do not treat music as speech evidence.+- The base is meant to stay hidden, so the covering Selections tile the Segment: its first word+ opens one, its last word closes one, and nothing falls between. Join them with the Script's+ absorbing markers — `../craft/generated-dependencies.md` holds the table. A gap shows the+ speaker for half a second in a program that has none.- Omit Caption components when there is no spoken Script. Use `typo:Track` for title, benefit, and CTAcopy.- Keep no more than one or two text groups on screen at once. Align text handoffs to the final trimmeddiff --git a/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.md b/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.mdindex 1e14c2d3..5b826049 100644--- a/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.md+++ b/.agents/skills/hypit/references/playbooks/formats/voiceover-desk-demo.md@@ -6,14 +6,21 @@ screen, product, hand, or proof changes.## Author the SVML program1. Write one narration Script Segment with Selections/Moments for every visual proof beat.-2. Generate one continuous narration Blob with `mimo:Preset`, `mimo:VoiceDesign`, or- `mimo:VoiceClone`. Do not split TTS to match picture cuts.-3. Put the audio directly into an audio-only Speech Take:+2. Take the voice sample once, with `mimo:Preset` or `mimo:VoiceDesign`.+3. The narration is spoken by a take, and that take is the base. It is under the whole Segment and+ the B-roll covers it; the viewer sees the desk only where nothing is over it, and the speech and+ the picture are one generation either way — `../craft/generated-dependencies.md` says why that+ matters. Cut the Segment to fit one generation.```svml<program:Clock id="clock" frame-rate="30"/>-<pipeline:Normalize id="narration-media" source={narration.audio}- video="none" audio="default" span-authority="audio" clock={clock}/>+<seedance:ReferenceVideo id="narration-take" model="mini" prompt={narration-prompt}+ duration={narration-duration.duration} generate-audio="true">+ <seedance:Reference image={desk.image}/>+ <seedance:Reference audio={narration-voice.audio}/>+</seedance:ReferenceVideo>+<pipeline:Normalize id="narration-media" source={narration-take.video}+ video="primary-moving" audio="default" span-authority="video" clock={clock}/><whisperx:SemanticTake id="narration-semantic" narrative={story}segment={story.segment.narration} media={narration-media.media}/><speech:Track id="speech"@@ -26,7 +33,12 @@ screen, product, hand, or proof changes.`{speech.audio}` directly to `film:Film`.5. Build each visual beat from supplied media or the vendored `broll-v1` Kit. Generated desk/screenshots use `seedance:FrameVideo` or `seedance:ReferenceVideo` with `generate-audio="false"`.-6. Place visuals by the measured Script Selections/Moments. One sentence may span several visual+6. Place visuals by the measured Script Selections/Moments.+ The base is meant to stay hidden, so the covering Selections tile the Segment: its first word+ opens one, its last word closes one, and nothing falls between. Join them with the Script's+ absorbing markers — `../craft/generated-dependencies.md` holds the table. A gap shows the+ speaker for half a second in a program that has none.+ One sentence may span several visualcuts, and one visual may cover only part of a sentence.7. Add editorial explanation with `typo:Track`; add the complete Caption chain only when narrationcaptions are wanted. Normalize only additional BGM/SFX before placing them on `audio:Track`.