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: bind the street interview's footage, and drop the ranking preview
rpone3deb24105dc1
diff --git a/examples/regen-ranking-preview/build.svrun b/examples/regen-ranking-preview/build.svrundeleted file mode 100644index 7b8ef5bb..00000000--- a/examples/regen-ranking-preview/build.svrun+++ /dev/null@@ -1,16 +0,0 @@-<?svml using="@narratage/run-markup@1"?>--<svrun version="1">- <author source="./main.svml"/>- <target output="final.video"/>-- <!-- The three takes the documentation site ships for this piece, one per- Segment. -->- <file id="take-1" from="../../docs/public/regen-ranking/avatar-1.mp4" media-type="video/mp4"/>- <file id="take-2" from="../../docs/public/regen-ranking/avatar-2.mp4" media-type="video/mp4"/>- <file id="take-3" from="../../docs/public/regen-ranking/avatar-3.mp4" media-type="video/mp4"/>-- <satisfy output="take-intro.video" candidate="take-1"/>- <satisfy output="take-middle.video" candidate="take-2"/>- <satisfy output="take-payoff.video" candidate="take-3"/>-</svrun>diff --git a/examples/regen-ranking-preview/main.svml b/examples/regen-ranking-preview/main.svmldeleted file mode 100644index ee32a676..00000000--- a/examples/regen-ranking-preview/main.svml+++ /dev/null@@ -1,153 +0,0 @@-<?svml using="@narratage/markup@1"?>--<svml>- <import from="@narratage/script@1"/>- <import as="wording" from="@narratage/text@1"/>- <import as="seedance" from="@narratage/seedance@1"/>- <import as="media" from="@narratage/media@1"/>- <import as="speech" from="@narratage/speech-spine@1"/>- <import as="whisperx" from="@narratage/whisperx@1"/>- <import as="media-track" from="@narratage/media-track@1"/>- <import as="ranking" from="@narratage/ranking@1"/>- <import as="caption" from="@narratage/caption@1"/>- <import as="caption-fine" from="@narratage/caption-fine@1"/>- <import as="caption-ai" from="@narratage/caption-gemini@1"/>- <import as="fonts" from="@narratage/fonts-open@1"/>- <import as="text" from="@narratage/typography-track@1"/>- <import as="space" from="@narratage/spatial@1"/>- <import as="film" from="@narratage/film@1"/>- <import as="render" from="@narratage/render-hyperframes@1"/>- <import as="studio" source="./studio.svs"/>-- <!-- The spoken words of the ranking demo. Each app is a Selection, so the- board row it fills and the moment it settles are both derived from the- Script rather than restated as timecodes. `@place!` fires once per app. -->- <script id="story">- <intro>- <NARRATOR>@board @photoshop Photoshop. @place!- <SPEAKER>Powerful, but only if you know how to use it. Otherwise, your new profile- picture becomes a three-hour design project@/photoshop.- <NARRATOR>@facetune Facetune. @place!- <SPEAKER>Fast and great for touch-ups. But it still leaves you with the same awkward- pose and the same dorm-room background@/facetune.- </intro>- <middle>- <NARRATOR>@remini Remini. @place!- <SPEAKER>Great for blurry photos. It restores detail, but it can't fix the pose,- outfit, or background. You get the same bad photo in HD@/remini.- <NARRATOR>@chatgpt ChatGPT. @place!- <SPEAKER>More flexible. It can create a new shot, but getting your face and the- details right becomes a prompt-writing group project@/chatgpt.- </middle>- <payoff>- <NARRATOR>@regen ReGen. @place!- <SPEAKER>Pick a photo you love, and the app @handsome-1 rebuilds it around you with- a@/handsome-1~ @handsome-2 better pose, outfit, and setting.@/handsome-2 From one- selfie, you can make @dating-photo a dating photo,@/dating-photo~- @linkedin-headshot LinkedIn headshot,@/linkedin-headshot~- @instagram-post or Instagram post,@/instagram-post @done! so you get what you- wanted instead of fixing a bad shot@/regen.@/board- </payoff>- </script>-- <space:Canvas id="vertical" width="1080" height="1920"/>- <space:Frame id="speech-frame" within={vertical}- left="0%" top="0%" right="100%" bottom="100%"/>- <!-- The board sits on the left third, as it does in the demo. -->- <space:Frame id="board-frame" within={vertical}- left="0%" top="16.98%" right="30.46%" bottom="58.65%"/>- <space:Frame id="title-frame" within={vertical}- left="0%" top="9.9%" right="100%" bottom="17.7%"/>- <space:Frame id="broll-frame" within={vertical}- left="0%" top="0%" right="100%" bottom="100%"/>-- <wording:Value id="direction">Vertical talking head, casual room, direct address to camera.</wording:Value>- <seedance:TextVideo id="take-intro" model="mini" prompt={direction} duration="12" generate-audio="true"/>- <seedance:TextVideo id="take-middle" model="mini" prompt={direction} duration="12" generate-audio="true"/>- <seedance:TextVideo id="take-payoff" model="mini" prompt={direction} duration="12" generate-audio="true"/>-- <!-- The cutaways and the board's icons are pictures on disk, so they are- named as files rather than as material a Provider has to make. The site- numbers the cutaways in the order they leave, so broll-5 is shown first. -->- <space:Extent id="portrait" width="540" height="960"/>- <space:Extent id="square" width="192" height="192"/>- <media:Image id="shot-handsome-1" src="../../docs/public/regen-ranking/broll-5.webp"/>- <media:Image id="shot-handsome-2" src="../../docs/public/regen-ranking/broll-4.webp"/>- <media:Image id="shot-dating" src="../../docs/public/regen-ranking/broll-3.webp"/>- <media:Image id="shot-linkedin" src="../../docs/public/regen-ranking/broll-2.webp"/>- <media:Image id="shot-instagram" src="../../docs/public/regen-ranking/broll-1.webp"/>- <media:Image id="icon-regen" src="../../docs/public/regen-ranking/ranking-icon-1.webp"/>- <media:Image id="icon-chatgpt" src="../../docs/public/regen-ranking/ranking-icon-2.webp"/>- <media:Image id="icon-remini" src="../../docs/public/regen-ranking/ranking-icon-3.webp"/>- <media:Image id="icon-facetune" src="../../docs/public/regen-ranking/ranking-icon-4.webp"/>- <media:Image id="icon-photoshop" src="../../docs/public/regen-ranking/ranking-icon-5.webp"/>-- <speech:Spine id="speech" frame-rate="24"- visual-frame={speech-frame} visual-appearance={studio.speech.visual} visual-z="0">- <speech:Take video={take-intro.video} segment={story.segment.intro}/>- <speech:Take video={take-middle.video} segment={story.segment.middle}/>- <speech:Take video={take-payoff.video} segment={story.segment.payoff}/>- </speech:Spine>- <whisperx:Alignment id="timing" narrative={story} audio={speech.audio}/>-- <fonts:Stack id="ui-font" family="inter" weight="700" style="normal"/>- <fonts:Stack id="title-font" family="archivo" weight="900" style="normal"/>-- <!-- The board. Rank order is the child order; each row settles on the next- `@place!` and the whole board leaves on `@done!`. -->- <ranking:ColumnStyle id="board-style" recipe={studio.ranking.board} font={ui-font}/>- <ranking:Column id="board" map={timing.map} space={speech.space} frame={board-frame}- during={story.selection.board} triggers={story.moment.place} terminal={story.moment.done}- style={board-style}>- <ranking:ColumnItem id="row-regen" label="ReGen" icon={icon-regen}/>- <ranking:ColumnItem id="row-chatgpt" label="ChatGPT" icon={icon-chatgpt}/>- <ranking:ColumnItem id="row-remini" label="Remini" icon={icon-remini}/>- <ranking:ColumnItem id="row-facetune" label="Facetune" icon={icon-facetune}/>- <ranking:ColumnItem id="row-photoshop" label="Photoshop" icon={icon-photoshop}/>- </ranking:Column>-- <!-- Five stills cut in over the payoff, each on its own Selection. -->- <media-track:Track id="shots" map={timing.map} space={speech.space} canvas={vertical}>- <media-track:Item id="handsome-1" image={shot-handsome-1} extent={portrait}- during={story.selection.handsome-1} frame={broll-frame}- appearance={studio.media.shot} motion={studio.motion.cut}/>- <media-track:Item id="handsome-2" image={shot-handsome-2} extent={portrait}- during={story.selection.handsome-2} frame={broll-frame}- appearance={studio.media.shot} motion={studio.motion.cut}/>- <media-track:Item id="dating-photo" image={shot-dating} extent={portrait}- during={story.selection.dating-photo} frame={broll-frame}- appearance={studio.media.shot} motion={studio.motion.cut}/>- <media-track:Item id="linkedin-headshot" image={shot-linkedin} extent={portrait}- during={story.selection.linkedin-headshot} frame={broll-frame}- appearance={studio.media.shot} motion={studio.motion.cut}/>- <media-track:Item id="instagram-post" image={shot-instagram} extent={portrait}- during={story.selection.instagram-post} frame={broll-frame}- appearance={studio.media.shot} motion={studio.motion.cut}/>- </media-track:Track>-- <text:Style id="title-style" recipe={studio.text.title} font={title-font}/>- <text:Track id="titles" space={speech.space}>- <text:Area id="headline" placement={title-frame} style={title-style} during="program">- RANKING AI PHOTO APPS FOR GUYS WITH NO GOOD PICS- </text:Area>- </text:Track>-- <caption-fine:Style id="base-caption" recipe={studio.caption.base} font={ui-font}/>- <caption:Program id="caption-program" display={story.caption} default={base-caption}/>- <caption-ai:Planner id="cue-plan" display={story.caption} program={caption-program}- model="gemini-2.5-flash"/>- <caption-fine:Track id="captions" display={story.caption}- correspondence={story.caption.correspondence}- map={timing.map} space={speech.space}- plan={cue-plan.plan} program={caption-program}/>-- <film:Film id="main" canvas={vertical} space={speech.space} appearance={studio.film.vertical}>- <film:Track source={speech.visual}/>- <film:Track source={speech.audioTrack}/>- <film:Track source={board.visual}/>- <film:Track source={titles.track}/>- <film:Track source={captions.track}/>- <film:Track source={shots.visual}/>- </film:Film>- <render:Video id="final" composition={main.composition} space={speech.space}/>-</svml>diff --git a/examples/regen-ranking-preview/studio.svs b/examples/regen-ranking-preview/studio.svsdeleted file mode 100644index 2c044205..00000000--- a/examples/regen-ranking-preview/studio.svs+++ /dev/null@@ -1,46 +0,0 @@-<?svml using="@narratage/svs@1"?>--<sheet version="1">- film.vertical { background: #05060a; }- speech.visual { fit: cover; }-- /* The board: a dark panel on the left third, one row per app, filling from the- bottom rank upward as each name is spoken. */- ranking.board {- board-background: #070810EF;- board-border-color: #FFFFFF2E; board-border-width: 1; board-radius: 6;- board-shadow-x: 0; board-shadow-y: 6; board-shadow-blur: 18; board-shadow-spread: 0;- board-shadow-color: #00000059;- rank-colors: #ff3f56|#ffa72d|#eadc2a|#84c654|#31add0;- padding: 18; row-height: 74; row-gap: 10;- icon-size: 58; icon-radius: 13; icon-fit: contain;- stage-x: 0.66; stage-y: 0.73; stage-size: 356;- font-size: 34; font-weight: 900; text-color: #FFFFFF; line-height: 1.1;- appear-frames: 11; move-frames: 13; motion-easing: ease-out;- board-stack: 20; item-stack: 30; stage-stack: 25;- }-- /* A cutaway replaces the shot, so it carries no box treatment. */- media.shot { stack-order: 60; fit: contain; }- motion.cut {- enter: fade; enter-frames: 2; enter-easing: linear;- exit: fade; exit-frames: 2; exit-easing: linear;- }-- text.title {- stack-order: 90;- weight: 900; size: 62; align: center; fill: #FFFFFF; tracking: -1;- padding: 14 22;- }-- caption.base {- cue-min-words: 1; cue-max-words: 3;- stack-order: 70; x: 0.68; y: 0.56; width: 0.6; anchor-x: center; anchor-y: top;- size: 50; line-height: 1.05; align: center;- fill: #FFFFFF; stroke-color: #05060A; stroke-width: 2;- shadow-color: #000000; shadow-opacity: 0.72; shadow-x: 0; shadow-y: 2; shadow-blur: 6;- background: #00000000; border-color: #00000000; border-width: 0; padding: 0 0; radius: 0;- karaoke: current; karaoke-transition: step; active-fill: #FFD34A;- cue-enter: fade; cue-enter-frames: 2; cue-exit: fade; cue-exit-frames: 2;- }-</sheet>diff --git a/examples/street-interview-preview/build.svrun b/examples/street-interview-preview/build.svrunindex 7ccd3ffb..fd25a07a 100644--- a/examples/street-interview-preview/build.svrun+++ b/examples/street-interview-preview/build.svrun@@ -7,13 +7,20 @@<!-- Footage the documentation site already ships. It is 24 fps, which is theframe rate this Source declares, so the preview can show it as authoredrather than normalizing it. -->- <file id="scene-hook" from="../../docs/public/street-interview/scene-1.mp4" media-type="video/mp4"/>- <file id="scene-price" from="../../docs/public/street-interview/scene-2.mp4" media-type="video/mp4"/>- <file id="scene-rainbow" from="../../docs/public/street-interview/scene-3.mp4" media-type="video/mp4"/>- <file id="scene-payment" from="../../docs/public/street-interview/scene-4.mp4" media-type="video/mp4"/>- <file id="cut-bags" from="../../docs/public/street-interview/broll-2.mp4" media-type="video/mp4"/>- <file id="cut-fee" from="../../docs/public/street-interview/broll-3.mp4" media-type="video/mp4"/>- <file id="cut-receipt" from="../../docs/public/street-interview/broll-4.mp4" media-type="video/mp4"/>+ <file id="scene-hook" type="@narratage/artifact@1#BlobArtifact"+ from="../../docs/public/street-interview/scene-1.mp4" media-type="video/mp4"/>+ <file id="scene-price" type="@narratage/artifact@1#BlobArtifact"+ from="../../docs/public/street-interview/scene-2.mp4" media-type="video/mp4"/>+ <file id="scene-rainbow" type="@narratage/artifact@1#BlobArtifact"+ from="../../docs/public/street-interview/scene-3.mp4" media-type="video/mp4"/>+ <file id="scene-payment" type="@narratage/artifact@1#BlobArtifact"+ from="../../docs/public/street-interview/scene-4.mp4" media-type="video/mp4"/>+ <file id="cut-bags" type="@narratage/artifact@1#BlobArtifact"+ from="../../docs/public/street-interview/broll-2.mp4" media-type="video/mp4"/>+ <file id="cut-fee" type="@narratage/artifact@1#BlobArtifact"+ from="../../docs/public/street-interview/broll-3.mp4" media-type="video/mp4"/>+ <file id="cut-receipt" type="@narratage/artifact@1#BlobArtifact"+ from="../../docs/public/street-interview/broll-4.mp4" media-type="video/mp4"/><!-- The recorded transcript, aligned onto this Script's own anchors by./align-transcript.ts. Which timings a Source is read with is an