OpenMontage
OpenMontageInc/OpenMontage · AGPL-3.0 · Link only · 526 entries
A whole video production system with no engine of its own. A coding agent reads its pipeline manifests and stage skills, calls its 163 Python tools, checks its own work and stops for your approval, from research to a rendered video.
- Link only
You are free to run it. Code you build on it has to be shared under the same license, so we describe it and link to it, and copy none of it.
- Needs
Python 3.10, FFmpeg, Node 22 and a coding agent to drive it. Nearly everything generative needs a key: its example settings file names about 50 keys and settings across image, video, voice and music services.
- Sends off your machine
We found no telemetry. It reads a .env file, starts a local web board and opens your browser, and calls whichever outside services you have given it keys for. That is the point of 125 of its 163 tools.
- We watched it run
With no keys at all, its own registry reported 36 of 163 tools available.
Its zero-key Remotion demo rendered: a title card, a big-number card, a bar chart and a pie chart.
Its slideshow check told eight identical text cards to revise and scored a varied plan strong.
- Not tried here
No pipeline was run end to end. The 125 keyed tools were read, not run.
- License
AGPL-3.0
You are free to run it. Code built on it has to be shared under the same license, so it is here by link only.
Everything in it
Remotion pieces
- AnimeSceneStill images with camera movement, particles, changing light and a vignette. Built on Remotion 4.0.484 and React 18.
- BarChartBars that grow, with optional grid and values. Built on Remotion 4.0.484 and React 18.
- CalloutBoxA boxed message with a title and bullets, in four flavors (info, warning, tip, quote). Built on Remotion 4.0.484 and React 18.
- CaptionOverlayWord-by-word captions over the picture. Built on Remotion 4.0.484 and React 18.
- CinematicRendererA composition for trailers and mood pieces: clips in sequence with titles and a soundtrack, its length worked out from its own data. Built…
- CollageBurstA collage composition: images and clips arranged with spring motion. Built on Remotion 4.0.484 and React 18.
- ComparisonCardTwo labeled values side by side. Built on Remotion 4.0.484 and React 18.
- EndTagA closing line of text that fades in, holds and fades out, in two light-on-black palettes. Built on Remotion 4.0.484 and React 18.
- ExplainerThe main composition. Plays a list of cuts from a props file; each cut is a clip, a still with a slow move, or one of the scene types…
- HeroTitleA full-frame title with subtitle, used as an opening or closing card and as an overlay. Built on Remotion 4.0.484 and React 18.
- KPIGridA grid of two to four columns of key figures. Built on Remotion 4.0.484 and React 18.
- LineChartA line that draws itself, with optional markers and axis labels. Built on Remotion 4.0.484 and React 18.
- LyricOverlayTimed lyric lines over a video. Built on Remotion 4.0.484 and React 18.
- ParticleOverlayDrifting particles over a scene. Built on Remotion 4.0.484 and React 18.
- PieChartA pie or donut that sweeps in, with legend and center label. Built on Remotion 4.0.484 and React 18.
- ProductRevealA product card: picture, name, price, tagline and a closing line, registered as wide and tall compositions of its own. Built on Remotion…
- ProgressBarAn animated progress bar, plain or in segments. Built on Remotion 4.0.484 and React 18.
- ProviderChipA rotating badge that cycles through a list of names. Built on Remotion 4.0.484 and React 18.
- remotionProject conventions for Remotion from a third-party video toolkit: custom transitions and shared components.
- remotion-best-practicesAn older copy of Remotion's own best-practices skill with 38 rule files. Upstream (remotion-dev/skills) states no license, and this copy…
- ScreenshotSceneA screenshot used as a frozen backdrop with scripted things drawn over it: a cursor, click pulses, typing, chat bubbles. Built on Remotion…
- SectionTitleA small section label, as an overlay. Built on Remotion 4.0.484 and React 18.
- StatCardOne big number with a line under it. Built on Remotion 4.0.484 and React 18.
- StatRevealA small number badge in a corner, as an overlay. Built on Remotion 4.0.484 and React 18.
- TalkingHeadA tall composition for speaker footage with captions. Built on Remotion 4.0.484 and React 18.
- TerminalSceneA fake terminal that types commands and prints output from a list of steps, with no real screen capture. Built on Remotion 4.0.484 and…
- TextCardOne large line of text as a beat, optionally over a background video. Built on Remotion 4.0.484 and React 18.
- TitledVideoPlays a video with a serif title treatment over it; a sample props file sits beside the composer. Built on Remotion 4.0.484 and React 18.
HTML to video
- hyperframesThe entry skill for HyperFrames (HTML rendered to video): routes any video request to the right HyperFrames skill. A copy of HeyGen's…
- hyperframes-animationAll the motion knowledge for HyperFrames: small motion rules, scene blueprints, transitions. Copy of HeyGen's skill.
- hyperframes-cliThe HyperFrames command-line loop: init, add, lint, validate, preview, render. Copy of HeyGen's skill.
- hyperframes-coreThe HyperFrames composition contract: structure, timing attributes, clips, tracks. Copy of HeyGen's skill.
- hyperframes-creativeCreative direction for HyperFrames videos apart from motion: design spec, palettes, type, narration, beat planning. Copy of HeyGen's skill.
- hyperframes-mediaAudio and media for HyperFrames from one shared audio script: speech from several providers, music, and 19 bundled sound effects from…
- hyperframes-registryInstalling ready-made HyperFrames blocks and components into a composition. Copy of HeyGen's skill.
- Ink PuppetA stick figure that draws itself in and then plays named motion-capture clips in sequence. The agent only chooses the moves; nothing is…
- Ink Theater engineA small script for hand-drawn black-ink animation in HTML and SVG on one paused GSAP timeline: wobbly ink strokes, a line 'boil' that is…
- mocap-figure exampleThe runnable example: a 21.8-second page where a pencil line becomes a stick figure that walks, runs, dances, kicks, sits and waves, with…
- motion-graphicsShort design-led motion graphics where the motion is the message: kinetic type, number count-ups, chart reveals, logo stings.
- music-to-videoTurning a music track into a beat-synced HyperFrames video, calm to hard-hitting.
- remotion-to-hyperframesPorting an existing Remotion composition to HyperFrames HTML, only when asked to; includes a test set of example compositions.
- Twelve motion-capture clipsTwelve 2D motion clips for the puppet: climb, dance_glide, dance_spin, jump, kick, march, run, shuffle, sit, twist, walk, wave. Made from…
- website-to-videoCapturing a website and turning it into a HyperFrames video (tour, showcase or social clip), with the same 19 bundled Pixabay sound…
GSAP motion
- gsap-coreGreenSock's own skill for the core GSAP API. A copy of the skill in greensock/gsap-skills, which is MIT.
- gsap-frameworksGreenSock's own skill for GSAP in Vue, Svelte and other non-React frameworks. Copy of the MIT upstream.
- gsap-performanceGreenSock's own skill for GSAP performance. Copy of the MIT upstream.
- gsap-pluginsGreenSock's own skill for the GSAP plugins (SplitText, Flip, MorphSVG and the rest). Copy of the MIT upstream.
- gsap-reactGreenSock's own skill for GSAP in React. Copy of the MIT upstream.
- gsap-scrolltriggerGreenSock's own skill for scroll-linked animation. Copy of the MIT upstream.
- gsap-timelineGreenSock's own skill for GSAP timelines. Copy of the MIT upstream.
- gsap-utilsGreenSock's own skill for the GSAP helper functions. Copy of the MIT upstream.
three.js and WebGL
- threejs-animationthree.js animation: keyframes, skeletons, morph targets, mixing.
- threejs-fundamentalsthree.js basics: scene, cameras, renderer, object hierarchy, coordinates.
- threejs-geometrythree.js geometry: built-in shapes, buffer geometry, custom shapes, instancing.
- threejs-interactionthree.js interaction: raycasting, controls, pointer input, selection.
- threejs-lightingthree.js lighting: light types, shadows, environment lighting.
- threejs-loadersthree.js asset loading: glTF, textures, HDR environments, async patterns.
- threejs-materialsthree.js materials: PBR, basic, shader materials and their properties.
- threejs-postprocessingthree.js post-processing: bloom, depth of field, screen effects.
- threejs-shadersthree.js shaders: GLSL, uniforms, custom effects.
- threejs-texturesthree.js textures: types, UV mapping, environment maps, settings.
- threejs-world-generationBuilding editable three.js worlds you can fly a camera through, from text or a structured brief.
Starters
- action_timeline schemaTimed character actions and poses ready to render. A JSON Schema; required fields: version, scenes.
- Anime GhibliA style playbook: one YAML file that fixes colors, type, motion, audio, asset prompts, chart palette and quality rules for a whole video…
- asset_manifest schemaThe inventory of assets made or found. A JSON Schema; required fields: version, assets.
- brief schemaThe creative brief: title, hook, key points, tone, style, platform, length. A JSON Schema; required fields: version, title, hook…
- character_design schemaCharacter definitions for rigged animation. A JSON Schema; required fields: version, characters.
- character_qa_report schemaA review of rig integrity, motion and render readiness. A JSON Schema; required fields: version, status, checks.
- checkpoint schemaThe resumable snapshot written after each stage. A JSON Schema; required fields: version, project_id, pipeline_type, stage, status…
- Clean ProfessionalA style playbook: one YAML file that fixes colors, type, motion, audio, asset prompts, chart palette and quality rules for a whole video…
- cost_log schemaEstimated, reserved and actual spend per operation. A JSON Schema; required fields: version, entries.
- decision_log schemaThe audit trail: every meaningful choice with the options considered and the reason, appended and never edited. A JSON Schema; required…
- edit_decisions schemaThe edit-decision format: timed cuts (source, in, out, speed, layer, transition, reason), overlays, audio (narration, music, effects)…
- final_review schemaThe self-review of a finished render: a technical probe, frames looked at from four points, an audio check, whether the promise was kept…
- Flat Motion GraphicsA style playbook: one YAML file that fixes colors, type, motion, audio, asset prompts, chart palette and quality rules for a whole video…
- Minimalist DiagramA style playbook: one YAML file that fixes colors, type, motion, audio, asset prompts, chart palette and quality rules for a whole video…
- pipeline_manifest schemaThe shape of a pipeline definition: stages, files in and out, tools, approval policy. A JSON Schema; required fields: name, version, stages.
- playbook schemaThe shape of a style playbook. A JSON Schema; required fields: identity, visual_language, typography, motion, audio, asset_generation…
- pose_library schemaNamed poses, expressions and transition hints. A JSON Schema; required fields: version, characters.
- Premium MinimalistA style playbook: one YAML file that fixes colors, type, motion, audio, asset prompts, chart palette and quality rules for a whole video…
- proposal_packet schemaThe proposal a person approves before anything is made: concept options, the chosen one, the production plan, an itemised cost estimate…
- publish_log schemaPer-platform export results. A JSON Schema; required fields: version, entries.
- render_report schemaWhat the render produced and where. A JSON Schema; required fields: version, outputs.
- research_brief schemaResearch findings with data points, audience insights, angles and sources. A JSON Schema; required fields: version, topic, research_date…
- review schemaA stage review: findings each graded critical, suggestion or nitpick, with the agent's response and whether it was accepted. A JSON Schema…
- rig_plan schemaRig parts, pivots, layers, constraints and views. A JSON Schema; required fields: version, characters.
- scene_plan schemaThe ordered scene list, with what each scene needs. A JSON Schema; required fields: version, scenes.
- script schemaThe timed script in sections. A JSON Schema; required fields: version, title, total_duration_seconds, sections.
- sky-spectrumA style playbook: one YAML file that fixes colors, type, motion, audio, asset prompts, chart palette and quality rules for a whole video. A…
- source_media_review schemaThe review of footage a user supplied, with what it means for planning. A JSON Schema; required fields: version, files, summary…
- video_analysis_brief schemaThe analysis of a reference video: content and structure. A JSON Schema; required fields: version, source, content_analysis…
- Zero-key demo propsFive ready props files for the Explainer composition that need no keys and no assets: world-in-numbers, code-to-screen, focusflow-pitch…
Agent skills
- /animated-drawingSlash command that makes a supplied drawing or photo of a character move with Meta's AnimatedDrawings. Copies for other agents sit in…
- /backlotSlash command that opens the Backlot board for the current or named project. Copies for other agents sit in .cursor/commands…
- /ink-artSlash command for a hand-drawn ink animation: a character that draws itself and moves, or a contraption explainer, rendered through…
- /reelThe general slash command: make or work on a video with the pipeline system, for whatever is described. Copies for other agents sit in…
- 3d-asset-generationGenerating, rebuilding and checking 3D models for the world-building tools, through Atlas Cloud, fal.ai, licensed catalogs and Blender.
- acestepMusic generation with the ACE-Step model: background music, vocal tracks, covers, stems.
- AGENT_GUIDE.mdThe operating contract every agent is told to read first (CLAUDE.md, AGENTS.md and the other agent files contain only that order). It sets…
- agentsBuilding voice agents with ElevenLabs.
- ai-video-genGenerating video from text through several provider gateways.
- animated-explainerAn explainer made from a topic alone: researched, scripted, narrated, illustrated, scored and rendered. Stages: research, proposal (waits…
- animationMotion graphics: kinetic type, diagram-led explainers, maths visuals, three.js worlds, stylized sequences. Stages: research, proposal…
- animation/asset-directorHow the agent runs the assets stage of the animation pipeline. The stage hands on the list of assets made or found. Stops for the person's…
- animation/compose-directorHow the agent runs the compose stage of the animation pipeline. The stage hands on a render report, a review of the finished render. No…
- animation/edit-directorHow the agent runs the edit stage of the animation pipeline. The stage hands on the edit-decision file. No approval stop by default.
- animation/executive-producerThe orchestrator skill for the animation pipeline: runs the stages in order, sends work back for another pass, and holds the budget…
- animation/idea-directorA director skill in the animation pipeline's folder that no stage in the current manifest names; kept from an earlier layout.
- animation/proposal-directorHow the agent runs the proposal stage of the animation pipeline. The stage hands on a proposal with concept options and costs, the decision…
- animation/publish-directorHow the agent runs the publish stage of the animation pipeline. The stage hands on a publish log. Stops for the person's approval.
- animation/research-directorHow the agent runs the research stage of the animation pipeline. The stage hands on a research brief. No approval stop by default.
- animation/scene-directorHow the agent runs the scene_plan stage of the animation pipeline. The stage hands on the scene plan. Stops for the person's approval.
- animation/script-directorHow the agent runs the script stage of the animation pipeline. The stage hands on the script. Stops for the person's approval.
- atlas-cloudGenerating and editing images and video through the Atlas Cloud gateway.
- avatar-spokespersonA presenter-led video with a digital presenter and simple support graphics. Stages: idea (waits for approval), script (waits for approval)…
- avatar-spokesperson/asset-directorHow the agent runs the assets stage of the avatar-spokesperson pipeline. The stage hands on the list of assets made or found. Stops for the…
- avatar-spokesperson/compose-directorHow the agent runs the compose stage of the avatar-spokesperson pipeline. The stage hands on a render report, a review of the finished…
- avatar-spokesperson/edit-directorHow the agent runs the edit stage of the avatar-spokesperson pipeline. The stage hands on the edit-decision file. No approval stop by…
- avatar-spokesperson/executive-producerThe orchestrator skill for the avatar-spokesperson pipeline: runs the stages in order, sends work back for another pass, and holds the…
- avatar-spokesperson/idea-directorHow the agent runs the idea stage of the avatar-spokesperson pipeline. The stage hands on the brief, the decision log. Stops for the…
- avatar-spokesperson/publish-directorHow the agent runs the publish stage of the avatar-spokesperson pipeline. The stage hands on a publish log. Stops for the person's approval.
- avatar-spokesperson/scene-directorHow the agent runs the scene_plan stage of the avatar-spokesperson pipeline. The stage hands on the scene plan. Stops for the person's…
- avatar-spokesperson/script-directorHow the agent runs the script stage of the avatar-spokesperson pipeline. The stage hands on the script. Stops for the person's approval.
- avatar-videoMaking avatar videos with HeyGen's API: avatars, voices, scripts, scenes, backgrounds.
- azure-speech-to-textTranscribing audio with Azure AI Speech.
- azure-text-to-speechNarration with Azure AI Speech.
- beautiful-mermaidRendering Mermaid diagrams to SVG and PNG with the Beautiful Mermaid library.
- bfl-apiCalling the Black Forest Labs FLUX API: endpoints, polling, rate limits, errors, webhooks.
- canvas-procedural-animationProcedural character effects with p5.js and canvas: particles, weather, squash and stretch, walk cycles.
- character-animationReusable 2D cartoon characters: character design, rig, pose library, action timeline, rendered in a browser. Marked beta. Stages: research…
- character-animation-qaReviewing local character animation: schema checks, browser previews, frame samples, final output checks.
- character-animation/asset-directorHow the agent runs the assets stage of the character-animation pipeline. The stage hands on the list of assets made or found. Stops for the…
- character-animation/character-design-directorHow the agent runs the character_design stage of the character-animation pipeline. The stage hands on the character design. Stops for the…
- character-animation/compose-directorHow the agent runs the compose stage of the character-animation pipeline. The stage hands on a render report, a review of the finished…
- character-animation/edit-directorHow the agent runs the edit stage of the character-animation pipeline. The stage hands on the edit-decision file, the action timeline. No…
- character-animation/executive-producerThe orchestrator skill for the character-animation pipeline: runs the stages in order, sends work back for another pass, and holds the…
- character-animation/proposal-directorHow the agent runs the proposal stage of the character-animation pipeline. The stage hands on a proposal with concept options and costs…
- character-animation/publish-directorHow the agent runs the publish stage of the character-animation pipeline. The stage hands on a publish log. Stops for the person's approval.
- character-animation/research-directorHow the agent runs the research stage of the character-animation pipeline. The stage hands on a research brief. No approval stop by default.
- character-animation/rig-plan-directorHow the agent runs the rig_plan stage of the character-animation pipeline. The stage hands on the rig plan, the pose library. No approval…
- character-animation/scene-directorHow the agent runs the scene_plan stage of the character-animation pipeline. The stage hands on the scene plan. Stops for the person's…
- character-animation/script-directorHow the agent runs the script stage of the character-animation pipeline. The stage hands on the script. Stops for the person's approval.
- character-riggingBuilding 2D character rigs from data: parts, pivots, layers, constraints, views.
- cinematicTrailers, brand films, montages and 3D fly-throughs, led by mood. Stages: research, proposal (waits for approval), script (waits for…
- cinematic/asset-directorHow the agent runs the assets stage of the cinematic pipeline. The stage hands on the list of assets made or found. Stops for the person's…
- cinematic/compose-directorHow the agent runs the compose stage of the cinematic pipeline. The stage hands on a render report, a review of the finished render. No…
- cinematic/edit-directorHow the agent runs the edit stage of the cinematic pipeline. The stage hands on the edit-decision file. No approval stop by default.
- cinematic/executive-producerThe orchestrator skill for the cinematic pipeline: runs the stages in order, sends work back for another pass, and holds the budget…
- cinematic/idea-directorA director skill in the cinematic pipeline's folder that no stage in the current manifest names; kept from an earlier layout.
- cinematic/proposal-directorHow the agent runs the proposal stage of the cinematic pipeline. The stage hands on a proposal with concept options and costs, the decision…
- cinematic/publish-directorHow the agent runs the publish stage of the cinematic pipeline. The stage hands on a publish log. Stops for the person's approval.
- cinematic/research-directorHow the agent runs the research stage of the cinematic pipeline. The stage hands on a research brief. No approval stop by default.
- cinematic/scene-directorHow the agent runs the scene_plan stage of the cinematic pipeline. The stage hands on the scene plan. Stops for the person's approval.
- cinematic/script-directorHow the agent runs the script stage of the cinematic pipeline. The stage hands on the script. Stops for the person's approval.
- clip-factoryMany short clips cut from one long recording, ranked and captioned. Marked beta. Stages: idea (waits for approval), script (waits for…
- clip-factory/asset-directorHow the agent runs the assets stage of the clip-factory pipeline. The stage hands on the list of assets made or found. Stops for the…
- clip-factory/compose-directorHow the agent runs the compose stage of the clip-factory pipeline. The stage hands on a render report, a review of the finished render. No…
- clip-factory/edit-directorHow the agent runs the edit stage of the clip-factory pipeline. The stage hands on the edit-decision file. No approval stop by default.
- clip-factory/executive-producerThe orchestrator skill for the clip-factory pipeline: runs the stages in order, sends work back for another pass, and holds the budget…
- clip-factory/idea-directorHow the agent runs the idea stage of the clip-factory pipeline. The stage hands on the brief, the decision log. Stops for the person's…
- clip-factory/publish-directorHow the agent runs the publish stage of the clip-factory pipeline. The stage hands on a publish log. Stops for the person's approval.
- clip-factory/scene-directorHow the agent runs the scene_plan stage of the clip-factory pipeline. The stage hands on the scene plan. Stops for the person's approval.
- clip-factory/script-directorHow the agent runs the script stage of the clip-factory pipeline. The stage hands on the script. Stops for the person's approval.
- comfyuiWorking with ComfyUI workflows from this system's image, video and music tools.
- core/color-gradingColor grading with FFmpeg: seven named looks, which look suits which kind of content, LUT use, and protecting skin tones.
- core/ffmpegWhen to reach for the FFmpeg-backed tools (anything that needs no AI model) and the patterns they share.
- core/hyperframesOpenMontage's own guide to HyperFrames: when to choose it over Remotion or plain FFmpeg, how a project folder is laid out, and how the…
- core/remotionOpenMontage's own guide to Remotion: when to route a video through the Remotion composer, the scene types it accepts, and how the pipeline…
- core/subtitle-syncTurning a transcript into subtitles with the subtitle tool: output formats, line lengths per platform, burn-in styling and timing.
- core/whisperxUsing the local transcriber: how it works, which model size to pick, and a quality checklist.
- create-videoMaking a video from a prompt with HeyGen's Video Agent.
- creative/3d-world-generationWhen a film needs a real, continuous three.js world instead of stills or generated clips: which tools to route through, what each asset…
- creative/animated-drawingMaking a person's own drawing or photo of a character move (dance, walk, jump, wave) with Meta's AnimatedDrawings and real motion capture…
- creative/animation-pipelineMotion-graphics basics for the two render paths: choosing Remotion or HyperFrames, frame rate, timing principles and scene transitions.
- creative/bg-remove-usageUsing the background-removal tool: which model, alpha matting, common recipes.
- creative/broll-planningPlanning supporting footage: stock against generated, pulling the needs out of a script, writing stock search queries, judging results.
- creative/cinematicThe cinematic look: wide aspect ratios, shot length and pacing, layered sound, grading, and replacing mood words with the visual cause of…
- creative/commercial-product-videoMaking a commercial for a physical product with generated shots of the exact item: turning a brief into a treatment and keeping the product…
- creative/data-visualizationShowing data in a video: which chart for which claim, the order to animate things in, label placement, and how much data a viewer can read.
- creative/diagram-gen-usageUsing the diagram tool for video: which diagram type, how many nodes a 1080p frame can carry, color themes, and building a diagram up step…
- creative/enhancement-strategyDeciding how to improve talking-head footage: the order of the enhancement tools, overlay types, how many overlays is too many, where to…
- creative/face-restore-usageUsing face restoration, and how it differs from the light face-enhance filter.
- creative/image-gen-usageGenerating stills for video: frame sizes, keeping a look consistent across a batch, and a three-part prompt structure.
- creative/image-provider-usageWhich image provider for which kind of scene, each one's quirks, cost against quality, and using the selector.
- creative/ink-theaterThe creative method behind Ink Theater: a black-ink character acts out an abstract idea by working an absurd low-tech machine. Gives the…
- creative/lip-sync-usageUsing local lip sync: when to use it against the talking-head generator, model choice, input needs and face padding.
- creative/long-formVideos of ten minutes and more: retention benchmarks, managing the retention curve, structure, keeping sound consistent, visual pacing.
- creative/manim-usageUsing Manim for maths animation in this system: render settings, timing, composition and color.
- creative/music-gen-usageGenerating background music: tempo by video type, key and mood, prompt writing, matching length, looping for long videos.
- creative/prompting/grok-promptingPrompt guidance for xAI Grok image and video generation.
- creative/prompting/hunyuan-promptingPrompt guidance for HunyuanVideo: a prompt formula, strengths, image-to-video practice, two examples.
- creative/prompting/ltx-promptingPrompt guidance for LTX video: a six-part structure, tips, what to avoid.
- creative/prompting/seedance-promptingPrompt guidance for Seedance: an eight-part structure, multi-shot and lip-sync patterns, a parameter sheet.
- creative/prompting/sora-promptingPrompt guidance for Sora: a template, optional fields, a color-palette technique, and which settings cannot be set in the prompt.
- creative/prompting/veo-promptingPrompt guidance for Google Veo: a fourteen-part structure, lens effects, art-movement references, and stopping unwanted subtitles.
- creative/scene-detect-usageUsing scene detection: which algorithm, tuning the threshold, cleaning up the result, presets by content type.
- creative/screen-recordingScreen recordings: recording settings, cursor handling, zoom and pan, post-processing.
- creative/short-formVertical short video: safe zones on a 1080 by 1920 frame, upload specs, length strategy, the one-second hook, pacing.
- creative/sound-designSound for video: level targets for speech, music and effects, ducking amounts, music choice by content type, effect placement, platform…
- creative/stock-sourcing-usageUsing the stock tools: which provider for what, input settings, traps (some download links expire), and a licensing summary.
- creative/storytellingStory structure for explainers: an arc template scaled by length, hook types, and a thirty-second rule.
- creative/talking-head-gen-usageUsing the photo-to-talking-head generator: when, input needs, model choice, settings.
- creative/typographyType for video: font choice, sizes at 1080p and 4K, safe zones, text animation timing, subtitle type.
- creative/upscale-usageUsing the upscaler: when it helps, model and scale choice, faces, denoise strength.
- creative/video-editingEditing choices for talking-head footage and the shape of the edit-decision file.
- creative/video-gen-promptingThe general guide to prompting video models: order of elements, a universal formula, camera shot types, with pointers to the per-model…
- creative/video-stitchingJoining clips: when to stitch, strategies, which transition, and keeping audio in step.
- creative/video-understand-usageUsing the local vision model on frames and clips: modes, model choice, which frames to pick.
- d3-vizData visualization with d3.js: charts, graphs, networks, maps.
- dashscopeAlibaba DashScope: image generation, speech, and transcription with word timings.
- docs/PROVIDERS.mdThe provider guide: every outside service the tools can call, how to get its key, what it costs and what the free tier is. 1,558 lines.
- documentary-montageA montage cut from real footage found in free stock and open archives, chosen by meaning with CLIP. Marked beta. Stages: idea (waits for…
- documentary-montage/asset-directorHow the agent runs the assets stage of the documentary-montage pipeline. The stage hands on the list of assets made or found. Stops for the…
- documentary-montage/compose-directorHow the agent runs the compose stage of the documentary-montage pipeline. The stage hands on a render report. No approval stop by default.
- documentary-montage/edit-directorHow the agent runs the edit stage of the documentary-montage pipeline. The stage hands on the edit-decision file. Stops for the person's…
- documentary-montage/executive-producerThe orchestrator skill for the documentary-montage pipeline: runs the stages in order, sends work back for another pass, and holds the…
- documentary-montage/idea-directorHow the agent runs the idea stage of the documentary-montage pipeline. The stage hands on the brief. Stops for the person's approval.
- documentary-montage/scene-directorHow the agent runs the scene_plan stage of the documentary-montage pipeline. The stage hands on the scene plan. Stops for the person's…
- doubao-ttsMandarin and multilingual narration with Volcengine Doubao Speech.
- elevenlabsVoiceovers, sound effects and music with the ElevenLabs APIs.
- explainer/asset-directorHow the agent runs the assets stage of the animated-explainer pipeline. The stage hands on the list of assets made or found. Stops for the…
- explainer/compose-directorHow the agent runs the compose stage of the animated-explainer pipeline. The stage hands on a render report, a review of the finished…
- explainer/edit-directorHow the agent runs the edit stage of the animated-explainer pipeline. The stage hands on the edit-decision file. No approval stop by…
- explainer/executive-producerThe orchestrator skill for the animated-explainer pipeline: runs the stages in order, sends work back for another pass, and holds the…
- explainer/idea-directorA director skill in the animated-explainer pipeline's folder that no stage in the current manifest names; kept from an earlier layout.
- explainer/proposal-directorHow the agent runs the proposal stage of the animated-explainer pipeline. The stage hands on a proposal with concept options and costs, the…
- explainer/publish-directorHow the agent runs the publish stage of the animated-explainer pipeline. The stage hands on a publish log. Stops for the person's approval.
- explainer/research-directorHow the agent runs the research stage of the animated-explainer pipeline. The stage hands on a research brief. No approval stop by default.
- explainer/scene-directorHow the agent runs the scene_plan stage of the animated-explainer pipeline. The stage hands on the scene plan. Stops for the person's…
- explainer/script-directorHow the agent runs the script stage of the animated-explainer pipeline. The stage hands on the script. Stops for the person's approval.
- faceswapSwapping a face in a video through HeyGen.
- ffmpegVideo and audio processing with FFmpeg: convert, resize, compress, extract audio, prepare assets for Remotion.
- fish-audio-ttsExpressive multilingual narration and cloned voices with fish.audio.
- flux-best-practicesPrompting the FLUX image models: text to image, image to image, structured prompts, color codes, lettering, multi-reference edits.
- framer-motionDisney's twelve animation principles applied with Framer Motion in React.
- framework-smokeA two-stage test manifest that exercises the pipeline machinery. Not for making a video. Stages: research (waits for approval), script…
- gemini-omniGenerating short videos with Google's Gemini Omni model and editing them by conversation.
- grok-mediaxAI Grok image and video generation: sign-in, endpoints, prompt structure, edits, polling.
- heygenAn older combined HeyGen skill; its own description marks it deprecated in favor of create-video and avatar-video.
- hybridYour own footage combined with designed or generated support graphics. Stages: idea (waits for approval), script (waits for approval)…
- hybrid/asset-directorHow the agent runs the assets stage of the hybrid pipeline. The stage hands on the list of assets made or found. Stops for the person's…
- hybrid/compose-directorHow the agent runs the compose stage of the hybrid pipeline. The stage hands on a render report, a review of the finished render. No…
- hybrid/edit-directorHow the agent runs the edit stage of the hybrid pipeline. The stage hands on the edit-decision file. No approval stop by default.
- hybrid/executive-producerThe orchestrator skill for the hybrid pipeline: runs the stages in order, sends work back for another pass, and holds the budget (default…
- hybrid/idea-directorHow the agent runs the idea stage of the hybrid pipeline. The stage hands on the brief, the decision log. Stops for the person's approval.
- hybrid/publish-directorHow the agent runs the publish stage of the hybrid pipeline. The stage hands on a publish log. Stops for the person's approval.
- hybrid/scene-directorHow the agent runs the scene_plan stage of the hybrid pipeline. The stage hands on the scene plan. Stops for the person's approval.
- hybrid/script-directorHow the agent runs the script stage of the hybrid pipeline. The stage hands on the script. Stops for the person's approval.
- kling-officialUsing Kling's official API from this system's Kling tools: video, image, speech, avatar, lip sync.
- localization-dubTranslated subtitles and dubbed audio for an existing video, optionally with lips re-synced. Marked beta. Stages: idea (waits for…
- localization-dub/asset-directorHow the agent runs the assets stage of the localization-dub pipeline. The stage hands on the list of assets made or found. Stops for the…
- localization-dub/compose-directorHow the agent runs the compose stage of the localization-dub pipeline. The stage hands on a render report, a review of the finished render…
- localization-dub/edit-directorHow the agent runs the edit stage of the localization-dub pipeline. The stage hands on the edit-decision file. No approval stop by default.
- localization-dub/executive-producerThe orchestrator skill for the localization-dub pipeline: runs the stages in order, sends work back for another pass, and holds the budget…
- localization-dub/idea-directorHow the agent runs the idea stage of the localization-dub pipeline. The stage hands on the brief, the decision log. Stops for the person's…
- localization-dub/publish-directorHow the agent runs the publish stage of the localization-dub pipeline. The stage hands on a publish log. Stops for the person's approval.
- localization-dub/scene-directorHow the agent runs the scene_plan stage of the localization-dub pipeline. The stage hands on the scene plan. Stops for the person's…
- localization-dub/script-directorHow the agent runs the script stage of the localization-dub pipeline. The stage hands on the script. Stops for the person's approval.
- lottie-bodymovinDisney's twelve animation principles applied with Lottie animations exported from After Effects.
- ltx2Video generation with the LTX model: text to video and image to video.
- lyriaGenerating and checking music with Google Lyria.
- manim-composerPlanning an explainer in the style of mathematical animation channels before writing Manim code. Third-party; the two Manim skills beside…
- manimce-best-practicesBest practices for Manim Community Edition. Carries its own MIT license file (Adithya S Kolavi, 2026).
- manimgl-best-practicesBest practices for ManimGL, the original Manim. Carries its own MIT license file.
- media-useOne routine that turns any media need (music, sound effect, image, icon) into a saved local file with a record of where it came from.
- meta/animation-runtime-selectorChoosing the render path for a video (Remotion, HyperFrames or FFmpeg) and which animation library to use inside it, with a stated bias…
- meta/bespoke-composition'Atelier' mode: writing a composition by hand from scratch for a piece that must not look like the stock templates. Sets when to choose it…
- meta/capability-extensionWhat the agent may do when no tool covers a need: when a one-off script, a custom style file, a new skill or a tool wrapper is allowed, and…
- meta/checkpoint-protocolWhen and how to save a stage's state and when to stop and wait for the person. A stage marked as needing approval cannot be recorded as…
- meta/creative-intakeThe questions to ask before research starts, asked as conversation and not as a form, and how to handle vague and detailed briefs.
- meta/onboardingWhat to do when a new user arrives without a concrete request: check what tools are set up, say in plain words what is possible, offer…
- meta/reviewerThe self-review an agent runs after every stage: check the file against its schema, against the stage's review points and the style rules…
- meta/skill-creatorHow the agent writes a new skill file when it meets a reusable gap.
- meta/taste-directionFixing the look before committing to it: a written taste profile (how varied, how much motion, how dense), a reference strategy and a list…
- meta/video-reference-analystStarting from a video the user likes: analyze what it does (content, pacing, structure, style), then offer two or three different concepts…
- meta/voice-performance-directorDirecting synthetic narration: a written plan for pace, pauses and emphasis, how that maps to each speech provider's settings, and a sample…
- minimax-h3Generating video with MiniMax H3 through its official API, fal.ai, Runway, ComfyUI or local weights.
- musicGenerating music with the ElevenLabs Music API.
- playwright-recordingRecording browser sessions as video with Playwright, for demos and walkthroughs.
- podcast-repurposeAudiograms, caption-led clips and quote cards from a podcast episode. Marked beta. Stages: idea (waits for approval), script (waits for…
- podcast-repurpose/asset-directorHow the agent runs the assets stage of the podcast-repurpose pipeline. The stage hands on the list of assets made or found. Stops for the…
- podcast-repurpose/compose-directorHow the agent runs the compose stage of the podcast-repurpose pipeline. The stage hands on a render report, a review of the finished…
- podcast-repurpose/edit-directorHow the agent runs the edit stage of the podcast-repurpose pipeline. The stage hands on the edit-decision file. No approval stop by default.
- podcast-repurpose/executive-producerThe orchestrator skill for the podcast-repurpose pipeline: runs the stages in order, sends work back for another pass, and holds the budget…
- podcast-repurpose/idea-directorHow the agent runs the idea stage of the podcast-repurpose pipeline. The stage hands on the brief, the decision log. Stops for the person's…
- podcast-repurpose/publish-directorHow the agent runs the publish stage of the podcast-repurpose pipeline. The stage hands on a publish log. Stops for the person's approval.
- podcast-repurpose/scene-directorHow the agent runs the scene_plan stage of the podcast-repurpose pipeline. The stage hands on the scene plan. Stops for the person's…
- podcast-repurpose/script-directorHow the agent runs the script stage of the podcast-repurpose pipeline. The stage hands on the script. Stops for the person's approval.
- pose-library-designDesigning reusable 2D character poses, action cycles and expressions.
- PROMPT_GALLERY.mdA gallery of example requests to give the agent, grouped by what is set up (no keys, free footage, an image or video provider, full setup).
- provider-model-refreshNotes on the image, video, speech and avatar provider adapters added in September 2026.
- provider-refresh-oct23API contracts and routing for the providers added on October 23 2026.
- SCENE_TYPES.mdThe list of every cut type and overlay type the Explainer composition accepts, with required and common fields, and the five steps for…
- screen-demoA polished software demo, from a real screen capture or from fake terminal scenes that need no capture at all. Stages: idea (waits for…
- screen-demo/asset-directorHow the agent runs the assets stage of the screen-demo pipeline. The stage hands on the list of assets made or found. Stops for the…
- screen-demo/compose-directorHow the agent runs the compose stage of the screen-demo pipeline. The stage hands on a render report, a review of the finished render. No…
- screen-demo/edit-directorHow the agent runs the edit stage of the screen-demo pipeline. The stage hands on the edit-decision file. No approval stop by default.
- screen-demo/executive-producerThe orchestrator skill for the screen-demo pipeline: runs the stages in order, sends work back for another pass, and holds the budget…
- screen-demo/idea-directorHow the agent runs the idea stage of the screen-demo pipeline. The stage hands on the brief, the decision log. Stops for the person's…
- screen-demo/publish-directorHow the agent runs the publish stage of the screen-demo pipeline. The stage hands on a publish log. Stops for the person's approval.
- screen-demo/scene-directorHow the agent runs the scene_plan stage of the screen-demo pipeline. The stage hands on the scene plan. Stops for the person's approval.
- screen-demo/script-directorHow the agent runs the script stage of the screen-demo pipeline. The stage hands on the script. Stops for the person's approval.
- seedance-2-0Generating cinematic clips with ByteDance Seedance 2.0.
- seedance-2-5Generating 4 to 30 second clips with Seedance 2.5 through fal.ai, Volcengine, Runway or ComfyUI.
- setup-api-keyWalking a user through setting up an ElevenLabs API key.
- skills/INDEX.mdThe index of every OpenMontage skill and vendored pack, with when to read each.
- sound-effectsGenerating sound effects from text with ElevenLabs.
- speech-to-textTranscribing audio with ElevenLabs Scribe.
- svg-character-animationAnimating SVG character rigs with GSAP, CSS transforms and Remotion frame control.
- synthetic-screen-recordingFaking a terminal screen recording with the composer's TerminalScene component, with no real capture.
- tailwind-design-systemBuilding design systems with Tailwind CSS v4: tokens, component libraries, responsive patterns.
- talking-headAn edit of someone speaking to camera: transcribed, cut, captioned, mixed. Marked beta. Stages: idea (waits for approval), script (waits…
- talking-head/asset-directorHow the agent runs the assets stage of the talking-head pipeline. The stage hands on the list of assets made or found. Stops for the…
- talking-head/compose-directorHow the agent runs the compose stage of the talking-head pipeline. The stage hands on a render report, a review of the finished render. No…
- talking-head/edit-directorHow the agent runs the edit stage of the talking-head pipeline. The stage hands on the edit-decision file. No approval stop by default.
- talking-head/executive-producerThe orchestrator skill for the talking-head pipeline: runs the stages in order, sends work back for another pass, and holds the budget…
- talking-head/idea-directorHow the agent runs the idea stage of the talking-head pipeline. The stage hands on the brief, the decision log. Stops for the person's…
- talking-head/publish-directorHow the agent runs the publish stage of the talking-head pipeline. The stage hands on a publish log. Stops for the person's approval.
- talking-head/scene-directorHow the agent runs the scene_plan stage of the talking-head pipeline. The stage hands on the scene plan. Stops for the person's approval.
- talking-head/script-directorHow the agent runs the script stage of the talking-head pipeline. The stage hands on the script. Stops for the person's approval.
- text-to-speechHeyGen's own voice model and catalog speech: voice discovery, timestamps, streaming.
- vercel-composition-patternsReact component composition patterns from Vercel. Front matter says MIT.
- vercel-react-best-practicesReact and Next.js performance guidelines from Vercel. Front matter says MIT.
- video-downloadDownloading video and audio from YouTube and other sites with yt-dlp.
- video-editEditing video locally with FFmpeg: trim, join, resize, speed, overlay, compress.
- video-toolkitMaking videos with a third-party Claude Code video toolkit: voiceovers, images, music, talking heads, Remotion rendering. A second copy…
- video-translateTranslating and dubbing a video into other languages through HeyGen.
- video-understandUnderstanding a video locally with FFmpeg frame samples and Whisper transcription.
- visual-styleCreating, extracting and applying a portable visual design system kept in one style file.
- web-design-guidelinesReviewing interface code against web interface guidelines.
Tools
- action_timeline_compilerCompiles a scene plan into a timed list of character actions and poses. Runs on the machine. Works with no keys.
- Asset cacheA cache keyed on a tool's inputs so a repeated paid generation call returns the saved file and is not paid for twice.
- atelier_snapshots.pyRenders one review still per scene of a hand-written composition so the board can show them.
- atlas_3dA 3D model from a text description, through Atlas Cloud. Calls an outside service; keys named in its code: ATLASCLOUD_API_KEY…
- atlas_imageImage generation and editing through Atlas Cloud (Seedream and others). Calls an outside service; keys named in its code…
- atlas_media_smoke.pyAn opt-in paid test run of the Atlas Cloud media tools.
- atlas_refresh_imageOpenAI and Google image models reached through Atlas Cloud. Calls an outside service; keys named in its code: ATLASCLOUD_API_KEY. Needs a…
- atlas_videoVideo generation through Atlas Cloud (Seedance and others). Calls an outside service; keys named in its code: ATLASCLOUD_API_KEY. Needs a…
- audio_energyMeasures how loud a track is over time to find the best point to start the music from, so a quiet intro can be skipped. Runs on the…
- audio_enhanceCleans up speech: noise reduction and loudness levelling with FFmpeg. Runs on the machine; needs ffmpeg. Works with no keys.
- audio_mixerMixes narration, music and effects into one track, with ducking under speech and fades. Runs on the machine; needs ffmpeg. Works with no…
- audio_probeReads the length and stream details of an audio or video file with ffprobe. Runs on the machine; needs ffprobe. Works with no keys.
- auto_reframeConverts a video to another shape, such as wide to tall, keeping the face in frame. Runs on the machine; needs ffmpeg. Works with no keys.
- azure_sttSpeech to text through Azure AI Speech, with word timings. Calls an outside service; keys named in its code: AZURE_SPEECH_KEY. Needs a key…
- azure_ttsText to speech through Azure AI Speech neural voices. Calls an outside service; keys named in its code: AZURE_SPEECH_KEY. Needs a key, a…
- BacklotA local web board that watches the projects folder and shows a production as it runs: stages, script, scene plan, generated assets as a…
- backlot_screenshot_stage.pyBuilds fictional projects and captures the board screenshots used in the README, with Playwright.
- backlot_simulate_run.pyFakes a pipeline run on disk so the Backlot board can be watched updating; useful as a demo of the board.
- backlot_visual_eval.pyA screenshot test for the board: captures fixed views and compares them with saved ones.
- backlot_watch_captures.pyCaptures a board screenshot each time a watched project changes.
- bfl_imageFLUX image generation direct from Black Forest Labs. Calls an outside service; keys named in its code: BFL_API_KEY. Needs a key, a program…
- bg_removeCuts the background out of an image with rembg. Routes to whatever provider is installed or keyed. Needs a key, a program or a download…
- bgm_montage_liteCuts supplied clips to the beat of one music track, through the separate BMTS-Lite program (itself AGPL-3.0-only, by another author). Runs…
- blender_worldAssembles and renders a 3D world in Blender from generated and licensed assets. Runs on your own GPU with model weights you download. Needs…
- bria_fal_imageBria image generation reached through fal.ai. Calls an outside service; keys named in its code: FAL_KEY. Needs a key, a program or a…
- bria_imageBria image generation and editing, direct. Calls an outside service; keys named in its code: BRIA_API_TOKEN. Needs a key, a program or a…
- bvh2clip and add-motionTwo Node scripts that turn a 3D BVH motion-capture file into one of the puppet's flat 2D clips (joint tracks per frame, scaled to a fixed…
- cap_recorderScreen recording through the Cap desktop app, with webcam overlay. Runs on the machine. Works with no keys.
- cartesia_ttsText to speech through Cartesia Sonic. Calls an outside service; keys named in its code: CARTESIA_API_KEY. Needs a key, a program or a…
- character_animation_reviewerChecks a character animation: rig integrity, motion and render readiness, as a report. Runs on the machine. Works with no keys.
- character_rig_rendererRenders a rigged character performance in a browser to frames and video. Runs on the machine. Works with no keys.
- character_spec_generatorTurns an approved character idea into a structured character design file. Runs on the machine. Works with no keys.
- Checkpoint storeWrites and reads a saved state after each stage so a run can resume, and refuses to record a gated stage as done without recorded approval.
- Clip corpusA project-local library of downloaded candidate clips with thumbnails and embeddings, queried offline; the heart of the documentary-montage…
- CLIP embedderA thin wrapper around OpenAI's CLIP ViT-B/32 model that turns images and text into vectors for matching footage to a description. Downloads…
- clip_searchSearches a local library of downloaded clips by meaning, using CLIP embeddings, to fill a described slot. Runs on the machine; needs numpy…
- code_snippetRenders a piece of source code as a highlighted image for an overlay. Runs on the machine; needs pygments, PIL. Needs a key, a program or a…
- cogvideo_videoLocal video generation with CogVideo. Runs on your own GPU with model weights you download. Needs a key, a program or a download before it…
- color_gradeApplies a color grade with FFmpeg filters or a LUT; named looks included. Runs on the machine; needs ffmpeg. Works with no keys.
- comfyui_imageImage generation through a ComfyUI server you run. Runs on your own GPU with model weights you download. Needs a key, a program or a…
- comfyui_musicMusic generation through a ComfyUI server you run. Runs on your own GPU with model weights you download. Needs a key, a program or a…
- comfyui_videoVideo generation through a ComfyUI server you run. Runs on your own GPU with model weights you download. Needs a key, a program or a…
- composition_validatorChecks a planned composition before rendering: catches audio and picture lengths that do not match and similar plan errors. Runs on the…
- Configuration modelLoads config.yaml (model provider, budget mode and caps, approval policy, output defaults) with environment overrides. Budget default is…
- corpus_builderFills a project's clip library: searches the stock and archive sources, downloads, makes thumbnails and indexes. Sources it can reach…
- Cost trackerBudget control: estimate before a call, reserve, record the real spend after; three modes (observe, warn, cap).
- Custom playbook generatorWrites a new schema-valid style playbook when none of the shipped ones fits a brief.
- dashscope_asrSpeech to text through Alibaba's DashScope, with word timings. Calls an outside service; keys named in its code: DASHSCOPE_API_KEY. Needs a…
- dashscope_imageImage generation through Alibaba's DashScope (Qwen Image). Calls an outside service; keys named in its code: DASHSCOPE_API_KEY. Needs a…
- dashscope_ttsText to speech through Alibaba's DashScope (Qwen voices), strong in Mandarin. Calls an outside service; keys named in its code…
- Delivery promiseClassifies what a video has promised to be (for example led by motion or led by stills) at proposal time and locks it, so the render cannot…
- diagram_genDraws a diagram from Mermaid text, with Graphviz or a plain drawing fallback. Runs on the machine. Works in part with no keys.
- direct_clip_searchSearches the same stock and archive sources directly and downloads chosen clips, without building a library first. Routes to whatever…
- doubao_ttsText to speech through Volcengine Doubao Speech, Mandarin first. Calls an outside service; keys named in its code: DOUBAO_SPEECH_API_KEY…
- elevenlabs_soundtrackA soundtrack written to a finished video by ElevenLabs, with stems. Calls an outside service; keys named in its code: ELEVENLABS_API_KEY…
- elevenlabs_ttsText to speech through ElevenLabs. Calls an outside service; keys named in its code: ELEVENLABS_API_KEY. Needs a key, a program or a…
- export_bundlePacks a finished render with its metadata into a folder ready to hand to any platform; it uploads nothing. Runs on the machine. Works with…
- eye_enhanceBrightens and sharpens eyes in talking-head footage. Runs on the machine; needs ffmpeg. Needs a key, a program or a download before it…
- face_enhanceLight face clean-up with FFmpeg filters. Runs on the machine; needs ffmpeg. Works with no keys.
- face_restoreRebuilds degraded faces with CodeFormer or GFPGAN. Runs on your own GPU with model weights you download; needs gfpgan, torch. Needs a key…
- face_trackerFinds and follows a face through footage with MediaPipe, for reframing and face effects. Runs on the machine; needs ffmpeg. Needs a key, a…
- fal_3dA 3D model from text or a picture, and object reconstruction, through fal.ai. Calls an outside service; keys named in its code…
- fal_elevenlabs_musicElevenLabs music generation reached through a fal.ai account. Calls an outside service; keys named in its code: FAL_AI_API_KEY, FAL_KEY…
- fal_elevenlabs_ttsElevenLabs speech reached through a fal.ai account. Calls an outside service; keys named in its code: FAL_AI_API_KEY, FAL_KEY. Needs a key…
- fish_audio_ttsText to speech through fish.audio, including cloned voices by reference. Calls an outside service; keys named in its code…
- flux3_fal_imageFLUX 3 image generation through fal.ai. Calls an outside service; keys named in its code: FAL_KEY. Needs a key, a program or a download…
- flux3_replicate_imageFLUX 3 image generation through Replicate. Calls an outside service; keys named in its code: REPLICATE_API_TOKEN. Needs a key, a program or…
- flux3_videoFLUX video generation through fal.ai. Calls an outside service; keys named in its code: FAL_KEY. Needs a key, a program or a download…
- flux_imageFLUX image generation through fal.ai. Calls an outside service; keys named in its code: FAL_AI_API_KEY. Needs a key, a program or a…
- frame_samplerPulls still frames out of a video with FFmpeg, at set times or intervals. Runs on the machine; needs ffmpeg. Works with no keys.
- freesound_musicSearches and downloads tracks from Freesound.org. Calls an outside service; keys named in its code: FREESOUND_API_KEY. Needs a key, a…
- gemini_fal_imageGoogle's image model reached through fal.ai, generation and editing. Calls an outside service; keys named in its code: FAL_KEY. Needs a…
- gemini_omni_falGoogle's Gemini Omni video model reached through fal.ai. Calls an outside service; keys named in its code: FAL_AI_API_KEY, FAL_KEY. Needs a…
- gemini_omni_videoGoogle's Gemini Omni video model: generates a clip and edits it by conversation. Calls an outside service; keys named in its code…
- gemini_replicate_imageGoogle's image model reached through Replicate. Calls an outside service; keys named in its code: REPLICATE_API_TOKEN. Needs a key, a…
- gemini_ttsText to speech through Google's Gemini speech models, including directed dialogue. Calls an outside service; keys named in its code…
- google_imagenGoogle Imagen image generation. Calls an outside service; keys named in its code: GEMINI_API_KEY, GOOGLE_API_KEY. Needs a key, a program or…
- google_musicMusic generation through Google Lyria. Calls an outside service; needs that service's key or sign-in (see the tool's own install note)…
- google_ttsText to speech through Google Cloud, hundreds of voices across many languages. Calls an outside service; keys named in its code…
- green_screen_compositePlaces keyed talking-head footage over a new background. Runs on the machine; needs ffmpeg, numpy, PIL. Works with no keys.
- green_screen_processorKeys out a green screen. Runs on the machine; needs ffmpeg. Works with no keys.
- grok_imagexAI Grok image generation and editing. Calls an outside service; keys named in its code: XAI_API_KEY. Needs a key, a program or a download…
- grok_ttsNarration through xAI's speech API. Calls an outside service; keys named in its code: XAI_API_KEY. Needs a key, a program or a download…
- grok_videoxAI Grok video generation with its own synchronized sound. Calls an outside service; keys named in its code: XAI_API_KEY. Needs a key, a…
- h3_max_videoThe H3 Max video model on fal.ai. Calls an outside service; keys named in its code: FAL_KEY. Needs a key, a program or a download before it…
- heygen_avatarA presenter video from a HeyGen digital twin. Calls an outside service; keys named in its code: HEYGEN_API_KEY. Needs a key, a program or a…
- heygen_catalog_ttsSpeech from HeyGen's catalog of voices. Calls an outside service; keys named in its code: HEYGEN_API_KEY. Needs a key, a program or a…
- heygen_ttsSpeech from HeyGen's own voice model, with voice discovery. Calls an outside service; keys named in its code: HEYGEN_API_KEY. Needs a key…
- heygen_videoVideo generation through HeyGen, which resells several video models under one key. Calls an outside service; keys named in its code…
- heygen_voice_convertChanges the voice of a recording to another voice while keeping its timing, through HeyGen. Calls an outside service; keys named in its…