Powered by OpenMontage

Describe the video. The studio produces it.

Creative Video Studio runs on OpenMontage, an open-source, agent-driven production system. Your AI coding assistant reads the pipeline, researches the topic, writes the script, plans scenes, generates assets, edits, composes the final cut, and stops at every creative gate for your approval.

Pipelines
12
Production-ready
6
Style playbooks
5
Approval gates
60

How a production runs

Every request goes through a pipeline. Before each stage the agent reads that stage's director skill, does the work with OpenMontage tools, self-reviews, and writes a checkpoint you can approve or send back.

  1. 1. Idea
  2. 2. Script
  3. 3. Scene Plan
  4. 4. Assets
  5. 5. Edit
  6. 6. Compose
  7. 7. Publish

Pipelines

Each pipeline is a YAML manifest plus stage director skills under openmontage/. Pick the one that matches the request; the agent drives it end to end.

production
AI-generated
Reference video
Animated Explainer
Generated explainer video from topic/idea - fully AI-produced with narration, visuals, and music. Features a research-first pre-production phase: the agent researches the topic, proposes concepts with cost estimates, and gets explicit user approval before any assets are generated.
  1. Research
  2. Proposal
  3. Script
  4. Scene Plan
  5. Assets
  6. Edit
  7. Compose
  8. Publish

8 stages · 5 approval gates · default budget $2.00

View pipeline
production
Animation
Reference video
Animation
Animation-first pipeline for motion graphics, diagram-led explainers, kinetic typography, math visuals, explicit Three.js worlds, and stylized illustrative sequences. Features a research-first pre-production phase: the agent researches the topic and animation techniques, proposes concepts with animation mode selection and cost estimates, and gets explicit user approval before any assets are generated.
  1. Research
  2. Proposal
  3. Script
  4. Scene Plan
  5. Assets
  6. Edit
  7. Compose
  8. Publish

8 stages · 5 approval gates · default budget $2.00

View pipeline
production
Specialized
Avatar Spokesperson
Presenter-led avatar pipeline for spokesperson videos, internal updates, onboarding, sales intros, and short scripted explainers. Best for projects where a digital presenter is the anchor and support graphics stay simple. EP orchestration adds quality gates for lip-sync quality, presenter framing, and CTA landing.
  1. Idea
  2. Script
  3. Scene Plan
  4. Assets
  5. Edit
  6. Compose
  7. Publish

7 stages · 5 approval gates · default budget $2.00

View pipeline
production
Cinematic
Reference video
Cinematic
Mood-led cinematic pipeline for trailers, brand films, montages, explicit 3D-world fly-throughs, and short-form dramatic edits. Works best with supplied footage, stills, or source media, and can optionally use generated support visuals for gap filling or concept-led inserts. EP orchestration adds quality gates for emotional pacing, color consistency, and audio dynamics.
  1. Research
  2. Proposal
  3. Script
  4. Scene Plan
  5. Assets
  6. Edit
  7. Compose
  8. Publish

8 stages · 5 approval gates · default budget $2.00

View pipeline
production
Hybrid
Hybrid
Hybrid pipeline for videos that combine source footage with designed or generated support assets: interviews plus diagrams, product footage plus overlays, screen recordings plus companion graphics, or montage edits with support inserts. EP orchestration adds quality gates for source/support balance, overlay density, and cross-medium coherence.
  1. Idea
  2. Script
  3. Scene Plan
  4. Assets
  5. Edit
  6. Compose
  7. Publish

7 stages · 5 approval gates · default budget $2.00

View pipeline
production
Screen recording
Screen Demo
Screen recording pipeline. Two production modes: 1. REAL CAPTURE — takes raw screen capture (app demo, browser walkthrough, coding tutorial) via screen_recorder, cap_recorder, or playwright-recording and produces a polished demo video with callouts, zoom crops, subtitles, and cleaned audio. 2. SYNTHETIC (Remotion TerminalScene) — for CLI/terminal/install-flow demos, renders a deterministic terminal animation with typed commands, scrolling output, floating command pills, and blinking cursor. See .agents/skills/synthetic-screen-recording/SKILL.md. Preferred when the demo content is predictable (install walkthroughs, make targets, git clone, API key config) because it's faster to iterate, privacy-safe, pixel-perfect, and frame-accurate to narration cues. The idea-director picks the mode at brief time based on whether the demo surface is a real app UI (real capture) or a scriptable terminal session (synthetic).
  1. Idea
  2. Script
  3. Scene Plan
  4. Assets
  5. Edit
  6. Compose
  7. Publish

7 stages · 5 approval gates · default budget $1.00

View pipeline
beta
Animation
Reference video
Character Animation
Character animation pipeline for local, reusable cartoon characters. It turns a script and scene plan into character specs, rig plans, pose libraries, action timelines, and browser-rendered SVG/Canvas/Remotion/HyperFrames animation. The pipeline is designed for deterministic local motion, not remote video-gen replacement.
  1. Research
  2. Proposal
  3. Script
  4. Character Design
  5. Rig Plan
  6. Scene Plan
  7. Assets
  8. Edit
  9. Compose
  10. Publish

10 stages · 6 approval gates · default budget $2.00

View pipeline
beta
Specialized
Clip Factory
Multi-clip extraction pipeline. Takes long-form content (webinar, stream, presentation, interview) and produces multiple short clips optimized for social distribution. Outputs N independent deliverables from a single source. EP orchestration adds quality gates for clip selection, batch consistency, and hook placement.
  1. Idea
  2. Script
  3. Scene Plan
  4. Assets
  5. Edit
  6. Compose
  7. Publish

7 stages · 5 approval gates · default budget $1.00

View pipeline
beta
Documentary
Documentary Montage
Retrieval-first thematic montage pipeline. Builds a semantic corpus of real-world footage from Pexels, Archive.org (Prelinger et al.), NASA, Wikimedia Commons, and Unsplash, then uses CLIP-based retrieval to fill slot descriptions from a thematic brief. The edit arranges clips by narrative beat with music sync and uniform color grade across mixed-era footage. Inspired by Adam Curtis / Chris Marker / Errol Morris tone poems.
  1. Idea
  2. Scene Plan
  3. Assets
  4. Edit
  5. Compose

5 stages · 4 approval gates · default budget $1.00

View pipeline
beta
Specialized
Localization Dub
Transcript-first localization pipeline for producing translated subtitles, dubbed audio, and optional lip-synced language variants from an existing source video. EP orchestration adds quality gates for translation accuracy, timing preservation, and per-locale consistency.
  1. Idea
  2. Script
  3. Scene Plan
  4. Assets
  5. Edit
  6. Compose
  7. Publish

7 stages · 5 approval gates · default budget $3.00

View pipeline
beta
Specialized
Podcast Repurpose
Podcast-to-video repurposing pipeline. Takes podcast audio (or video podcast) and produces visual content: audiogram or caption-led clips, quote-led social assets, and optional full-episode companion video when the source and asset budget support it. EP orchestration adds quality gates for audio preservation, clip selection, and multi-deliverable consistency.
  1. Idea
  2. Script
  3. Scene Plan
  4. Assets
  5. Edit
  6. Compose
  7. Publish

7 stages · 5 approval gates · default budget $1.00

View pipeline
beta
Talking head
Talking Head
End-to-end talking-head video pipeline. Takes raw footage of a person speaking, transcribes it, makes edit decisions, generates subtitles, mixes audio, and composes the final output.
  1. Idea
  2. Script
  3. Scene Plan
  4. Assets
  5. Edit
  6. Compose
  7. Publish

7 stages · 5 approval gates · default budget $0.50

View pipeline

Style playbooks

A playbook fixes the visual language for a production: palette, typography, motion, and audio rules. Pipelines recommend the playbooks they work best with.

Anime Ghibli
warm, whimsical, contemplative, magical · slow pace

Best for: Narrative animations, nature-themed stories, emotional storytelling, fantasy visuals, educational content with wonder

Noto Serif JP · Noto Sans

anime-ghibli

Clean Professional
polished, trustworthy, clear · moderate pace

Best for: Corporate explainers, educational content, SaaS demos, conference talks

Inter

clean-professional

Flat Motion Graphics
energetic, modern, bold · fast pace

Best for: Social media explainers, TikTok/Reels, product launches, startup pitches

Space Grotesk

flat-motion-graphics

Minimalist Diagram
focused, technical, precise · deliberate pace

Best for: Technical deep-dives, architecture explainers, math/CS concepts, documentation videos

IBM Plex Sans

minimalist-diagram

Premium Minimalist
calm, editorial, precise · deliberate pace

Best for: Investor updates, expert explainers, product narratives, high-trust launch videos

Inter

premium-minimalist

Get started

The engine runs locally next to this app. Set it up once, then drive it from your AI coding assistant.

1. Set up the engine
Needs Python 3.10+, Node.js 18+, and FFmpeg. Everything else is installed for you.
cd openmontage
make setup   # Python venv, Remotion composer, Piper TTS, HyperFrames
make demo    # render the zero-key demo videos — no API keys needed

Add provider keys to openmontage/.env to unlock cloud image, video, voice, and music models. The free local paths (stock footage, Piper voices, Remotion and HyperFrames composition) work without any.

2. Make a video
Open this repository in Claude Code, Cursor, Codex, Copilot, or Windsurf and describe what you want.
"Make a 60-second animated explainer about how neural networks learn"
"Here's a YouTube Short I love — make something like it about quantum computing"
"Cut this webinar recording into five vertical clips for TikTok"

The agent reads openmontage/AGENT_GUIDE.md, picks a pipeline, runs preflight to discover your available tools, and opens the Backlot board so you can watch the production and approve each gate.