Open-Source AI Video Studio

Turn Your Ideas into Fully Rendered Videos

A team of 9 specialized AI agents collaborates to write scripts, create storyboards, generate voiceovers, compose background music, and render complete videos from a single sentence prompt.

AI_STUDIO_V1.0.0
"Create a high-octane cyberpunk video featuring neon streets, a rainy night, cinematic synthetic score, and a narrative around a rogue detective."
Script AgentCOMPLETE
Art Style NodeCyberpunk Neon
BGM NodeSynthwave Track
Status: Rendered
Watch Render Output

Demo: A cyberpunk detective story generated entirely by AI — from script to final render in minutes. The video showcases OpenDirector's 9-agent pipeline producing cinematic visuals, character art, voiceover narration, and original background music from a single text prompt.

Demo Video Walkthrough

See how OpenDirector transforms a single sentence into a complete cinematic video through its 9-agent pipeline.

0:00

Prompt Input

The user enters a single sentence: a cyberpunk detective story set in a neon-lit city. OpenDirector's Research Agent immediately begins gathering background information on cyberpunk aesthetics, noir storytelling tropes, and visual references.

0:10

Script Generation

The Script Agent writes a complete narrative with three-act structure, dialogue, scene descriptions, and pacing notes. It adapts the story for short-form video format with dramatic beats and a satisfying conclusion.

0:20

Art Direction

The Art Style Agent selects from 34 built-in styles across 9 categories, applying cyberpunk genre conventions. The Storyboard Agent then plans each shot using cinematic principles — rule of thirds, leading lines, and camera angles with metadata for image generation.

0:30

Character & Location Design

The Character Agent generates detailed character sheets with consistent visual identity across scenes, including expression variations and style embeddings. The Location Agent creates atmospheric interior and exterior environments with depth layers for parallax effects.

0:40

Voice & Music

The Voice Agent produces natural narration using TTS providers (Edge, OpenAI, or custom voices) with SSML markup for pacing control. The BGM Agent composes background music matched to the story's mood, with crossfading and sound effects layering.

0:50

Final Render

The Media Agent assembles all assets — character images, backgrounds, voiceover, music, and subtitles — into a fully rendered video using FFCreator. It handles image composition, subtitle overlay, audio synchronization, and encoding to the target resolution up to 1080p.

The entire process from prompt to final video takes just minutes, with manual editing available at every stage in Creative Mode.

What is OpenDirector?

OpenDirector is an open-source AI video production platform that uses 9 specialized AI agents to automate the entire video creation pipeline. Built on LangGraph for agent orchestration, Next.js for the web interface, and FFCreator for video rendering, it transforms a single sentence prompt into a fully produced video — complete with script, storyboard, character designs, location art, voiceover, background music, and final render. The platform offers two production modes: Creative Mode for interactive, high-end cinematic outputs with manual editing at every stage, and Batch Mode for automated bulk generation of short-form videos. It ships with 34 built-in art styles across 9 categories, supports 16:9, 9:16, and 1:1 aspect ratios, and exports up to 1080p Full HD. As a Docker-first, self-hosted solution, all data stays on the user's local machine, ensuring complete privacy. The project is MIT-licensed and maintained by seme-org on GitHub.

Dual Production Engines

Choose between customized interactive creation and automated bulk video generation.

AI Director Full Workflow

Creative Mode

Auto-generates a complete plan: brief, story, storyboard, voiceover, plates, and BGM from one sentence. Keep full creative control with inline manual editing.

  • Interactive storyboard preview with audio sync
  • 34 built-in art styles across 9 categories
  • Multiple TTS voice options with real-time preview
  • Supports 16:9 cinematic, 9:16 portrait, and 1:1 square layouts
  • Export resolutions up to 1080p Full HD
Full Control / Real-time Editing / Custom Plates
Mass Video Production

Batch Mode

Designed for bulk production of short videos. Input topics, and the AI automatically writes multiple scripts, retrieves stock footage, and generates high-converting clips.

  • Topic-to-video batch generation engine
  • Customizable clip duration & transition pacing
  • Subtitle overlay with custom fonts, colors, and positioning
  • Royalty-free HD footages from Pexels & Pixabay
  • Generate multiple variants at once to select the best
Mass Production / Stock Integration / Configurable Transition

Self-Host with One Command

OpenDirector is Docker-first. Keep your transcripts, files, and assets completely private on your local machine.

1

Clone repository

Terminal step 1
2

Configure API credentials in env file

Terminal step 2
3

Boot up MySQL, Redis, MinIO, and App

Terminal step 3
4

Open in browser to start creating

Terminal step 4
self_host_setup.sh
git clone https://github.com/seme-org/open-director.git
cd open-director
cp .env.example .env
# Edit .env and enter your WAVESPEED_API_KEY and OPENAI_API_KEY
docker compose up -d --build
# Open http://localhost:3000 in your browser
FAQ

Frequently Asked Questions

Everything you need to know about OpenDirector.

What is OpenDirector?
OpenDirector is an open-source AI video production platform where 9 specialized AI agents collaborate to produce complete videos from a single sentence prompt. Built on LangGraph for orchestration, Next.js for the frontend, and FFCreator for rendering, it automates the entire pipeline — from scriptwriting and storyboarding to voiceover, background music, and final video render. It supports both interactive creative mode and automated batch production.
How does OpenDirector work?
OpenDirector uses a 9-agent pipeline orchestrated by LangGraph. The Research Agent gathers context, the Script Agent writes the narrative, the Art Style Agent selects from 34 visual styles, the Storyboard Agent plans shots, Character and Location Agents design visuals, the Voice Agent generates voiceovers, the BGM Agent composes music, and the Media Agent renders the final video. Each agent communicates through a state graph, allowing real-time collaboration and manual override at any stage.
Is OpenDirector free?
Yes, OpenDirector is completely free and open-source under the MIT license. You can use it for personal and commercial projects. The only costs are for the AI API keys you configure (such as OpenAI, Anthropic, or other LLM providers) and any TTS or image generation services you connect.
How do I deploy OpenDirector?
OpenDirector is Docker-first. Clone the GitHub repository, configure your API credentials in the .env file, then run docker compose up to boot MySQL, Redis, MinIO, and the app. Open your browser to start creating. The entire setup takes about 5 minutes on any machine with Docker installed.
What video formats and aspect ratios does OpenDirector support?
OpenDirector supports three aspect ratios: 16:9 cinematic widescreen, 9:16 vertical portrait, and 1:1 square format. Videos can be exported at up to 1080p Full HD resolution. The platform includes 34 built-in art styles across 9 categories, from cinematic and anime to watercolor and neon noir.
Is my data private with OpenDirector?
Yes. Since OpenDirector is self-hosted via Docker, all your scripts, voiceovers, character designs, and rendered videos stay on your local machine. Nothing is uploaded to third-party servers. The only external calls are to the AI APIs you explicitly configure for generation tasks.