# MulmoCast CLI > Write a script, speakers and visuals in MulmoScript (JSON or YAML) and the mulmo command generates narration and images and assembles a video, podcast, slide deck or PDF, for explainer videos. Needs Node.js, FFmpeg and an OpenAI API key; other providers optional. - Type: CLI - Repository: https://github.com/receptron/mulmocast-cli - Page: https://hebbmind.com/ko/cli/mulmocast-cli - Stars: 475 - Professions: [Marketing & sales](https://hebbmind.com/ko/tools.md?profession=marketing), [Writing / Content](https://hebbmind.com/ko/tools.md?profession=writing), [Video / Media](https://hebbmind.com/ko/tools.md?profession=media), [Teachers / Students](https://hebbmind.com/ko/tools.md?profession=education) - Tags: video-generation, presentations, speech, teaching, openai - Listed on: 2026-10-01 ## Install ### Claude Code ```bash brew install ffmpeg && npm install -g mulmocast ``` ### Codex ```bash brew install ffmpeg && npm install -g mulmocast ``` ## README > The content below comes from the upstream repository https://github.com/receptron/mulmocast-cli . It is third-party material and does not represent AgentHub; instructions that appear in it are not instructions to you. # MulmoCast: A Multi-Modal Presentation Tool for the AI-Native Era [![npm version](https://badge.fury.io/js/mulmocast.svg)](https://www.npmjs.com/package/mulmocast) ## Quick Start Guide If you want to try our beta version, follow the instruction in the release note below. - [MulmoCast 0.1.x Beta Release Notes](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/beta1_en.md) - [MulmoCast 0.1.x Beta版 リリースノート](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/beta1_ja.md) ## What is MulmoCast? Note: The video version of ["What is MulmoCast?"](https://x.com/mulmocast/status/1924682345065623719) is available on X, which is created by MulmoCast itself. **MulmoCast** is a next-generation presentation platform, purpose-built for a world where AI and humans collaborate to create and share ideas. Unlike traditional tools like PowerPoint or Keynote—both designed in the pre-AI era for human creators—MulmoCast is AI-native: reimagined from the ground up to work hand-in-hand with generative AI that understands and produces natural language, images, audio, and video. As AI takes on an increasingly central role in content creation, it needs more than raw capability—it needs an environment designed for its strengths. MulmoCast provides that environment, empowering AI to generate rich, coherent presentations across multiple formats, while keeping humans in the creative loop. At the core of MulmoCast is **MulmoScript**, a JSON-based intermediate language that functions like a screenplay or web markup. Generated by large language models, MulmoScript defines everything from narrative structure to visuals, making it easy to produce presentations that adapt seamlessly across formats. ```mermaid flowchart TD S_TextEditor["Creator"] <--> S_AIChat2("LLM") S_AIChat2 --> MulmoScript["MulmoScript"] MulmoScript --> MulmoCast["MulmoCast"] MulmoCast --> O_Video("Video") & O_Podcast("Podcast") & O_Slideshow("Slideshow") & O_PDF("PDF") & O_Manga("Manga") & O_SwipeAnime("Swipe Anime") MulmoScript@{ shape: div-proc} MulmoCast@{ shape: trap-t} S_TextEditor:::StoryInput S_AIChat2:::ScriptInput O_Video:::ScriptOutput O_Podcast:::ScriptOutput O_Slideshow:::ScriptOutput O_PDF:::ScriptOutput O_Manga:::ScriptOutput O_SwipeAnime:::ScriptOutput classDef StoryInput stroke-width:1px, stroke-dasharray:none, stroke:#46EDC8, fill:#DEFFF8, color:#378E7A classDef ScriptInput stroke-width:1px, stroke-dasharray:none, stroke:#374D7C, fill:#E2EBFF, color:#374D7C classDef ScriptOutput stroke-width:1px, stroke-dasharray:none, stroke:#FBB35A, fill:#FFEFDB, color:#8F632D ``` In today’s world, people consume information through many channels—on Zoom calls, in Slack threads, via videos on the go, or through podcasts during commutes. Presentations can no longer be confined to a single format or device. That’s why MulmoCast is built to be truly multi-modal, enabling output not only as slide decks but also as videos, podcasts, manga-style comics, and PDF documents. Whether you're building a podcast from a research report or turning a business pitch into a narrated video, MulmoCast transforms source material into dynamic, multi-format content with the help of state-of-the-art AI like ChatGPT and Claude. MulmoCast isn't just a tool. It’s a new foundation for communication—one where humans and AI co-create across every mode of expression. ## MulmoScript **MulmoScript** is a simple JSON/YAML format for describing multi-modal content. You can define speakers, text, images, and layout — all in one script. Here is the "Hello World" in MulmoScript. ```JSON { "$mulmocast": { "version": "1.1" }, "beats": [ { "text": "Hello World" } ] } ``` See [MulmoScript Format](#mulmoscript-format) for details on the structure. ## Installation ```bash npm install -g mulmocast ``` You'll also need to install ffmpeg: ```bash # For macOS with Homebrew brew install ffmpeg # For other platforms # Visit https://ffmpeg.org/download.html ``` You can also use [`Dockerfile`](./Dockerfile) which helps you install the pre-requisits. ``` docker build -t mulmo-cli . ``` You can use the Docker image like this: ``` docker run -e OPENAI_API_KEY= -it mulmo-cli mulmo tool scripting -i -t children_book -o ./ -s story ``` ## Configuration Create a `.env` file in your project directory with the following API keys: ### Required ```bash OPENAI_API_KEY=your_openai_api_key ``` #### (Optional) For Google's image and TTS. ```bash GEMINI_API_KEY=your_google_gemini_api_key ``` #### (Optional) For AI providers ```bash # For Anthropic Claude (htmlPrompt feature) ANTHROPIC_API_TOKEN=your_anthropic_api_token ``` For htmlPrompt configuration, see [docs/image.md](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/image.md#2-htmlprompt). #### (Optional) For Movie models ```bash REPLICATE_API_TOKEN=your_replicate_api_key ``` #### (Optional) For TTS models ```bash # For ElevenLabs TTS ELEVENLABS_API_KEY=your_elevenlabs_api_key ``` #### (Optional) to access web in mulmo tool ```bash BROWSERLESS_API_TOKEN=your_browserless_api_token # to access web in mulmo tool ``` #### (Optional) Local usage tracking ```bash MULMOCAST_DUMP_USAGE=1 # print JSON usage dump to stdout after each CLI action MULMOCAST_DUMP_USAGE=/tmp/usage.json # ...or write it to a file ``` Token / per-second / per-char usage per provider:model. See [docs/api.md](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/api.md#usage-tracking) for the full reference. ### Google Vertex AI For enterprise/production environments, or to use Veo movie models that are only available on Vertex AI, use Vertex AI with Application Default Credentials (ADC): ```bash # Install gcloud CLI and authenticate gcloud auth application-default login ``` Configure in MulmoScript: ```json { "imageParams": { "provider": "google", "model": "gemini-2.5-flash-image", "vertexai_project": "your-project-id", "vertexai_location": "us-central1" } } ``` | Parameter | Description | Default | | ------------------- | ----------------------- | -------------------------------------- | | `vertexai_project` | Google Cloud Project ID | None (enables Vertex AI mode when set) | | `vertexai_location` | Region | `us-central1` | For detailed setup instructions, see [Vertex AI Setup Guide](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/vertexai_en.md). ### Azure OpenAI To use Azure OpenAI instead of OpenAI API: ```bash # For image generation IMAGE_OPENAI_API_KEY= IMAGE_OPENAI_BASE_URL=https://.openai.azure.com/ # For TTS (Text-to-Speech) TTS_OPENAI_API_KEY= TTS_OPENAI_BASE_URL=https://.openai.azure.com/ # For LLM (translate, scripting) LLM_OPENAI_API_KEY= LLM_OPENAI_BASE_URL=https://.openai.azure.com/ LLM_OPENAI_API_VERSION=2025-04-01-preview # optional ``` MulmoScript configuration (same as OpenAI): ```json { "imageParams": { "provider": "openai", "model": "gpt-image-1.5" }, "speechParams": { "speakers": { "Presenter": { "provider": "openai", "voiceId": "alloy", "model": "tts" } } } } ``` **Important**: Azure deployment names must match model names exactly (e.g., deployment name `gpt-image-1.5` for model `gpt-image-1.5`). For detailed setup and region availability, see [Azure OpenAI Usage Guide](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/azure_openai_usage.md). ### mulmo.config.json Create a `mulmo.config.json` file to set project-wide defaults. The CLI searches for it in **CWD** first, then **home directory (`~/`)**. ```json { "speechParams": { "provider": "elevenlabs" }, "imageParams": { "provider": "google" }, "audioParams": { "bgm": { "kind": "path", "path": "assets/bgm.mp3" }, "bgmVolume": 0.15 } } ``` Top-level keys are applied as **defaults** (script values take precedence). Use the `override` key to **force** values over scripts — useful for enterprise branding or TTS provider enforcement: ```json { "speechParams": { "provider": "elevenlabs" }, "override": { "speechParams": { "provider": "elevenlabs", "model": "eleven_multilingual_v2", "speakers": { "Presenter": { "provider": "elevenlabs", "voiceId": "Rachel" } } } } } ``` Priority chain: `config (defaults)` < `template/style` < `script` < `config.override` < `presentationStyle (-p)` > **Note**: `kind: "path"` entries in `mulmo.config.json` are resolved relative to the **script file directory**, not the config file location. This is consistent with all other path resolution in MulmoScript. Verify the merged result with: ```bash mulmo tool info merged --script ``` ## Workflow 1. Create a MulmoScript JSON file with `mulmo tool scripting` 2. Generate audio with `mulmo audio` 3. Generate images with `mulmo images` 4. Create final video with `mulmo movie` ## Quick Start ### Step 1: Generate a MulmoScript with interactive mode - Step 1-1: Run the script generation command ```bash mulmo tool scripting -i -t children_book -o ./ -s story ``` This will initiate the script creation process. - Step 1-2: Interactive conversation with AI After running the command, you'll engage in an interactive conversation with the AI to create your story script. The AI will guide you through the process and help shape your content based on your inputs. Once completed, a JSON file (like ⁠`story-1746600802426.json`) will be generated. ### Step 2: Generate both audio and images, then combine into video ```bash mulmo movie {generated_script_file} ``` Replace `{generated_script_file}` with the output file from STEP 1, such as `story-1746600802426.json`. Optionally, you can specify _\__clipboard_ as the script file name to paste the script from the clipboard, which is generated by other interactive environment such as ChatGPT or Claude. ## Quick Start for Ghibli-Style Animation [![Watch Ghibli-Style Animation Example](https://github.com/receptron/mulmocast-cli/blob/main/docs/images/introducing-mulmocast-new-era-presentations-thumbnail.jpg?raw=true)](https://www.youtube.com/watch?v=gz_Oe5p2n3s) _Click the image above to watch an example of what you can create_ ### Step 1: Check/Update Environment Setup Verify your `.env` file contains: ```bash OPENAI_API_KEY=your_openai_api_key ``` > **Note:** Ensure your OpenAI organization is verified to access the GPT Image models. Visit https://platform.openai.com/settings/organization/general and complete the "Verifications" section. ### Step 2: Generate a Ghibli-style MulmoScript ```bash mulmo tool scripting -i -t ghibli_comic -o ./ -s story ``` This will initiate an interactive conversation with the AI to create your Ghibli-inspired story. Once completed, a JSON file (e.g., `story-1747834931950.json`) will be generated. ### Step 3: Translate the MulmoScript ```bash mulmo translate {generated_script_file_from_step_2} ``` ### Step 4: Generate video with Japanese subtitles ```bash mulmo movie {generated_script_file_from_step_2} -c ja ``` The `-c ja` flag adds Japanese subtitles to your video. When the process completes, the CLI will display the path to your generated video file: ```bash Video created successfully! 14.939 sec writing: /Users/username/path/to/output/story-1747834931950__ja.mp4 ``` ## Generate MulmoScript ```bash # Generate script from web content (requires Browserless API KEY) mulmo tool scripting -u https://example.com # Generate script from local file mulmo tool scripting --input-file story.txt # Generate script with interactive mode mulmo tool scripting -i ``` Note: - When -i is specified, --input-file value will be ignored - When --input-file is specified, -u value will be ignored ### Complete MulmoScript from minimal beats You can create a minimal JSON with just beats and complete it with `mulmo tool complete`: ```json { "beats": [{ "text": "Hello, welcome to MulmoCast!" }, { "text": "This is a simple example." }] } ``` Save this as `my_beats.json`, then complete it with a style: ```bash # Complete with built-in style mulmo tool complete my_beats.json -s ani # Complete with custom style file mulmo tool complete my_beats.json -s ./my_style.json # Output to specific file mulmo tool complete my_beats.json -s ani -o my_script.json ``` This generates a complete MulmoScript with all required fields (canvasSize, speechParams, imageParams, etc.) from the style. ## Generate content from MulmoScript Mulmo provides several commands to handle different aspects of content creation: ```bash # Generate audio from script mulmo audio script.json # Generate images for script mulmo images script.json # Generate both audio and images, then combine into video mulmo movie script.json # Translate script to Japanese mulmo translate script.json ``` ### Usage tracking (token / character / predict-second per provider:model) Any of the commands above can dump a JSON breakdown of upstream AI consumption when `MULMOCAST_DUMP_USAGE` is set: ```bash # print JSON to stdout (pipe-friendly: `... | jq .`) MULMOCAST_DUMP_USAGE=1 mulmo audio script.json # ...or write it to a file MULMOCAST_DUMP_USAGE=/tmp/usage.json mulmo movie script.json ``` Payload shape: ```json { "records": 3, "byModel": [ { "provider": "openai", "model": "gpt-4o-mini-tts", "records": 1, "inputChars": 20 }, { "provider": "gemini", "model": "gemini-3.8-flash-tts", "records": 1, "inputTokens": 9, "outputTokens": 59, "totalTokens": 68 }, { "provider": "elevenlabs", "model": "eleven_multilingual_v2", "records": 1, "inputChars": 18 } ], "snapshot": [/* per-call UsageRecord[] */] } ``` `byModel` groups by `provider:model` (different models have different rate cards, so summing across them isn't meaningful). The full per-call snapshot is also included so a billing layer can apply its own grouping. See [docs/api.md § Usage tracking](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/api.md#usage-tracking) for the per-agent field-population matrix and the programmatic (library) API. ### Usage estimation (before running anything) Every generation command accepts `--estimate`: it prints what the command would consume — scoped to that command's pipeline — and exits without generating: ```bash mulmo movie script.json --estimate # table per provider:model + total cost mulmo audio script.json --estimate --json # raw UsageEstimate[] records (pipe-friendly) ``` `mulmo audio --estimate` covers TTS (plus translation when `-l` differs from the script language); `mulmo images` / `mulmo pdf` cover image, htmlImage, movie, sound-effect, lip-sync and reference-media generation; `mulmo movie` covers everything; `mulmo translate` only translation. Values marked `~` are heuristic estimates; unmarked values are exact for the given script. The library API can estimate the same thing — per beat, per process — without calling any API: ```typescript import { estimateUsage } from "mulmocast"; const estimates = estimateUsage(script, { targetLangs: ["ja"] }); // [{ process: "tts", beatIndex: 0, provider: "openai", model: "gpt-4o-mini-tts", // inputChars: { value: 50, precision: "exact" }, outputTokens: { value: 150, precision: "estimated" }, // costUSD: 0.0019, pricingAsOf: "2026-07-03" }, ...] ``` Each metric carries a `precision` flag: `"exact"` for values that are deterministic from the script (TTS character counts, tokenized OpenAI prompts, fixed image-output token tables) and `"estimated"` for heuristics (LLM output length, speech duration derived from text). `costUSD` appears when pricing data exists in `modelPricing` (`src/types/provider2agent.ts`), where every price records the date it was last verified. See [docs/api.md § Pre-run estimation](https://github.com/receptron/mulmocast-cli/blob/HEAD/docs/api.md#pre-run-estimation-estimateusage). ### Strict network mode (scripts you did not write) HTML-based beats (`html_tailwind`, `markdown`, `textSlide`, `chart`, `mermaid`, `slide`, captions, HTML prompts) and PDF output are rendered in a headless browser that normally has full network access. For a script from an untrusted source, add `--strict-network` (or set `MULMO_STRICT_NETWORK=1`; library callers set `context.strictNetwork`): ```bash mulmo images untrusted.json --strict-network ``` The renderer may then load only files in the script's folder and mulmocast's output folders, `data:` / `blob:` URLs, and the CDNs mulmocast's own templates use (`cdn.tailwindcss.com`, `fonts.googleapis.com`, `fonts.gstatic.com`, and on `cdn.jsdelivr.net` only the mermaid and Chart.js files the templates load). Anything else — other local files, remote images in the script, `fetch`, WebSockets, WebRTC, popups, preconnect hints — is blocked, and each blocked request is logged (`strict network: blocked …`). Files next to the script in the same folder remain readable, so keep an untrusted script in a folder of its own (a script loaded by URL gets the output folders only). Requests to the allowed CDNs still reach those providers, so treat what a page sends there as visible to them. Strict mode guards what the browser loads; files the script names with `kind: "path"` (images, movies, logos, mermaid or remotion code) are read by mulmocast itself and are not restricted yet ([#1622](https://github.com/receptron/mulmocast-cli/issues/1622)). Remotion beats are always guarded this way. The `vision` beat renders in its own browser inside `mulmocast-vision`, which the guard cannot reach, so in strict mode a `vision` beat stops with an error instead of rendering unguarded. ## Cache and Re-run When running the same `mulmo` command multiple times, previously generated files are treated as cache. For example, audio or image files will not be regenerated if they already exist. To force regeneration, delete the old files — including temporary files — under the output directory before re-running the command or use -f (force) option. If you modify the text or instruction fields in a MulmoScript, mulmo will automatically detect the changes and regenerate the corresponding audio content upon re-run. ## Slide Presentations MulmoCast includes a powerful **Slide DSL** (`type: "slide"`) for creating structured presentation slides with JSON. Slides are rendered via Tailwind CSS + Puppeteer into images. ### Features - **12 Layouts**: title, columns, comparison, grid, bigQuote, stats, timeline, split, matrix, table, funnel, waterfall - **10 Content Block Types**: text, bullets, code, callout, metric, divider, image, imageRef, chart, mermaid - **Chart.js Plugins**: sankey (`chartjs-chart-sankey`) and treemap (`chartjs-chart-treemap`) auto-loaded by chart type - **13-Color Theme System**: Semantic color palette with dark/light support - **6 Preset Themes**: dark, pop, warm, creative, minimal, corporate ### Usage Set a theme once with `slideParams.theme`, then use `"type": "slide"` in each beat: ```json { "$mulmocast": { "version": "1.1" }, "slideParams": { "theme": { "colors": { "bg": "0F172A", "bgCard": "1E293B", "bgCardAlt": "334155", "text": "F8FAFC", "textMuted": "CBD5E1", "textDim": "64748B", "primary": "3B82F6", "accent": "8B5CF6", "success": "22C55E", "warning": "F59E0B", "danger": "EF4444", "info": "14B8A6", "highlight": "EC4899" }, "fonts": { "title": "Georgia", "body": "Calibri", "mono": "Consolas" } } }, "beats": [ { "text": "Welcome to the presentation", "image": { "type": "slide", "slide": { "layout": "title", "title": "Main Title", "subtitle": "Subtitle" } } } ] } ``` Or use a preset presentation style: ```bash mulmo tool complete beats.json -s slide_dark -o presentation.json ``` Available preset styles: `slide_dark`, `slide_pop`, `slide_warm`, `slide_creative`, `slide_minimal`, `slide_corporate` For detailed layout specifications and content block reference, see the [Slide DSL documentation](https://github.com/receptron/mulmocast-cli/blob/HEAD/.claude/skills/slide/SKILL.md). ## Markdown Slide Styles MulmoCast includes 100 pre-designed CSS styles for markdown slides, organized in 10 categories: | Category | Description | Example Styles | | ---------- | ------------------------------- | --------------------------------------------- | | business | Professional corporate designs | corporate-blue, executive-gray, finance-green | | tech | Technology and developer themes | cyber-neon, matrix-green, terminal-dark | | creative | Artistic and expressive styles | artistic-splash, watercolor-soft, graffiti | | minimalist | Clean and simple designs | clean-white, zen-beige, nordic-light | | nature | Nature-inspired themes | forest-green, ocean-blue, sunset-orange | | dark | Dark mode and elegant themes | charcoal-elegant, midnight-blue, obsidian | | colorful | Vibrant and bold colors | vibrant-pink, candy-colors, aurora | | vintage | Retro and classic styles | retro-70s, art-deco, typewriter | | japanese | Japanese aesthetic designs | washi-paper, sakura-pink, zen-garden | | geometric | Pattern-based designs | hexagon-pattern, isometric, bauhaus | ### Usage Add the `style` property to a markdown beat: ```json { "beats": [ { "text": "Corporate presentation slide", "image": { "type": "markdown", "markdown": "# Quarterly Report\n\n## Key Highlights\n\n- Revenue up 15%\n- New market expansion\n- Team growth", "style": "corporate-blue" } } ] } ``` ### Discover Available Styles Use the `mulmo tool info` command to see all available styles: ```bash mulmo tool info styles ``` ## MulmoScript Format MulmoScript is a JSON format to define podcast or video scripts: Schema definition: [schema.ts](https://github.com/receptron/mulmocast-cli/blob/HEAD/src/types/schema.ts) ## Sample MulmoScript https://github.com/receptron/mulmocast-cli/tree/main/scripts ## Directory Structure | Directory | Description | | ---------------- | ----------------------------------------------------------------------- | | `output/` | Artifacts generated by commands — e.g., `.json`, audio, and video files | | `output/audio/` | Temporary audio fragments used in the final audio assembly | | `output/images/` | Image files generated by the `images` command | | `output/cache/` | Internal cache files for various processing steps | > These directories are automatically created as needed by the `mulmo` commands. ## Help CLI Usage ``` mulmo [options] Commands: mulmo translate Translate Mulmo script mulmo audio Generate audio files mulmo images Generate image files mulmo movie Generate movie file mulmo pdf Generate PDF files mulmo markdown Generate markdown files mulmo bundle Generate bundle files mulmo html Generate html files mulmo tool Generate Mulmo script and other tools Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] ``` ``` mulmo translate Translate Mulmo script Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] ``` ``` mulmo audio Generate audio files Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] -a, --audiodir Audio output directory [string] ``` ``` mulmo images Generate image files Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] -i, --imagedir Image output directory [string] ``` ``` mulmo movie Generate movie file Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] -a, --audiodir Audio output directory [string] -i, --imagedir Image output directory [string] -c, --caption Video captions [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] ``` ``` mulmo pdf Generate PDF files Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] -i, --imagedir Image output directory [string] --pdf_mode PDF mode [string] [choices: "slide", "talk", "handout"] [default: "slide"] --pdf_size PDF paper size (default: letter) [choices: "letter", "a4"] [default: "letter"] ``` ``` mulmo markdown Generate markdown files Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] --image_width Image width (e.g., 400px, 50%, auto) [string] ``` ``` mulmo html Generate html files Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] --image_width Image width (e.g., 400px, 50%, auto) [string] ``` ``` mulmo bundle Generate bundle files Positionals: file Mulmo Script File [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -l, --lang target language [string] [choices: "en", "ja", "fr", "es", "de", "zh-CN", "zh-TW", "ko", "it", "pt", "ar", "hi"] -f, --force Force regenerate [boolean] [default: false] -g, --grouped Output all files under output// directory [boolean] [default: false] --backup create backup media file [boolean] [default: false] --strict-network Let HTML renderers reach only local files and the CDNs mulmocast's templates use (also MULMO_STRICT_NETWORK=1) [boolean] [default: false] -p, --presentationStyle Presentation Style [string] ``` ``` mulmo tool Generate Mulmo script and other tools Commands: mulmo tool scripting Generate mulmocast script mulmo tool prompt Dump prompt from template mulmo tool schema Dump mulmocast schema mulmo tool story_to_script Generate Mulmo script from story mulmo tool whisper Process file with whisper mulmo tool complete Complete MulmoScript with schema defaults and optional style mulmo tool info [category] Show available options (styles, bgm, templates, voices, images, movies, llm, themes, config, merged) Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] ``` ``` mulmo tool scripting Generate mulmocast script Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -u, --url URLs to reference (required when not in interactive mode) [array] [default: []] --input-file input file name [string] -i, --interactive Generate script in interactive mode with user prompts [boolean] -t, --template Template name to use [string] [choices: "akira_comic", "ani", "business", "characters", "children_book", "coding", "comic_strips", "documentary", "drslump_comic", "ghibli_comic", "ghibli_comic_strips", "ghost_comic", "html", "image_prompt", "leda", "onepiece_comic", "portrait_movie", "realistic_movie", "sensei_and_taro", "shorts", "sifi_story", "trailer", "vision"] -c, --cache cache dir [string] -s, --script script filename [string] [default: "script"] --llm llm [string] [choices: "openai", "anthropic", "gemini", "groq", "mock"] --llm_model llm model [string] ``` ``` mulmo tool story_to_script Generate Mulmo script from story Positionals: file story file path [string] [required] Options: --version Show version number [boolean] -v, --verbose verbose log [boolean] [required] [default: false] -h, --help Show help [boolean] -o, --outdir output dir [string] -b, --basedir base dir [string] -t, --template Template name to use [string] [choices: "akira_comic", "ani", "business", "characters", "children_book", "coding", "comic_strips", "documentary", "drslump_comic", "ghibli_comic", "ghibli_comic_strips", "ghost_comic", "html", "image_prompt", "leda", "onepiece_comic", "portrait_movie", "realistic_movie", "sensei_and_taro", "shorts", "sifi_story", "trailer", "vision"] -s, --script script filename [string] [default: "script"] --beats_per_scene beats per scene [number] [default: 3] ``` > The README is long; the above is its first 40000 characters. Full content: https://github.com/receptron/mulmocast-cli