### Create Your First Video (Hello World)

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/getting-started.md

Navigate to the example directory, install dependencies, and run commands to preview and export your first video. No API keys are required for this basic setup.

```bash
cd examples/hello-world
npm install
npm run studio    # Preview in browser
npm run render    # Export MP4
```

--------------------------------

### Render Hello World Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/README.md

Skip the full setup and render an MP4 video immediately by navigating to the 'hello-world' example directory, installing Node.js dependencies, and running the render script. No API keys are required.

```bash
cd examples/hello-world && npm install && npm run render
```

--------------------------------

### Quick Start Project Setup and Rendering

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/templates/concept-explainer-short/README.md

Steps to copy the template, set up a new project, and perform an initial render. Includes commands for generating voiceover, captions, and the final video.

```bash
cp -r templates/concept-explainer-short projects/my-short
cd projects/my-short

# 0. Renders immediately — placeholder cards, estimated timing, silent
python3 build.py

# 1. Write your scenes (see scenes.json for the example)
# 2. Generate visuals (from the TOOLKIT ROOT — see "Visuals" below)
# 3. Voiceover → captions → final render (from the project dir)
python3 gen_vo.py
python3 gen_captions.py        # needs: pip install openai-whisper
python3 build.py
```

--------------------------------

### Run Remotion Examples

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/README.md

Instructions for setting up and running Remotion-based examples. Requires copying the project and installing Node.js dependencies.

```bash
cp -r examples/example-name projects/my-project
cd projects/my-project
npm install
npm run studio
```

--------------------------------

### Quick Start Commands for Remotion Project

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/sprint-review-cho-oyu/README.md

Use these bash commands to copy the example project, install dependencies, and run the Remotion studio or render commands.

```bash
cp -r examples/sprint-review-cho-oyu projects/my-version
cd projects/my-version

# Create required assets (see ASSETS-NEEDED.md)
# ...

# Preview
cd remotion
npm install
npm run studio

# Render
npm run render
```

--------------------------------

### Share an Example Project

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/CONTRIBUTORS.md

To get listed as a contributor by sharing an example project, follow this path within the project.

```bash
/contribute → Option 5 (Share an example project)
```

--------------------------------

### Automated RunPod Setup and Usage

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/runpod-setup.md

Quick start for setting up RunPod endpoints and using the tools. Adds API key to .env, creates endpoints via --setup, and demonstrates tool usage.

```bash
# 1. Add your RunPod API key to .env
echo "RUNPOD_API_KEY=your_key_here" >> .env

# 2. Run automated setup for each tool you need
python tools/image_edit.py --setup    # AI image editing
python tools/upscale.py --setup       # AI upscaling
python tools/dewatermark.py --setup   # AI watermark removal

# 3. Done! Now use them:
python tools/image_edit.py --input photo.jpg --style cyberpunk
python tools/upscale.py --input photo.jpg --output photo_4x.png --runpod
python tools/dewatermark.py --input video.mp4 --region x,y,w,h --output out.mp4 --runpod
```

--------------------------------

### Development Environment Setup

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/CONTRIBUTING.md

Set up a Python virtual environment and install project dependencies.

```bash
python -m venv .venv
source .venv/bin/activate
pip install -r tools/requirements.txt
```

--------------------------------

### Install and Run Project

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/templates/ai-engineering-review/README.md

Install dependencies, open the preview studio, and render the final video using npm commands.

```bash
npm install

npm run studio

npm run render
```

--------------------------------

### Remotion Project Setup and Commands

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/digital-samba-skill-demo/VIDEO-SPEC.md

Commands to set up a new Remotion project or install dependencies, and to preview or render the video composition.

```bash
cd remotion
npx create-video@latest  # If starting fresh
npm install
npm run studio  # Preview
npm run render  # Final output
```

--------------------------------

### Install Dependencies and Run Remotion Studio/Render

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/digital-samba-skill-demo/ASSETS-NEEDED.md

These commands are used after creating the necessary assets. They install project dependencies, start the Remotion preview studio, and render the final MP4 video.

```bash
cd remotion
npm install
npm run studio    # Preview
npm run render    # Final MP4
```

--------------------------------

### Verify Setup

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/modal-setup.md

Run this Python script to verify your current setup.

```bash
python3 tools/verify_setup.py
```

--------------------------------

### Install and Run Sprint Review Template

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/templates/sprint-review-v2/README.md

Install dependencies, open the preview studio for development, and render the final video.

```bash
npm install

# Open the preview studio
npm run studio

# Render final video
npm run render
```

--------------------------------

### Install Dependencies and Run Stinger Build

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/ds-crt-stinger/README.md

Installs necessary Python packages and system dependencies, then navigates to the example directory to build the stinger. Subsequent runs reuse cached intermediates.

```bash
# From the toolkit root:
python3 -m pip install -r tools/requirements.txt   # moviepy, Pillow, numpy
brew install librsvg                               # rsvg-convert (one-time)

cd examples/ds-crt-stinger
python3 build.py                                   # → ds_stinger_astro.mp4
```

--------------------------------

### Start Claude Code CLI and Run Setup Wizard

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/getting-started.md

Initiate the Claude Code command-line interface and use the `/setup` command to configure cloud GPU, file transfer, and voice settings. Alternatively, manually configure by copying and editing the .env file.

```bash
claude
```

```bash
cp .env.example .env
```

--------------------------------

### Install and Run Transition Studio

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/README.md

Navigate to the transitions showcase directory, install dependencies, and run the studio to preview all available scene transitions.

```bash
cd showcase/transitions && npm install && npm run studio
```

--------------------------------

### Install Dependencies and Run Studio/Render

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/templates/product-demo/README.md

Install project dependencies, open the preview studio for live editing, and render the final video.

```bash
# Install dependencies
npm install

# Open the preview studio
npm run studio

# Render final video
npm run render
```

--------------------------------

### Create Your First Video

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/getting-started.md

Initiate video creation using the unified /video command. This command guides you through project setup, template selection, branding, content gathering, and scene planning.

```bash
/video
```

--------------------------------

### Run First-Time Setup

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/CLAUDE.md

Execute this command for initial setup, including cloud GPU, file transfer, and voice configuration. Most features are free. This step is optional if you only intend to render videos with Node.js.

```bash
/setup
```

--------------------------------

### Contribute a New Example Project

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/README.md

Steps to add a new project as an example to the toolkit. Involves copying the project, removing media files, and creating asset documentation.

```bash
# Copy project to examples (without large media)
cp -r projects/my-project examples/

# Remove media files (these are gitignored anyway)
rm examples/my-project/public/demos/*.mp4
rm examples/my-project/public/audio/*.mp3

# Create asset documentation
# (describe what demos/audio are needed)

# Commit and PR
git add examples/my-project
git commit -m "Add example: my-project"
gh pr create
```

--------------------------------

### Install and Run Transition Showcase

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/lib/transitions/README.md

Set up and launch the standalone transition showcase project to visually preview all available transitions.

```bash
cd showcase/transitions
npm install
npm run studio
```

--------------------------------

### Quick Start: Text-to-Video Generation

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/ltx2.md

Basic command to generate a video clip from a text prompt. Ensure you have the LTX-2 tool installed and configured.

```bash
python3 tools/ltx2.py --prompt "A cat playing with yarn in a sunlit room"
```

--------------------------------

### Automated RunPod Setup

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docker/runpod-qwen3-tts/README.md

Automates the setup process for deploying the Qwen3-TTS worker on RunPod using a Python script.

```bash
python tools/qwen3_tts.py --setup
```

--------------------------------

### Install Dependencies and Run Build Script

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/quick-spot/README.md

Installs necessary Python dependencies and then executes the build script to generate the video.

```bash
# From the toolkit root (one-time — installs moviepy, Pillow, matplotlib
# alongside the rest of the toolkit's optional Python deps):
python3 -m pip install -r tools/requirements.txt

# Then:
cd examples/quick-spot
python3 build.py
```

--------------------------------

### Install Playwright and Browsers

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/playwright/README.md

Install Playwright and necessary browser binaries for recording demos.

```bash
cd playwright
npm install
npm run install-browsers
```

--------------------------------

### Run Moviepy Examples

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/README.md

Instructions for running moviepy-based examples directly. These are self-contained and produce an output file in the example directory.

```bash
cd examples/quick-spot   # or examples/data-viz-chart
python3 build.py         # produces out.mp4 in the example directory
```

--------------------------------

### Setup Python Virtual Environment for ElevenLabs

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/digital-samba-skill-demo/CLAUDE.md

Set up a Python virtual environment for audio generation scripts. Installs necessary packages like python-dotenv and elevenlabs. Requires a .env file for the ElevenLabs API key.

```bash
# First time setup
python3 -m venv .venv
source .venv/bin/activate
pip install python-dotenv elevenlabs

# Subsequent runs - always activate venv first
source .venv/bin/activate
```

--------------------------------

### Automated Setup

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docker/runpod-realesrgan/README.md

Use the provided Python script for an automated setup process. This may include building and deploying the container.

```bash
python tools/upscale.py --setup
```

--------------------------------

### Create Your First Video with Claude Code

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/README.md

Initiate video creation using the `/video` command in Claude Code. This command guides you through the entire workflow, starting from a project template.

```bash
/video                    # Create your first video
```

--------------------------------

### Build Short Video

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/sky-blue-short/README.md

Navigate to the example directory and run the build script to render the video from committed assets.

```bash
cd examples/sky-blue-short
python3 build.py          # re-render from committed assets → out/short.mp4
```

--------------------------------

### Install ProPainter

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/optional-components.md

Installs the ProPainter optional component, cloning the repository, setting up a virtual environment, and downloading model weights.

```bash
python tools/dewatermark.py --status
```

```bash
python tools/dewatermark.py --install
```

--------------------------------

### Quick Start: Image-to-Video Animation

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/ltx2.md

Animate a still image by providing a text prompt for motion and an input image file. The prompt guides the animation style.

```bash
python3 tools/ltx2.py --prompt "Camera slowly pans right" --input photo.jpg
```

--------------------------------

### Install and Render Remotion Video

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/digital-samba-skill-demo/VIDEO-PROMPT.md

Commands to install dependencies, preview the video in the studio, and render the final output.

```bash
cd ~/work/video/digital-samba-skill-demo/remotion
npx create-video@latest .  # If scaffolding needed
npm install
npm run studio  # Preview
npm run render  # Final output
```

--------------------------------

### Verify Setup

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/skills/openclaw-video-toolkit/SKILL.md

Run this script after navigating to the toolkit directory to check if all necessary components are correctly set up.

```bash
cd ~/.openclaw/workspace/claude-code-video-toolkit
python3 tools/verify_setup.py
```

--------------------------------

### Manual Project Setup with npm

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/getting-started.md

Use this command sequence to manually create and set up a new video project from a template using npm.

```bash
cp -r templates/sprint-review projects/my-video
cd projects/my-video
npm install
```

```bash
npm run studio
```

```bash
npm run render
```

--------------------------------

### SadTalker Setup

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/sadtalker.md

Configure your RunPod API key and run the setup script to create the endpoint.

```bash
RUNPOD_API_KEY=your_key_here
```

```bash
python tools/sadtalker.py --setup
```

--------------------------------

### Create Project from Template

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/skills/openclaw-video-toolkit/SKILL.md

Copy a project template and install its dependencies. Choose from 'product-demo', 'sprint-review', or 'sprint-review-v2'.

```bash
cd ~/.openclaw/workspace/claude-code-video-toolkit
cp -r templates/product-demo projects/PROJECT_NAME
cd projects/PROJECT_NAME
npm install
```

--------------------------------

### Install boto3 for S3-Compatible Operations

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/runpod-setup.md

Install the boto3 library to interact with S3-compatible storage like Cloudflare R2.

```bash
pip install boto3
```

--------------------------------

### Install Codex Skills

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/AGENTS.md

Run this script once to install the toolkit's skills under ~/.codex/skills/. Use --force to re-run.

```bash
python3 scripts/migrate_to_codex.py --force
```

--------------------------------

### Example Project Resume Session

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/lib/project/README.md

Illustrates the interactive process of resuming a video project, including project selection and status overview.

```bash
$ /video

Found 2 video projects:

  1. **product-launch** (product-demo)
     Phase: assets - 2/3 demos recorded
     Last worked: 2 days ago

  2. **q4-review** (sprint-review)
     ✅ Complete

Which project? > 1

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Resuming: product-launch (product-demo)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

## Scenes

| # | Scene | Type | Status |
|---|-------|------|--------|
| 1 | Title | title | ✅ Ready |
| 2 | Problem | problem | ✅ Ready |
| 3 | Demo: Onboarding | demo | ✅ Recorded |
| 4 | Demo: Dashboard | demo | ✅ Recorded |
| 5 | Demo: Export | demo | ⬜ Needs recording |
| 6 | CTA | cta | ✅ Ready |

## Audio

- Voiceover: ⬜ Not yet generated

## Next Actions

1. **Record export demo** (Scene 5)
   Run `/record-demo` or provide external video

Ready to record the export demo?

```

--------------------------------

### Install and Run Video Rendering

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/hello-world/README.md

Use these npm commands to install dependencies, preview the video in a browser, and export the final video file. No external services or API keys are required.

```bash
npm install
npm run studio   # Preview in browser
npm run render   # Export to out/video.mp4
```

--------------------------------

### Install and Render Banner

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/showcase/banner/README.md

Commands to install dependencies, preview the banner in Remotion Studio, and render it into MP4, GIF, and poster formats.

```bash
cd showcase/banner
npm install
npm run studio     # Preview / scrub in Remotion Studio
npm run render     # MP4 → out/toolkit-banner.mp4
npm run render:gif # GIF → out/toolkit-banner.gif
npm run render:poster # Static PNG poster frame
```

--------------------------------

### Install Dependencies and Build Chart

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/data-viz-chart/README.md

Installs necessary Python dependencies and then builds the animated chart. The first run may take longer due to rendering.

```bash
python3 -m pip install -r tools/requirements.txt
```

```bash
cd examples/data-viz-chart
python3 build.py
```

--------------------------------

### Fine-Tuned Settings Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/sadtalker.md

Customizes video generation with specific pose style, expression scale, and resolution.

```bash
python tools/sadtalker.py \
  --image portrait.png \
  --audio speech.mp3 \
  --pose-style 45 \
  --expression-scale 1.2 \
  --size 512 \
  --output custom.mp4
```

--------------------------------

### Project JSON Schema Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/lib/project/README.md

Example structure for the `project.json` file, detailing project metadata, phase, scenes, and audio information.

```json
{
  "name": "my-release-video",
  "template": "sprint-review",
  "brand": "digital-samba",
  "created": "2024-12-09T10:30:00Z",
  "updated": "2024-12-10T15:45:00Z",
  "phase": "assets",

  "scenes": [...],
  "audio": {...},
  "estimates": {...},
  "sessions": [...] 
}
```

--------------------------------

### Example File Structure

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/qwen-edit-patterns.md

Illustrates the file structure created after running image edit operations.

```text
<toolkit-root>/
├── conor_bond.png
├── conor_neo.png
├── conor_wick.png
├── conor_maverick.png
├── conor_gump.png
├── conor_indy.png
└── conor_shelby.png
```

--------------------------------

### Install Remotion Transitions Package

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/lib/transitions/README.md

Install the necessary packages for using Remotion transitions. This includes the main transitions package along with paths and shapes for advanced effects.

```bash
npm install @remotion/transitions @remotion/paths @remotion/shapes
```

--------------------------------

### Qwen3-TTS API Output Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docker/runpod-qwen3-tts/README.md

Example JSON response from the Qwen3-TTS API, showing success status, audio URL, R2 key, processing time, and mode used.

```json
{
  "success": true,
  "audio_url": "https://presigned-r2-url...",
  "r2_key": "qwen3-tts/results/job_xxx.mp3",
  "duration_seconds": 3.5,
  "mode": "custom_voice",
  "processing_time_seconds": 8.2
}
```

--------------------------------

### Professional/Calm Style Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/sadtalker.md

Creates a video with minimal head movement suitable for professional content, using the 'professional' preset and higher resolution.

```bash
python tools/sadtalker.py \
  --image headshot.png \
  --audio presentation.mp3 \
  --preset professional \
  --size 512 \
  --output presenter.mp4
```

--------------------------------

### Example Prompt: Simple Scene with Motion

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/ltx2.md

A sample prompt demonstrating a simple scene with specific details about motion, lighting, and background.

```text
# Simple scene with motion
"A single lit candle on a dark wooden table, flame gently flickering, soft bokeh background, cinematic lighting"
```

--------------------------------

### Split Screen Layout Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/sprint-review-cho-oyu/VIDEO-SPEC.md

Illustrates a side-by-side layout for screenshare demonstrations, combining iPhone and remote browser views.

```text
+------------------+------------------+
|                  |                  |
|   iPhone View    |  Remote Browser  |
|                  |     (Mac)        |
|                  |                  |
+------------------+------------------+
```

--------------------------------

### Natural Talking Head Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/sadtalker.md

Generates a video with natural head movement using the 'natural' preset.

```bash
python tools/sadtalker.py \
  --image portrait.png \
  --audio narration.mp3 \
  --preset natural \
  --output talking.mp4
```

--------------------------------

### Quick Start for Digital Samba Skill Demo

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/digital-samba-skill-demo/README.md

Use these commands to copy the demo project, set up assets, and preview or render the video using Remotion.

```bash
# Copy to your projects
cp -r examples/digital-samba-skill-demo projects/my-version
cd projects/my-version

# Create required assets (see ASSETS-NEEDED.md)
# ...

# Preview
cd remotion
npm install
npm run studio

# Render
npm run render
```

--------------------------------

### Install Playwright Browsers

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/_internal/reviews/playwright-review.md

Installs the necessary Chromium browser for Playwright. Run this command within the 'playwright' directory.

```bash
cd playwright
npm install
npx playwright install chromium
```

--------------------------------

### Example Usage of /components Command

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/_internal/BACKLOG.md

Demonstrates how to use the /components command to list all components, view specific component details, or filter components by category.

```bash
/components              # List all components
/components Envelope     # View Envelope component details
/components --category animations  # List animation components
```

--------------------------------

### Initialize Claude Code Configuration

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/README.md

Use the `/setup` command within Claude Code to configure cloud GPU, storage, and voice settings. This process takes approximately 5 minutes and is largely free.

```bash
/setup                    # Configure cloud GPU, storage, voice (~5 min, mostly free)
```

--------------------------------

### Set up Modal for Cloud GPU Deployment

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/CLAUDE.md

Install the Modal client and deploy applications to Modal for cloud GPU processing. Save the returned URL to your .env file.

```bash
# --- Modal setup (deploy each app you need) ---
pip install modal && python3 -m modal setup
modal deploy docker/modal-upscale/app.py        # Then save URL to .env
modal deploy docker/modal-image-edit/app.py
```

--------------------------------

### Example Prompt: Nature with Camera Motion

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/ltx2.md

An example prompt focusing on nature imagery with specified camera movement and lighting conditions.

```text
# Nature with camera motion
"Aerial drone shot slowly flying over turquoise ocean waves breaking on a white sand beach, golden hour sunlight"
```

--------------------------------

### Manually Create and Run Video Project

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/CLAUDE.md

Manually set up a video project by copying a template, installing dependencies, and running preview or render commands. Remember to restart Claude Code after modifying commands or skills.

```bash
cp -r templates/sprint-review projects/my-video
```

```bash
cd projects/my-video
```

```bash
npm install
```

```bash
npm run studio   # Preview
```

```bash
npm run render   # Export
```

--------------------------------

### Install YouTube API Python Dependencies

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/youtube-upload.md

Install the required Python packages for interacting with the YouTube Data API. These are opt-in dependencies.

```bash
pip install google-api-python-client google-auth-oauthlib google-auth-httplib2
```

--------------------------------

### Remotion Development Server

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/digital-samba-skill-demo/CLAUDE.md

Start the Remotion development server to preview and iterate on video compositions. Navigate to the Remotion directory and run the npm studio command.

```bash
cd remotion && npm run studio
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/skills/openclaw-video-toolkit/SKILL.md

Install the required Python packages using pip. The `--break-system-packages` flag may be necessary on Debian/Ubuntu systems.

```bash
cd ~/.openclaw/workspace/claude-code-video-toolkit
pip3 install --break-system-packages -r tools/requirements.txt
```

--------------------------------

### Install and Authenticate Modal CLI

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/modal-setup.md

Install the Modal Python package and authenticate your CLI with your Modal account. This saves your API token to `~/.modal.toml`.

```bash
pip install modal
python3 -m modal setup    # Opens browser to authenticate, saves token to ~/.modal.toml
modal app list             # Verify it works
```

--------------------------------

### Transition Gallery Showcase

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/lib/transitions/README.md

Instructions on how to run the standalone showcase project to visually preview all available transitions.

```APIDOC
## Standalone Showcase

### Description
Preview all transitions with the dedicated showcase project.

### Usage
1. Navigate to the showcase directory:
   ```bash
   cd showcase/transitions
   ```
2. Install dependencies:
   ```bash
   npm install
   ```
3. Run the studio:
   ```bash
   npm run studio
   ```
This will open Remotion Studio, displaying a visual gallery of each transition effect.
```

--------------------------------

### JSON Progress Output Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/skills/openclaw-video-toolkit/SKILL.md

Example of the JSON Lines output format for progress reporting, showing timestamps, stages, messages, and progress percentages.

```json
{"ts":"14:23:15","stage":"submit","msg":"Sending to acemusic.ai (XL Turbo 4B, thinking: on)...","pct":null,"elapsed":0.0}
{"ts":"14:23:30","stage":"waiting","msg":"Waiting for acemusic.ai response... (15s)","pct":null,"elapsed":15.0}
{"ts":"14:23:45","stage":"waiting","msg":"Waiting for acemusic.ai response... (30s)","pct":null,"elapsed":30.0}
{"ts":"14:24:02","stage":"complete","msg":"Saved: bg-music.mp3 (245 KB, 60.1s)","pct":100,"elapsed":47.3}
```

--------------------------------

### Clone Repository and Install Dependencies

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/README.md

Clone the toolkit repository and install Python dependencies for optional AI features. Then, launch the Claude Code interface.

```bash
git clone https://github.com/digitalsamba/claude-code-video-toolkit.git
cd claude-code-video-toolkit
python3 -m pip install -r tools/requirements.txt   # Optional: AI voiceover, image gen, music, moviepy examples
claude                                              # Open Claude Code in the toolkit
```

--------------------------------

### Setup: Deploy Modal App

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/ltx2.md

Deploy the LTX-2 Modal application. This step downloads and bakes model weights, which may take 10-15 minutes.

```bash
modal deploy docker/modal-ltx2/app.py
```

--------------------------------

### Qwen3-TTS API Input Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docker/runpod-qwen3-tts/README.md

Example JSON payload for the Qwen3-TTS API, demonstrating input parameters for text, mode, speaker, language, and R2 integration.

```json
{
  "input": {
    "text": "Hello, how are you today?",
    "mode": "custom_voice",
    "speaker": "Ryan",
    "language": "English",
    "instruct": "Speak warmly and enthusiastically",
    "output_format": "mp3",
    "r2": {
      "endpoint_url": "https://...",
      "access_key_id": "...",
      "secret_access_key": "...",
      "bucket_name": "..."
    }
  }
}
```

--------------------------------

### Quick Start: Fast Mode for Quicker Generation

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/ltx2.md

Utilize the 'fast' quality mode for quicker video generation at the cost of some quality. This mode uses fewer inference steps.

```bash
python3 tools/ltx2.py --prompt "A rocket launch" --quality fast
```

--------------------------------

### Install Python Toolkit Dependencies

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/CLAUDE.md

Install the necessary Python packages for the toolkit's tools. Ensure you run this command from the toolkit's root directory.

```bash
# Setup
pip install -r tools/requirements.txt
```

--------------------------------

### Run Demo Recording

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/playwright/README.md

Execute the recording script after configuring the demo URL and output settings.

```bash
npm run record
```

--------------------------------

### Remotion Sprint Configuration Example

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/examples/sprint-review-cho-oyu/README.md

An example TypeScript configuration object for Remotion, showing how to define sprint information and demo details. Update 'your-demo.mp4' and other fields to match your project.

```typescript
export const sprintConfig = {
  info: {
    name: 'Your Sprint Name',
    version: '1.0.0',
    dateRange: 'Jan 15 - Jan 29',
  },
  demos: [
    { type: 'single', videoFile: 'your-demo.mp4', ... }
  ]
};
```

--------------------------------

### Clone Repository and Install Python Dependencies

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/docs/getting-started.md

Clone the toolkit repository and set up a Python virtual environment with the necessary dependencies for audio and image tools.

```bash
git clone https://github.com/digitalsamba/claude-code-video-toolkit.git
cd claude-code-video-toolkit
```

```bash
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r tools/requirements.txt
```

--------------------------------

### Chain video from an existing clip

Source: https://github.com/digitalsamba/claude-code-video-toolkit/blob/main/skills/openclaw-video-toolkit/SKILL.md

Chain video clips starting from an existing video file, specifying start and end times, and a prompt. This method does not require scene images.

```bash
python3 tools/chain_video.py \
  --first-clip output/chain-04.mp4 \
  --output-dir output/ \
  --start 5 --end 30 \
  --prompt "Celtic mythology, flowing transition" \
  --progress json
```