Skip to content
Back to search

claude-code-video-toolkit

AI-native video production toolkit for Claude Code

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/digitalsamba/claude-code-video-toolkit with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/digitalsamba/claude-code-video-toolkit'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/digitalsamba-claude-code-video-toolkit/badge.svg)](/listings/digitalsamba-claude-code-video-toolkit)

HTML

<a href="/listings/digitalsamba-claude-code-video-toolkit"><img src="/api/listings/digitalsamba-claude-code-video-toolkit/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

git clone https://github.com/digitalsamba/claude-code-video-toolkit.git
cd claude-code-video-toolkit
uv sync   # Optional: AI voiceover, image gen, music, moviepy examples
claude    # Open Claude Code in the toolkit

> Python dependencies are managed with [uv](https://docs.astral.sh/uv/) — `uv sync` creates `.venv/` and installs everything from the lockfile in seconds. No uv yet? `curl -LsSf https://astral.sh/uv/install.sh | sh` (macOS/Linux) or `powershell -c "irm https://astral.sh/uv/install.ps1 | iex"` (Windows).

Then in Claude Code:

/setup                    # Configure cloud GPU, storage, voice (~5 min, mostly free)
/video                    # Create your first video

**That's it.** `/setup` walks you through everything interactively — cloud GPU provider, file transfer, voice config. `/video` creates a project from a template and guides you through the whole workflow.

**What's free:** The toolkit leans heavily on open-source AI models — voiceovers (Qwen3-TTS), image generation (FLUX.2), music (ACE-Step), and more. You deploy them to your own cloud GPU account and run them at cost. Cloudflare R2 has a generous free tier (10GB, zero egress), and Modal gives $30/month free compute on the Starter plan — more than enough for a few 5-minute videos a month.

**Requirements:** [Node.js](https://nodejs.org/) 18+ and [Claude Code](https://docs.anthropic.com/en/docs/claude-code). [uv](https://docs.astral.sh/uv/) recommended for the AI tools (it installs Python 3.10+ for you). FFmpeg optional.

> **Want to skip setup and just render something?** > ```bash > cd examples/hello-world && npm install && npm run render > ``` > No API keys needed — outputs an MP4 immediately.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 471 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # claude-code-video-toolkit
  2. <p align="center">
  3. <img src="assets/banner/toolkit-banner.gif" alt="claude-code-video-toolkit — NARRATE ▸ SCORE ▸ GENERATE ▸ COMPOSE ▸ RENDER" width="960" />
  4. </p>
  5. [![GitHub release](https://img.shields.io/github/v/release/digitalsamba/claude-code-video-toolkit)](https://github.com/digitalsamba/claude-code-video-toolkit/releases) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![GitHub stars](https://img.shields.io/github/stars/digitalsamba/claude-code-video-toolkit?style=social)](https://github.com/digitalsamba/claude-code-video-toolkit/stargazers) [![YouTube: subscribe](https://img.shields.io/badge/YouTube-Subscribe-FF0000?logo=youtube&logoColor=white)](https://www.youtube.com/@claudecodevideotoolkit?sub_confirmation=1)
  6. Tell [Claude Code](https://claude.ai/code) what video you want: it writes the script, generates the voiceover, music, and visuals, and renders the MP4. An AI-native video production workspace: the skills, commands, templates, and tools your AI agent needs to take a video from concept to final render, on open-source models that cost cents (voiceover ~$0.01, AI video clips ~$0.23). With Blender installed (optional), it also makes films with a 3D character who acts from a JSON spec.
  7. ## See What It Makes
  8. Every frame below was generated in this workspace. Click one to watch it.
  9. <a href="https://www.youtube.com/watch?v=CgxzhKQ0Afg"><img src="assets/readme-thumbs/just-a-quick-one.jpg" width="870" alt="Just a Quick One: a 3D character in his kitchen with a mug of tea, and a small computer with a face on the counter"></a><br>
  10. **Just a Quick One**: the toolkit's trailer, with a 3D character acting from a JSON spec. He walks into his kitchen
  11. with his tea, sits down and opens the laptop; every move is a verb in the spec, checked before Blender renders it.
  12. [How it works](https://digitalsamba.github.io/claude-code-video-toolkit/3d-characters.html), and what your machine needs.
  13. <a href="https://www.youtube.com/watch?v=3HjPatdeal4"><img src="assets/readme-thumbs/made-with-itself.jpg" width="870" alt="Made with itself: the toolkit's own video, made in the toolkit"></a><br>
  14. **Made with itself**: this toolkit in 90 seconds, made with this toolkit. Every terminal line on screen is the real
  15. output of the command that made that part, and the bill is measured ($0.33).
  16. | | |
  17. |:--:|:--:|
  18. | <a href="https://demos.digitalsamba.com/video/ds-release-650.mp4"><img src="assets/readme-thumbs/ds-release-650.jpg" width="430" alt="Release-notes video with product UI rebuilt from source"></a> | <a href="https://www.youtube.com/watch?v=AQLzseZ2aAY"><img src="assets/readme-thumbs/design-sources.jpg" width="430" alt="Design a video with Claude Code: one chart, three design skills"></a> |
  19. | **Release-notes video**<br>product UI rebuilt from source,<br>no screen recording | **Design sources**<br>one chart in three design skills,<br>plug in your own or use ours |
  20. | | | |
  21. |:--:|:--:|:--:|
  22. | <a href="https://demos.digitalsamba.com/video/ds-free-schedule-demo.mp4"><img src="assets/readme-thumbs/ds-free-schedule-demo.jpg" height="280" alt="Product demo with an AI narrator tile"></a> | <a href="https://demos.digitalsamba.com/video/hallucinations_short.mp4"><img src="assets/readme-thumbs/hallucinations-short.jpg" height="280" alt="AI hallucinations explainer short"></a> | <a href="https://youtube.com/shorts/1hyDgC5Qg_o"><img src="assets/readme-thumbs/youre-on-mute-short.jpg" height="280" alt="You're On Mute: every video call ever, as a horror trailer"></a> |
  23. | **Product demo**<br>scripted cursor and camera,<br>AI narrator tile | **AI hallucinations explainer**<br>9:16 Short: Ideogram 4 cards,<br>cloned voice, burned captions | **You're On Mute**<br>every video call ever, as a horror trailer;<br>invented cast, `parody-short` skill |
  24. More in the [showcase table](#templates) below, and new ones land on the [YouTube channel](https://www.youtube.com/@claudecodevideotoolkit) first ([subscribe](https://www.youtube.com/@claudecodevideotoolkit?sub_confirmation=1)). Made one yourself? Post it in [Show and tell](https://github.com/digitalsamba/claude-code-video-toolkit/discussions/categories/show-and-tell).
  25. ## Quick Start
  26. ```bash
  27. git clone https://github.com/digitalsamba/claude-code-video-toolkit.git
  28. cd claude-code-video-toolkit
  29. uv sync # Optional: AI voiceover, image gen, music, moviepy examples
  30. claude # Open Claude Code in the toolkit
  31. ```
  32. > Python dependencies are managed with [uv](https://docs.astral.sh/uv/) — `uv sync` creates `.venv/` and installs everything from the lockfile in seconds. No uv yet? `curl -LsSf https://astral.sh/uv/install.sh | sh` (macOS/Linux) or `powershell -c "irm https://astral.sh/uv/install.ps1 | iex"` (Windows).
  33. Then in Claude Code:
  34. ```
  35. /setup # Configure cloud GPU, storage, voice (~5 min, mostly free)
  36. /video # Create your first video
  37. ```
  38. **That's it.** `/setup` walks you through everything interactively — cloud GPU provider, file transfer, voice config. `/video` creates a project from a template and guides you through the whole workflow.
  39. **What's free:** The toolkit leans heavily on open-source AI models — voiceovers (Qwen3-TTS), image generation (FLUX.2), music (ACE-Step), and more. You deploy them to your own cloud GPU account and run them at cost. Cloudflare R2 has a generous free tier (10GB, zero egress), and Modal gives $30/month free compute on the Starter plan — more than enough for a few 5-minute videos a month.
  40. **Requirements:** [Node.js](https://nodejs.org/) 22+ (24 LTS recommended) and [Claude Code](https://docs.anthropic.com/en/docs/claude-code). [uv](https://docs.astral.sh/uv/) recommended for the AI tools (it installs Python 3.10+ for you). FFmpeg optional.
  41. > **Want to skip setup and just render something?**
  42. > ```bash
  43. > cd examples/hello-world && npm install && npm run render
  44. > ```
  45. > No API keys needed — outputs an MP4 immediately.
  46. ---
  47. ## A Note from the Author *(not AI-generated)*
  48. > I've spent months painstakingly putting this toolkit together and plan to keep iterating on it. AI makes things easier, but hard work still has huge value. Every video I create is a chance for improvement — every skill, template, tool, and workflow here has been refined through that cycle. It would be wonderful if others wanted to get involved with that: use it, refine it, and feed back into the repo via an issue or PR what you learn.
  49. >
  50. > My own use case is fairly specific: creating sprint review videos for the AI mobile development arm of [Digital Samba](https://www.digitalsamba.com/). But the idea behind this project is a reusable toolkit for using Claude Code to autonomously generate any kind of "explainer" style video — product demos, walkthroughs, presentations, whatever you need. Autonomous video creation is a lofty ideal for such a subjective field, but we can try :)
  51. >
  52. > What makes this work is that Claude Code is fantastically resourceful and flexible — give it the framing and tooling that this toolkit provides and it will adapt it to create templates and videos based on your prompting. The skills, templates, and tools here are building blocks. Claude Code is the builder. You are the director, editor, and designer.
  53. >
  54. > **If you're getting started**, run `/setup` then `/video` and let Claude Code guide you. Or start with `/template` to create a template for your own use case.
  55. >
  56. > **Cloud GPU** — I recommend [Modal](https://modal.com/) for running the toolkit's AI tools. The Starter plan gives you $30/month free compute, which is more than enough. [RunPod](https://runpod.io/) is also supported as an alternative. Run `/setup` to deploy the tools you need.
  57. >
  58. > My motto: **Be brave. Experiment.** And please share any videos you create or ideas you have back with the project — it helps me keep improving this toolkit for everyone.
  59. ## Features
  60. ### Skills
  61. Claude Code has deep knowledge in:
  62. | Skill | Description |
  63. |-------|-------------|
  64. | **remotion** | React-based video framework — compositions, animations, rendering |
  65. | **elevenlabs** | AI audio — text-to-speech, voice cloning, music, sound effects |
  66. | **ffmpeg** | Media processing — format conversion, compression, resizing |
  67. | **playwright-recording** | Browser automation — record demos as video |
  68. | **video-design** | Visual design for video: colour by act, one data accent, type steps, a contact-sheet critique; takes direction from any design skill ([design sources](#design-sources)) |
  69. | **qwen-edit** | AI image editing — prompting patterns and best practices |
  70. | **ideogram4** | AI image generation with best-in-class in-image text — title cards, thumbnails, exact brand colors |
  71. | **acestep** | AI music generation — prompts, lyrics, scene presets, video integration |
  72. | **ltx2** | AI video generation — text-to-video, image-to-video clips, prompting guide |
  73. | **parody-short** | Comedy shorts about a group's own life or a shared topic, in a borrowed genre: in-jokes from the group's own chat and docs, costumed and animated photos or an invented cast, sound placed on the movement, vertical cuts |
  74. | **blender** *(optional)* | 3D from a JSON shot spec: a rigged cartoon cast acting on cue, a scene that turns out to be on a laptop, an app on a phone or a 3D model on a studio stage; every camera checked before the render; as a film or as clips in any video. Needs [Blender](docs/blender.md) and renders in minutes with a GPU. Characters fitted from a generated 3D model are experimental |
  75. | **moviepy** | Python video composition — overlay text on LTX-2/SadTalker output, build.py-style projects |
  76. | **runpod** | Cloud GPU — setup, Docker images, endpoint management, costs |
  77. > The always-current catalog of skills, commands, tools, and templates lives in [`_internal/toolkit-registry.json`](_internal/toolkit-registry.json).
  78. ### Commands
  79. | Command | Description |
  80. |---------|-------------|
  81. | `/setup` | First-time setup — cloud GPU, file transfer, voice, prerequisites |
  82. | `/video` | Video projects — list, resume, or create new |
  83. | `/scene-review` | Scene-by-scene review in Remotion Studio |
  84. | `/design` | Set a video's design direction (design.md) from a design source, refine a scene, or critique the render |
  85. | `/brand` | Brand profiles — list, edit, or create new |
  86. | `/template` | List available templates or create new ones |
  87. | `/skills` | List installed skills or create new ones |
  88. | `/contribute` | Share improvements — issues, PRs, examples |
  89. | `/record-demo` | Record browser interactions with Playwright |
  90. | `/generate-voiceover` | Generate AI voiceover from a script |
  91. | `/redub` | Redub existing video with a different voice |
  92. | `/voice-clone` | Record, test, and save a cloned voice to a brand |
  93. | `/thumbnail` | Generate a YouTube thumbnail with Ideogram 4 (hook phrase + brand colours) |
  94. | `/publish` | Publish a finished video to YouTube (metadata auto-filled from `project.json`) |
  95. | `/versions` | Check dependency versions and toolkit updates |
  96. > **Note:** After creating or modifying commands/skills, restart Claude Code to load changes.
  97. ### Templates
  98. Pre-built video structures in `templates/`:
  99. - **sprint-review** — Sprint review videos with demos, stats, and voiceover
  100. - **sprint-review-v2** — Composable scene-based sprint review with modular architecture
  101. - **product-demo** — Marketing videos with dark tech aesthetic, stats, CTA
  102. - **concept-explainer-short** — 9:16 vertical TikTok/Reels/Shorts explainers (Python/moviepy, no Remotion)
  103. - **ds-release-notes** — Synthetic release-notes videos: product screens rebuilt from source, scripted cursor and camera, sentence-level cloned narration (ships as the Digital Samba 650 build)
  104. See `examples/` for finished projects you can learn from (newest first — scroll down to watch the toolkit evolve in reverse):
  105. | Date | Demo | Description |
  106. |------|------|-------------|
  107. | 2026-11-12 | [made-with-itself](https://www.youtube.com/watch?v=3HjPatdeal4) | 93s video about the toolkit, made in the toolkit from one sentence typed into Claude Code: each stage (narrate, score, generate, compose, check) is the real command in the new `Terminal` component, every line its saved output, then what it made; narrated by Marilyn from the ElevenLabs voice library through the new `brands/video-toolkit`; the bill is measured ($0.33) and the Check scene shows what `qc.py` really found in the draft (`examples/toolkit-made-itself`) |
  108. | 2026-11-09 | [design-sources](https://www.youtube.com/watch?v=AQLzseZ2aAY) | 46s: one chart designed three ways (the toolkit's own palettes, taste-skill, and a house style of your own), the page turning between them on the narration with `PageTurns`, then the render checked one frame per scene with `contact_sheet.py` |
  109. | 2026-11-07 | [the-great-return](https://www.youtube.com/watch?v=YUqkQydQDh4) | 98s wildlife documentary about the return to the office, made with the `parody-short` skill and the same invented cast: mock-Latin lower thirds, a designed narrator voice, LTX clips lengthened with `ltx_extend.py` instead of frozen, every sound effect placed on its movement with `sync_check.py` ([vertical cut](https://youtube.com/shorts/e4HW-tvi8-8)) |
  110. | 2026-11-07 | [youre-on-mute](https://www.youtube.com/watch?v=73JNiOJgx5k) | 76s horror trailer about the video call that never ends, from the `parody-short` skill: an invented cast of four (FLUX portraits animated with LTX through `LivingPhoto`), a call UI built in Remotion that misbehaves, a stinger after the title ([vertical cut](https://youtube.com/shorts/1hyDgC5Qg_o)) |
  111. | 2026-11-04 | [data-chart-stars](https://demos.digitalsamba.com/video/data-chart-stars.mp4) | 31s chart video of the toolkit's GitHub star history, drawn as SVG by the new `LineChart` and `BarChart` components: the line is drawn while Lugh narrates each stretch, and the March spike's band and the monthly bars light on the words that name them, timed with `cue()` (`examples/data-chart-stars`) |
  112. | 2026-11-01 | [the-agent-handoff](https://demos.digitalsamba.com/video/the-agent-handoff.mp4) | *An experiment in agent-first, one-prompt video, kept for the record rather than as a showcase.* 57s an agent made unattended from one Discord message: the agent wrote the script and the shot list, `video_job.py` voiced it with a cloned voice, generated four LTX-2 clips and a diagram card, built and QC'd it, and the Discord bot posted the link when it went live; $0.47, the fourth take after three pipeline fixes (`docs/agent-video-jobs.md`) |
  113. | 2026-10-28 | [ds-release-650](https://demos.digitalsamba.com/video/ds-release-650.mp4) | 87s release-notes video built from the `ds-release-notes` template: six items across the room and account center, Lugh's cloned voice made livelier with `voice_prosody.py`, checked with `qc.py --render --layout` (`templates/ds-release-notes`) |
  114. | 2026-10-21 | [ds-release-649](https://demos.digitalsamba.com/video/ds-release-649.mp4) | Release-notes video with no screen recording: three product UIs rebuilt from their source code, driven by a scripted cursor and camera, narrated by Lugh; re-rendered 2026-11-09 in the DS act palette from `video-design` (`examples/ds-release-649`) |
  115. | 2026-10-21 | [ds-free-schedule-demo](https://demos.digitalsamba.com/video/ds-free-schedule-demo.mp4) | 26s synthetic product demo of scheduling a call, with a SoulX talking-head narrator tile (`examples/ds-free-schedule-demo`) |
  116. | 2026-06-09 | [hallucinations-short](https://demos.digitalsamba.com/video/hallucinations_short.mp4) | 3:41 vertical explainer on AI hallucinations — Ideogram 4 cards, LTX-2 b-roll, burned karaoke captions, Qwen3-TTS voice *clone* (reference sample from [Pixabay](https://pixabay.com/sound-effects/search/voice%20overs/)) |
  117. | 2026-06-09 | [sky-blue-short](https://demos.digitalsamba.com/video/short-blue-sky.mp4) | 52s "Why is the sky blue?" — concept-explainer-short template showcase (`examples/sky-blue-short`), stock Qwen3-TTS voice |
  118. | 2026-04-08 | [q2-townhall-stars](https://demos.digitalsamba.com/video/q2-townhall-stars.mp4) | GitHub star history time-lapse with animated chart and deadpan-to-excited commentary |
  119. | 2026-04-08 | [q2-townhall-longarm-ad](https://demos.digitalsamba.com/video/q2-townhall-longarm-ad.mp4) | Super Bowl-style launch ad with dramatic Qwen3-TTS announcer and LTX-2 animated Lugh cameo |
  120. | 2026-03-15 | [the-space-between](https://demos.digitalsamba.com/video/the-space-between.mp4) | AI-generated video essay — flux2 avatar, Qwen3-TTS voice, SadTalker animation |
  121. | 2026-02-23 | [cortina](https://demos.digitalsamba.com/video/sprint-review.mp4) | Mobile platforms sprint review |
  122. | 2026-01-25 | [schlumbergera](https://demos.digitalsamba.com/video/schlumbergera.mp4) | Android sprint review video |
  123. | 2026-01-22 | [ds-remote-mcp](https://demos.digitalsamba.com/video/ds-remote-mcp.mp4) | Remote MCP server demo *(the jazz background music is a joke)* |
  124. | 2025-12-10 | [digital-samba-skill-demo](https://demos.digitalsamba.com/video/digital-samba-skill-demo.mp4) | Product demo showcasing Claude Code skill |
  125. | 2025-12-05 | [sprint-review-cho-oyu](https://demos.digitalsamba.com/sprint-review-cho-oyu.mp4) | iOS sprint review with demos |
  126. Videos other people have made with the toolkit are in [Show and tell](https://github.com/digitalsamba/claude-code-video-toolkit/discussions/categories/show-and-tell). Share yours there: a link, the template or tools you used, and what it cost.
  127. ### Scene Transitions
  128. The toolkit includes a transitions library for scene-to-scene effects:
  129. | Transition | Description |
  130. |------------|-------------|
  131. | `glitch()` | Digital distortion with RGB shift |
  132. | `rgbSplit()` | Chromatic aberration effect |
  133. | `zoomBlur()` | Radial motion blur |
  134. | `lightLeak()` | Cinematic lens flare |
  135. | `clockWipe()` | Radial sweep reveal |
  136. | `pixelate()` | Digital mosaic dissolution |
  137. | `checkerboard()` | Grid-based reveal (9 patterns) |
  138. Plus official Remotion transitions: `slide()`, `fade()`, `wipe()`, `flip()`
  139. Preview all transitions:
  140. ```bash
  141. cd showcase/transitions && npm install && npm run studio
  142. ```
  143. See [lib/transitions/README.md](lib/transitions/README.md) for full documentation.
  144. ### Brand Profiles
  145. Define visual identity in `brands/`. When you create a project with `/video`, the brand's colors, fonts, and styling are automatically applied.
  146. ```
  147. brands/my-brand/
  148. ├── brand.json # Colors, fonts, typography
  149. ├── voice.json # ElevenLabs voice settings
  150. └── assets/ # Logo, backgrounds
  151. ```
  152. Included brands: `default`, `digital-samba`
  153. Create your own with `/brand`.
  154. ### Project Management System
  155. Video projects are tracked through a multi-session lifecycle:
  156. ```
  157. planning → assets → review → audio → editing → rendering → complete
  158. ```
  159. Each project has a `project.json` that tracks:
  160. - **Scenes** — What to show, asset status, visual types
  161. - **Audio** — Voiceover and music status
  162. - **Sessions** — Work history across Claude Code sessions
  163. - **Phase** — Current stage in the workflow
  164. The system automatically reconciles intent (what you planned) with reality (what files exist), and generates a `CLAUDE.md` per project for instant context when resuming.
  165. See [lib/project/README.md](lib/project/README.md) for schema details, scene status tracking, and filesystem reconciliation logic.
  166. ### Python Tools
  167. Audio, video, and image tools in `tools/`:
  168. ```bash
  169. # AI voiceover — ElevenLabs or self-hosted Qwen3-TTS (9 voices + cloning)
  170. uv run tools/voiceover.py --provider qwen3 --speaker Ryan --scene-dir public/audio/scenes --json
  171. # AI music (ACE-Step — free cloud API)
  172. uv run tools/music_gen.py --preset corporate-bg --duration 120 --output music.mp3
  173. # AI image generation (FLUX.2) and editing (Qwen-Image)
  174. uv run tools/flux2.py --preset title-bg --brand digital-samba --cloud modal
  175. uv run tools/image_edit.py --input photo.jpg --prompt "Add sunglasses" --cloud modal
  176. # AI video generation (LTX-2.3 — text-to-video, image-to-video)
  177. uv run tools/ltx2.py --prompt "A sunset over the ocean, cinematic" --cloud modal
  178. # Talking head from a portrait + audio (SoulX-FlashHead)
  179. uv run tools/soulx.py --image portrait.png --audio voiceover.mp3 --output talking.mp4
  180. ```
  181. <details>
  182. <summary><strong>All tools</strong> — sound effects, redub, upscaling, watermark removal, NotebookLM rebranding, in-image text…</summary>
  183. ```bash
  184. # Generate voiceover (ElevenLabs)
  185. uv run tools/voiceover.py --script script.md --output voiceover.mp3
  186. # Generate voiceover (Qwen3-TTS — self-hosted, cheaper alternative)
  187. uv run tools/voiceover.py --provider qwen3 --speaker Ryan --scene-dir public/audio/scenes --json
  188. uv run tools/qwen3_tts.py --text "Hello world" --tone warm --output hello.mp3
  189. # Generate background music (ElevenLabs)
  190. uv run tools/music.py --prompt "Upbeat corporate" --duration 120 --output music.mp3
  191. # Generate background music (ACE-Step — free cloud API, XL Turbo 4B model)
  192. uv run tools/music_gen.py --preset corporate-bg --duration 120 --output music.mp3
  193. uv run tools/music_gen.py --prompt "Dramatic cinematic" --duration 30 --bpm 90 --key "D Minor" --output reveal.mp3
  194. uv run tools/music_gen.py --prompt "Upbeat indie rock" --duration 60 --variations 4 --output intro.mp3
  195. # Generate sound effects
  196. uv run tools/sfx.py --preset whoosh --output sfx.mp3
  197. # Find real recorded sound effects (Creative Commons, free, no API key)
  198. uv run tools/sfx_search.py --query "whoosh" --output sfx.mp3
  199. # Redub video with different voice
  200. uv run tools/redub.py --input video.mp4 --voice-id VOICE_ID --output dubbed.mp4
  201. # Add background music to existing video
  202. uv run tools/addmusic.py --input video.mp4 --prompt "Subtle ambient" --output output.mp4
  203. # Rebrand NotebookLM videos (trim outro, add your logo/URL)
  204. uv run tools/notebooklm_brand.py --input video.mp4 --logo logo.png --url "mysite.com" --output branded.mp4
  205. # AI image editing (style transfer, backgrounds, custom prompts)
  206. uv run tools/image_edit.py --input photo.jpg --style cyberpunk --cloud modal
  207. uv run tools/image_edit.py --input photo.jpg --prompt "Add sunglasses" --cloud modal
  208. # AI image upscaling (2x/4x)
  209. uv run tools/upscale.py --input photo.jpg --output photo_4x.png --cloud modal
  210. # Remove watermarks (requires cloud GPU)
  211. uv run tools/dewatermark.py --input video.mp4 --preset sora --output clean.mp4 --cloud modal
  212. # Locate watermark coordinates
  213. uv run tools/locate_watermark.py --input video.mp4 --grid --output-dir ./review/
  214. # Generate talking head video from image + audio (SoulX-FlashHead)
  215. uv run tools/soulx.py --image portrait.png --audio voiceover.mp3 --output talking.mp4
  216. # AI image generation (FLUX.2 klein 4B; klein-9B is a non-commercial Modal opt-in)
  217. uv run tools/flux2.py --prompt "A sunset over mountains" --cloud modal
  218. uv run tools/flux2.py --preset title-bg --brand digital-samba --cloud modal
  219. uv run tools/flux2.py --list-presets
  220. # AI video generation (LTX-2.3 22B — text-to-video + image-to-video)
  221. uv run tools/ltx2.py --prompt "A sunset over the ocean, cinematic" --cloud modal
  222. uv run tools/ltx2.py --prompt "Gentle camera drift" --input photo.jpg --cloud modal
  223. # 3D shots from a JSON spec (optional; needs Blender 4.2+, and a GPU to render in minutes: see docs/blender.md)
  224. uv run tools/blender_render.py doctor # is Blender here, and how fast is it?
  225. uv run tools/blender_render.py check examples/blender-disk-panic/spec.json # cameras verified, contact sheet, ~5 s
  226. uv run tools/blender_render.py render spec.json --clips --alpha --to projects/my-video/public/blender
  227. # Publish a finished render to YouTube (OAuth 2.0 + Data API v3) — contributed by @dascope (#29)
  228. uv run tools/youtube_upload.py --auth # one-time browser login
  229. uv run tools/youtube_upload.py --video out/video.mp4 --title "My video" --privacy private --json-out
  230. ```
  231. </details>
  232. **Tool Categories:**
  233. | Type | Tools | Purpose |
  234. |------|-------|---------|
  235. | **Project** | voiceover, music, music_gen, sfx, sfx_search | Used during video creation workflow |
  236. | **Utility** | redub, addmusic, notebooklm_brand, locate_watermark | Quick transformations, no project needed |
  237. | **Cloud GPU** | image_edit, upscale, dewatermark, sadtalker, soulx, qwen3_tts, flux2, music_gen, ltx2 | AI processing via Modal or RunPod |
  238. | **Checks** | qc, sync_check, contact_sheet | Before showing a render: freezes and motion that stops dead, loudness, layout, sound effects on their movement |
  239. | **Publishing** | youtube_upload | Upload a finished render to YouTube (or use `/publish`) |
  240. | **3D (optional)** | blender_render | Character acting, 3D reveals, product shots and logo idents from a shot spec; does nothing unless Blender is installed |
  241. | **Brand** | mark_sheet | A logo at every size, on every ground, in a circle and as a watermark, with warnings, before it is used |
  242. ### Cloud GPU (Modal + RunPod)
  243. 8 AI tools run on cloud GPUs. Use `--cloud modal` (recommended) or `--cloud runpod` on any tool.
  244. | Tool | What It Does | Est. Cost |
  245. |------|--------------|-----------|
  246. | `qwen3_tts` | AI text-to-speech (9 speakers, voice cloning) | ~$0.01 |
  247. | `flux2` | AI image generation & editing | ~$0.02 |
  248. | `image_edit` | AI image editing & style transfer | ~$0.03 |
  249. | `upscale` | AI image upscaling (2x/4x) | ~$0.01 |
  250. | `music_gen` | AI music generation (8 scene presets) | Free (acemusic) / ~$0.05 (self-hosted) |
  251. | `soulx` | Talking head video from portrait + audio — holds identity over long takes | ~$0.0024/sec |
  252. | `sadtalker` | Talking head video, warp-based — fast, cheap drafts | ~$0.10 |
  253. | `ltx2` | AI video generation (text-to-video, image-to-video) | ~$0.23 |
  254. | `ltx_extend` | Lengthen an LTX clip by continuing it from its last good frame, instead of holding or looping it | ~$0.08 per extension |
  255. | `dewatermark` | Video watermark removal | ~$0.10 |
  256. **Modal (recommended):** Each tool deploys from `docker/modal-*/app.py` — Modal builds and hosts the containers. $30/month free compute on the Starter plan, typical usage is $1-2/month. Run `/setup` to deploy all tools automatically.
  257. **RunPod (alternative):** Uses pre-built Docker images from `ghcr.io/conalmullan/video-toolkit-*`. Pay-per-second, no minimums. Run `uv run tools/<tool>.py --setup` to create endpoints.
  258. See [docs/modal-setup.md](docs/modal-setup.md) and [docs/runpod-setup.md](docs/runpod-setup.md) for details.
  259. ## Project Structure
  260. ```
  261. claude-code-video-toolkit/
  262. ├── .claude/
  263. │ ├── skills/ # Domain knowledge for Claude
  264. │ └── commands/ # Slash commands (/video, /brand, etc.)
  265. ├── lib/ # Shared components, theme system, utilities
  266. │ ├── components/ # Reusable video components (11 components)
  267. │ ├── transitions/ # Scene transition effects (7 custom + 4 official)
  268. │ ├── theme/ # ThemeProvider, useTheme
  269. │ └── project/ # Multi-session project system
  270. ├── tools/ # Python CLI tools
  271. ├── templates/ # Video templates
  272. ├── brands/ # Brand profiles
  273. ├── projects/ # Your video projects (gitignored)
  274. ├── examples/ # Curated showcase projects with finished videos
  275. ├── assets/ # Shared assets
  276. ├── playwright/ # Recording infrastructure
  277. ├── docs/ # Documentation
  278. └── _internal/ # Toolkit metadata & roadmap
  279. ```
  280. ## Documentation
  281. - [Getting Started](docs/getting-started.md)
  282. - [Modal Setup](docs/modal-setup.md) — Cloud GPU with Modal (recommended)
  283. - [RunPod Setup](docs/runpod-setup.md) — Cloud GPU with RunPod (alternative)
  284. - [Creating Templates](docs/creating-templates.md)
  285. - [Creating Brands](docs/creating-brands.md)
  286. - [Project System](lib/project/README.md) — Multi-session lifecycle, schema, reconciliation
  287. - [Optional Components](docs/optional-components.md) — Local GPU tools setup
  288. - [Blender](docs/blender.md): 3D shot specs (optional): setup, what your machine needs, timings, what it has been run on, and how a character film is made over several sessions
  289. - [Voiceover](docs/voiceover.md): ElevenLabs, Qwen3-TTS and 60db, and fixing a cloned voice that is flat or rushed
  290. - [Timing](docs/timing.md): word budgets, scene durations, TTS drift and audio-anchored timelines
  291. - [QC](docs/qc.md): what `qc.py` checks before and after a render, loudness, and sound effects placed on movement
  292. - [Captions](docs/captions.md): burned word captions, SRT and VTT
  293. - [Image Tools](docs/image-tools.md): cloud GPU providers, FLUX.2 or Ideogram 4, image editing, upscaling, watermark removal
  294. - [Music and Sound](docs/music-and-sound.md): ACE-Step music, choosing a take, ducking under speech, stock sound effects
  295. - [Reusing a Video](docs/repurposing.md): cut-downs to 9:16 and 1:1, transcript highlights, redub, NotebookLM branding
  296. - [Agent Video Jobs](docs/agent-video-jobs.md) — Brief in, MP4 out for any agent: `video_job.py` submit/status/result, the MCP server, and the `skills/video-toolkit/` skill for OpenClaw, Codex, Hermes and friends
  297. - [Toolkit Development](_internal/ROADMAP.md) — Roadmap, backlog, changelog
  298. ## Video Workflow
  299. ```
  300. /video → Script → Assets → Scene Review → Design → Audio → Preview → Render → Publish
  301. ```
  302. 1. **Create project** — Run `/video`, choose template and brand
  303. 2. **Review script** — Edit `VOICEOVER-SCRIPT.md` to plan content and assets
  304. 3. **Gather assets** — Record demos with `/record-demo` or add external videos
  305. 4. **Scene review** — Run `/scene-review` to verify visuals in Remotion Studio
  306. 5. **Design** — `/video` sets the design direction before scenes are built; `/design` changes it, refines a scene with `video-design`, or critiques the render
  307. 6. **Generate audio** — AI voiceover with `/generate-voiceover`
  308. 7. **Configure** — Update config file with asset paths and timing
  309. 8. **Preview** — `npm run studio` for live preview
  310. 9. **Iterate** — Work with Claude Code to adjust timing, styling, content
  311. 10. **Render** — `npm run render` for final MP4
  312. ## Using with Codex
  313. The toolkit is built for Claude Code, but an experimental migration script installs its skills and workflows for [Codex](https://openai.com/codex/) and generates an `AGENTS.md` block from `CLAUDE.md`:
  314. ```bash
  315. uv run scripts/migrate_to_codex.py --force
  316. ```
  317. See [docs/codex.md](docs/codex.md) for what it installs, how the `AGENTS.md` block is managed, and how to remove it. Contributed by [@kimhoontae-gogo](https://github.com/kimhoontae-gogo) in [#16](https://github.com/digitalsamba/claude-code-video-toolkit/pull/16).
  318. ## Using with Kiro CLI
  319. A sibling migration script installs the toolkit's skills and workflows for [Kiro CLI](https://kiro.dev/) — `/video`, `/setup`, etc. work as slash commands, from any directory:
  320. ```bash
  321. uv run scripts/migrate_to_kiro.py --force
  322. ```
  323. See [docs/kiro.md](docs/kiro.md) for what it installs, how it achieves Claude Code-parity, and how to remove it.
  324. ## Design sources
  325. **Plug in your own design skill, or use ours.** `/design` and `/scene-review` take their visual direction from the
  326. source you choose, then apply the toolkit's own video rules (`video-design`) and critique the render from a contact
  327. sheet. The choice is saved per project; nothing here depends on one particular skill.
  328. | Source | What it's good for | Install |
  329. |--------|--------------------|---------|
  330. | Ours (default) | `video-design`'s act palettes and rules, with your brand's colours and fonts | Nothing to install |
  331. | [taste-skill](https://github.com/Leonxlnx/taste-skill) (recommended plug-in) | Dealt directions and palettes from 247 studied sites, measured house rules, a juror's critique (MIT) | `/plugin marketplace add Leonxlnx/taste-skill` then `/plugin install taste-skill@taste-skill` |
  332. | [frontend-design](https://github.com/anthropics/skills) | Anthropic's general visual direction for interfaces (written for web pages) | See the anthropics/skills README |
  333. Bring your own: any design skill works if it can fill `design.md` (palette per act, ink, one accent, type).
  334. To list one here, open an issue with a link, its licence, and a contact sheet of `examples/data-chart-stars`
  335. restyled with it. See [`.claude/skills/video-design/sources.md`](.claude/skills/video-design/sources.md).
  336. ## Community add-ons
  337. Projects built on or around the toolkit that live in their own repos — typically because they need
  338. software or a service we can't bundle. We haven't reviewed them; check each project's README.
  339. | Add-on | What it does | Needs |
  340. |--------|--------------|-------|
  341. | [VOICEPEAK for voiceover.py](https://github.com/fialuxe/claude-code-video-toolkit-expand-ja-voicepeak/) | Offline Japanese TTS provider (patches `voiceover.py`) | VOICEPEAK (paid, local) |
  342. | [arkiv](https://github.com/vulture-s/arkiv) | Natural-language search (EN/中文/日本語) over your own footage archive, returning scenes with start/end timecodes to use as a template's `videoFile` | A local arkiv instance (source-available, PolyForm Perimeter) |
  343. | [Upload-Post publishing](https://github.com/Upload-Post/claude-code-video-toolkit-upload-post) | Publish a rendered video to TikTok, Instagram, YouTube, LinkedIn, Facebook, X, Threads, Pinterest and Bluesky via a `/publish-social` command | An Upload-Post account and API key (hosted, free plan available) |
  344. | [CommentKeyword comment-to-DM](https://github.com/commentkeyword/agent-toolkit/tree/main/integrations/claude-code-video-toolkit) | Sets up the Instagram auto-DM behind a video's "Comment KEYWORD" CTA, armed for the next post, via a `/comment-dm` command | A CommentKeyword account and API token (hosted, free plan available; Instagram only) |
  345. | [easybrandkit](https://github.com/EminBudak/easybrandkit) | Reads a live site's logo, colors and fonts into a BRAND.md that `/brand` can start from | Node 22 and Chrome, Chromium, Edge or Brave |
  346. To be listed, open an issue with a link and a one-line description. Integrations that need a
  347. hosted third-party service live here rather than in the toolkit itself — see
  348. [CONTRIBUTING.md](CONTRIBUTING.md) for why, and for how the few exceptions came about.
  349. ## Contributing
  350. Contributions welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
  351. ## License
  352. MIT License — see [LICENSE](LICENSE) for details.
  353. ---
  354. Built for use with [Claude Code](https://claude.ai/code) by Anthropic.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.