Claude Code Video Toolkit
Claude Code Video Toolkit is an agent skill in our Code-to-video engine category. Digital Samba's MIT workspace and skills for Claude Code: describe a video and it writes the script, makes voiceover, music, images and clips on open models (Qwen3-TTS, FLUX.2, ACE-Step) on your own cloud GPU account, then renders with Remotion; per the README its 90 s self-explainer cost $0.33. Optional Blender support (v0.28-0.29, Nov 2026): 3D character films from one JSON spec, with shots by type, acting as verbs timed to narration, a pre-render body/camera check and transparent clips for Remotion.
Where it fits: Remotion, Audio, voice & music, Open-weight video & audio models.
Listing isn’t endorsement. This is our summary of the project’s own docs. Check the licence and requirements at the source before you build on it.
Lab posts that cover Claude Code Video Toolkit
Related Lab posts
- OpenMotion 0.2.0 adds seven studios for images, voice, video and 3D; plus LTX's SDR-to-HDR comparison, Kling Image 4.0 in ComfyUI and HyperFrames 0.9.72
- huashu-motion: an open skill that writes the launch film, scores it, and lets you point at the frame to fix it
- anything2explainer: a topic in, a sourced, narrated explainer out (non-commercial licence)
- Comfy's lip-sync dubbing workflow redraws only the mouth: one shot into any language with ElevenLabs and MiniMax H3; plus Genie 4 and HeyGen Decision 1 in ComfyUI
- Remotion 4.0.545 adds real motion blur: ask your agent, click a button, or wrap a component
Similar skills & repos
- story-to-handdrawn-video · Skill, Code-to-video engine
- motlab · Skill, Code-to-video engine
- Motion Canvas · Repo, Code-to-video engine
- Cinematic Skill · Skill, Code-to-video engine
- cangshu koubo video skills · Skill, Motion graphics
- cinecode · Skill, Code-to-video engine