#3737th of 56 in Image and videoFor image, video and design, video and animation
digital-human-koubo
Agent skill that turns a photo and a prompt into a talking-head video
- Stars
- 1.9k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
1,180 on 27 Oct 20261,935 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
An Agent Skill (SKILL.md plus Python, shell and Remotion scripts) that drives an AI agent through script writing, lip-synced presenter clips via Renoise MCP (Grok Video 1.5), whisper QA, voice unification and Remotion editing. It ships five editing templates and 48 packaging components, and adds a cover as the first frame. Generation is paid through Renoise credits, and the agent quotes the cost before batching.
Who it is for: Creators who use Claude Code or Codex to produce AI presenter videos
Strengths
- Cost quote and first-segment approval before batch generation
- Whisper back-check and frame inspection catch wrong words and burned-in subtitles
- Fixed presenter in persona.json keeps the same face across videos
- Five Remotion style templates with 48 named packaging components, 9:16 adaptive
Weaknesses
- Video generation requires a Renoise account and paid credits
- Text-behind-presenter effect needs macOS Apple Vision
- Needs an agent that loads skills, connects MCP and runs local commands
- Swapping in a different voice leaves about 100 ms lip offset
What it needs
- no GPU
- Needs Renoise MCP (renoise.ai account, credits), ffmpeg, Python 3 with numpy and Pillow, Node.js 18+ (Remotion), whisper.cpp with ggml-medium-q5_0 model, Playwright + Chromium, Xiaomi MiMo TTS API (optional)
- Models: Grok Video 1.5, Wan 3.0, OmniHuman, GPT Image 2.5, Xiaomi MiMo TTS
Quick answers
Is digital-human-koubo open source?
Yes. Its code is on GitHub under the MIT license.
Does digital-human-koubo need a GPU?
No, it runs without one.
Also in Image and video
See all 56| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 92 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 86 out of 100 |
| #4 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |
| #5 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 85 out of 100 |