kevinbadi/ai-os-skills · Archived
Clone Kevin's videos as Kev's Assistant using AI face swap + voice clone + WAN 2.2 animate.
npx skills add kevinbadi/ai-os-skills --skill wan-video-clone
This repository is archived — consider an actively maintained alternative.
Post text and optional image content to LinkedIn via browser automation. Use when creating Link…
5 installsScrape users who liked specific Instagram posts using Apify actor WxPRaG9gfg5KZ4gY1 (datadoping…
5 installsSend Facebook Messenger DMs as a personal account to business pages via Playwright + facebook.c…
5 installsEnd-to-end longform video cloning pipeline. Downloads YouTube video, transcribes, generates Hey…
4 installsRelated neighbors and high-traction skills in the same topics — useful to compare before installing.
Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn…
3.6K installsGenerate a report about a video
2.3K installs>- Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection…
1.9K installsUse to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VL…
1.9K installsUse this skill to ask the VSS agent's video_understanding tool a fresh visual question about a …
1.8K installsUse this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-rang…
1.8K installsOther skills from kevinbadi/ai-os-skills · top by installs.
npx skills add kevinbadi/ai-os-skills
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Files included with this skill beyond the listing page.
SKILL.md
4,370 B
SUMMARY.md
358 B
Takes Kevin's video in, splits it into ~30s chunks, runs each through the AI pipeline, stitches them back together. Out the other side: Kev's Assistant talking in Kevin's chair with Kev's Assistant's voice.
Kevin's Video
│
▼
┌─────────────────────┐
│ ffmpeg split (~5s) │
└────────┬────────────┘
│
┌────▼────┐
│ chunk_0 │ chunk_1 chunk_2 ...
└────┬────┘
│ For each chunk:
├─ Extract audio (ffmpeg local)
├─ Voice clone → Kev's Assistant (ChatterboxHD / fal.ai)
├─ Merge cloned audio back (ffmpeg local)
├─ Upload merged chunk to fal.ai
├─ WAN 2.2 animate/replace (Kev's Assistant face + chunk)
└─ Download output chunk
│
┌────▼────────────────┐
│ ffmpeg stitch all │
└────────┬─────────────┘
│
▼
Kev's Assistant's VideoFAL_KEY env var (fal.ai API key)ffmpeg installedassets/kevs-reference.png — Kev's Assistant face reference imageassets/kevs-voice-sample.mp3 — Kev's Assistant voice sample for cloningREPLICATEAPITOKEN (not needed if using local ffmpeg for audio)# Basic — clone a video
node skills/wan-video-clone/scripts/wan-video-clone.js \
--video "https://example.com/kevin-video.mp4"
# Local file
node skills/wan-video-clone/scripts/wan-video-clone.js \
--video /path/to/kevin.mp4
# Custom chunk size (default 5s)
node skills/wan-video-clone/scripts/wan-video-clone.js \
--video "URL" --chunk-duration 5
# Process 2 chunks at a time (parallel)
node skills/wan-video-clone/scripts/wan-video-clone.js \
--video "URL" --parallel 2
# Skip voice clone (face only)
node skills/wan-video-clone/scripts/wan-video-clone.js \
--video "URL" --skip-voice
# Skip face swap (use Kev's Assistant ref image directly with WAN)
node skills/wan-video-clone/scripts/wan-video-clone.js \
--video "URL" --skip-face-swap
# Dry run (show plan without executing)
node skills/wan-video-clone/scripts/wan-video-clone.js \
--video "URL" --dry-run| Flag | Default | Description |
|---|---|---|
--video |
required | Source video URL or local path |
--chunk-duration |
30 |
Seconds per chunk |
--parallel |
1 |
Max concurrent chunk processing |
--resolution |
720p |
WAN output resolution |
--kevs-image |
auto | Kev's Assistant face image URL (uses asset if not set) |
--kevs-voice |
auto | Kev's Assistant voice sample URL (uses asset if not set) |
--prompt |
auto | Face swap prompt for Nano Banana |
--skip-voice |
false | Skip voice cloning step |
--skip-face-swap |
false | Use Kev's Assistant ref image directly |
--output |
output/wan-clones/ |
Output directory |
--dry-run |
false | Show plan without executing |
Final video saved to output/wan-clones/<timestamp>/kevs-assistant-clone-<timestamp>.mp4
fal-ai/nano-banana-pro/edit)resemble-ai/chatterboxhd/speech-to-speech)fal-ai/wan/v2.2-14b/animate/replace)