# Video Podcast Maker Nano

Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not...

- Repository: https://github.com/Agents365-ai/video-podcast-maker (1708 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Agents365-ai/video-podcast-maker --skill video-podcast-maker-nano -g -a claude-code -y`
Codex: `npx skills add Agents365-ai/video-podcast-maker --skill video-podcast-maker-nano -g -a codex -y`
Cursor: `npx skills add Agents365-ai/video-podcast-maker --skill video-podcast-maker-nano -g -a cursor -y`
Gemini CLI: `npx skills add Agents365-ai/video-podcast-maker --skill video-podcast-maker-nano -g -a gemini-cli -y`

## Description

Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default, topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints; any TTS backend and any video tool (Remotion, HyperFrames, CapCut, ...) work, and how much human oversight to apply is set by the working project's AGENTS.md/CLAUDE.md, not here. Use when the user wants a quick personal narrated video with minimal steps, whether or not they name the tool stack. Do NOT trigger for audio-only podcasts, written episodic content, or heavy multi-format production.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Video Podcast Maker Nano

A 7-step pipeline for personal use: **research ∥ materials → script → TTS → audio checkpoint → video → preview checkpoint → 4K render ∥ publish kit**. No bundled scripts, no hardcoded backends, no templates. The skill owns the *logic* and runs autonomously by default; the TTS backend and video tool are chosen per video (see [Tool selection](#tool-selection-per-video)).

What makes this work regardless of tool choice, the three invariants:

1. **Checkpoints are never skipped, but who checks is policy.** Three checkpoints exist: script (after Step 2), audio (after Step 3), preview (before render). Default checker is the agent itself (self-verification, defined per checkpoint); a project's AGENTS.md/CLAUDE.md may upgrade any checkpoint to a human gate, see [Oversight policy](#oversight-policy).
2. **Audio is the master clock.** The final video's duration must match the narration audio within ±0.5s (`ffprobe` both). Visuals are cut to the audio, never the reverse.
3. **A script change invalidates everything downstream.** Edit the script → re-run the script checkpoint, then TTS → audio checkpoint → visuals → preview checkpoint → render. Never hand-patch timings.

## Oversight policy

Default mode is **autonomous**: the pipeline runs end to end, with the agent performing every checkpoint's self-verification. A working project's AGENTS.md/CLAUDE.md can override per checkpoint with one line each:

- `Checkpoint 1 (script): human`, halt after Step 2 until the user approves the script. Worth it: a late script change costs a full re-run.
- `Checkpoint 2 (audio): human`, the user listens to the full audio before visuals. Worth it when TTS misreadings are costly to catch later.
- `Checkpoint 3 (preview): human`, the user reviews the draft before render. Worth it for style-sensitive channels.

The rest: https://github.com/Agents365-ai/video-podcast-maker/blob/HEAD/skills/video-podcast-maker-nano/SKILL.md