Menu
Free Video skillFootage videos

Narrated Footage Video

Combine your footage with a script, narration and subtitles using the pinned MoneyPrinterTurbo workflow.

Current FeedSkills page captures with reused narration and supplied captions · complete listening review pending 9:16 · 0:33

What you get

  • A composed MP4 and inspectable task directory
  • Narration and optional subtitles
  • Cached intermediate files for revisions

You will need

  • Python 3.11, uv, FFmpeg and FFprobe
  • First use downloads the pinned upstream source and locked dependencies
  • Local footage and a script; supplied audio or optional online TTS
  • Automatic writing or stock sourcing needs the user’s provider account; generated media may incur charges

Good fit

  • Turning owned footage into a narrated short
  • Revising the script while retaining source media

Not for

  • Invented footage or guaranteed stock rights
  • Unverified subtitles from supplied audio

You say

“Read the installed SKILL.md. Use my topic and inputs, identify missing requirements, and create the declared deliverables. Keep factual evidence, service calls and unverified steps explicit.”

After installing, say something like this to your agent with your own topic and assets. It asks only for what is missing.

FAQ

Do I need an account?

No. Copy the install prompt into your agent, or download the free ZIP.

What does it cost to run?

The Skill is free. It needs the tools listed under “You will need”. Any voice, model or media service you choose bills you directly; FeedSkills does not include provider credits.

Can I use the videos commercially?

Videos you make are yours to use, including commercially. The Skill package is licensed as: MIT. Fonts, music, footage and services you add keep their own terms.

Which agents does it work with?

Agents that read SKILL.md files, such as Codex or Claude Code. What FeedSkills has actually tested is listed under Tested scope below.

Tested scope

Version
0.1.1
Acceptance
Acceptance for this version is still pending. It remains installable; check what has been tested before relying on it.
Tested
Two owned-page themes and one sentence revision rendered using the pinned MoneyPrinterTurbo, previously generated Edge narration and a supplied-caption FFmpeg pass. Static page cuts follow the script. Decode and caption-tail checks passed; full independent listening, other providers, transcription and fresh-system validation remain unverified.
Runs on
Codex · macOS · see dependencies
License
MIT

Details

Turn owned footage into a narrated short

Supply a script and local images or video. The pinned MoneyPrinterTurbo workflow combines the material with narration, optional subtitles and optional rights-cleared background music, then keeps the output and intermediate files in an inspectable task directory.

The helper checks local inputs before installing the fixed upstream source. It verifies the source archive checksum and uses the upstream locked Python environment. It does not bundle media, model weights or credentials.

Choose the services you need

A supplied script and local footage avoid LLM and stock-provider requests. You can provide local narration audio or use an online TTS service. The default Edge voice sends narration text to Microsoft’s service. Supplied audio needs a separate subtitle transcription path; a subtitle file is not proof of accurate words or timing.

Automatic writing, stock search and AI-generated material use your own configured providers. Some require paid accounts or per-request charges. Check the installed Skill’s service and data notes before enabling them.

Keep revisions inspectable

Create a separate output root for a new cut, retain the source media, and change the requested script or option. Compare the finished picture, narration and captions with the previous version. A successful task record or decoded MP4 proves only the technical path; review the full cut before publishing.