Skip to content
← All projects

Automation · Media

Automated media production chain

A pipeline that produces narrated videos, from script to edit, stopping at every step for me to approve.

  • 7episodes ready to publish
  • < $2per finished episode, all in
  • 3series
Role
I designed the pipeline and its steps, set the approvals and the budget, and had it built with coding assistants.
Period
July 2026 — ongoing
Status
In development
Team
Personal project
A frame from the episode "The Crow and the Fox" in YouTube format: the fox, in a waistcoat, looks up at the crow, with the English subtitle.
The fox in close-up, in the vertical episode of The Crow and the Fox.

At a glance

  1. 1The problem

    Producing narrated videos regularly means going through about ten jobs: script, characters, images, voice, editing, subtitles. None is hard, but repeating them every week quickly becomes unsustainable.

  2. 2Solution

    A six-step pipeline, from topic to a video ready to publish, with my approval between each step and a maximum budget per episode.

  3. 3The result

    Production becomes regular and its cost is known in advance, without letting the machine decide on the content.

Where it stands · Ongoing. The pipeline produces complete episodes, but publishing is still done by hand.

In pictures

A frame from the episode "The Crow and the Fox" in YouTube format: the fox, in a waistcoat, looks up at the crow, with the English subtitle.
The Crow and the Fox, in YouTube format. The seven ready episodes are in English.
The fox in close-up, in the vertical episode of The Crow and the Fox.
The Crow and the Fox
The hare and the tortoise at the starting line, in the vertical episode.
The Hare and the Tortoise
The lamb by the stream, in the vertical episode of The Wolf and the Lamb.
The Wolf and the Lamb
The cicada in a winter field, in the vertical episode of The Cicada and the Ant.
The Cicada and the Ant

The project

I wanted to produce narrated videos regularly: La Fontaine's fables, and a story set in ancient Rome. Each video takes about ten different jobs: writing the script, keeping characters consistent, creating images, voice, editing, subtitles, delivery.

No single step is hard. Repeating them every week is what does not hold up.

Why not one program that does it all

The first reflex is a single program that goes from topic to finished video. It does not work, for three reasons.

When it breaks, you lose everything. One error halfway, on an image, and all the earlier work has to be redone.

You find out the cost afterwards. Generated images and voices are paid per use. Without a limit, you learn what an episode cost once it is finished.

Automating everything gives a worse result. A pipeline that picks its own topics and publishes without review produces exactly the kind of content platforms push down.

What I built

A six-step pipeline, each step independent, with an approval between each one.

An approval between every step. Nothing goes from topic to publication without me seeing the result.
  • A step can fail without breaking everything. Progress is kept, and you pick up where it stopped.
  • The budget is set upfront. If the cost goes over the cap, the pipeline stops rather than carrying on.
  • Every step waits for my go-ahead. AI does the production, not the choices.

What the pipeline does not do

It does not find its own topics or fact-check: it starts from a topic I give it. And it does not publish on its own: it prepares a complete episode, ready to go, which I put online myself.

Show technical details

The steps

They cover the script, character consistency, images, voice, editing, music, checks, delivery, publishing, progress tracking, a report and a dashboard. Progress tracking is the central piece: it is what makes it possible to resume at the step that failed.

Editing

Everything goes through FFmpeg: still images animated with a camera movement, subtitles, mixing voice and music, adjusting the volume.

Short formats

A separate tool produces vertical clips in 1080 × 1920, with subtitles generated by automatic transcription and volume adjusted for social media.

Budget

The cap is read at start-up. Every paid generation is counted, and the pipeline stops cleanly, keeping its progress, if the cap is reached.

What I did

  1. 01ArchitectureI split production into independent steps, so a failing step does not bring the others down.
  2. 02Needs definitionI decided what should be automated (production) and what should not (choosing the content).
  3. 03Assisted developmentThe pipeline was written in Python with coding assistants, using FFmpeg for editing and automatic transcription for subtitles.
  4. 04Quality controlI set an approval between every step and a maximum budget per episode.
  5. 05DocumentationI documented how the pipeline works, the tools it uses and its limits.

Numbers

7

episodes ready to publish

a complete series of fables, produced end to end

Source · ready-to-publish episodes directory

< $2

per finished episode, all in

actual cost of the seven episodes, from $1.04 to $1.59 each, script, images, voice and checks included

Source · costs recorded by the pipeline in each episode's progress file

3

series

three worlds, each with its own visual style and characters

Source · project episodes directory

Evidence

  • Independent steps

    verified

    Each step is independent and keeps track of its progress. A step can be rerun without restarting everything, and a failure does not wipe out the work already done.

    Source
    project pipeline directory
    Verify with
    Listed the steps and read the progress tracking.
  • Seven episodes produced

    verified

    A complete series was produced by the pipeline, from script to an edited, subtitled video ready to publish.

    Source
    ready-to-publish episodes directory
    Verify with
    Listed the episodes on disk.
  • A maximum budget per episode

    verified

    The pipeline stops if the cost of generation goes over a cap set in advance. You know what an episode costs before launching it, not after.

    Source
    chain configuration
    Verify with
    Reading the configuration and the budget control mechanism.
  • Short formats

    verified

    A separate tool turns a video into a vertical clip for social media: cutting, automatic subtitles and adjusted volume.

    Source
    the project's vertical formatting tool
    Verify with
    Read the tool and its settings.

Limitations

  • Publishing is not automatic: the pipeline prepares an episode ready to go, and I put it online myself.
  • The pipeline does not find its own topics and does not fact-check. It starts from a topic I give it.
  • It depends on external services for images and voices. If their prices or how they work change, part of it has to be redone.

What I take away

  • The reflex is to want to automate everything. The real gain comes from automating repetitive production and keeping the content choices, where the difference is made.
  • Splitting into independent steps changes everything: when a single-block pipeline breaks halfway, you lose it all. With steps, you pick up where it broke.
  • A hard budget set before launching beats a cost-tracking dashboard you look at afterwards.

What it could bring to a company

  • A marketing team can organise its content production the same way: assisted generation, approval at every step, controlled cost.
  • A training team can produce internal videos from approved scripts, with automatic subtitles.
  • Any repetitive multi-step task (reports, product sheets, translations) can be split the same way, to resume at the step that failed.
TechnologiesPythonFFmpegWhisperBashImage and voice generation APIs

Does this project speak to you?

Let's talk about what I could bring to your team.

Get in touch →