CONTENT CREATION

Length-gated show notes builder: full kit for long episodes, brief for short ones

On a manual trigger, transcribe an episode and branch on its length — long episodes get full show notes plus quote cards, short ones get a lightweight summary only.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggermanual
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerManually start run with episode file
  • ActionTranscribe audio and capture durationElevenLabsElevenLabs
  • LogicBranch on episode length vs threshold
  • ActionLong path: full show notes + quote cardsImage generation
  • ActionShort path: brief summary onlyOpenAI
  • OutputFile assets to Notion under the episodeNotionNotion

What it does

Processes an episode you submit manually and decides how much asset production it deserves based on runtime. Long-form episodes get the full treatment — detailed show notes and rendered quote cards — while short clips or bonus segments get a quick summary, so you never over-invest effort on a five-minute bonus drop.

When to use it

Use it when your feed mixes flagship long-form episodes with shorter bonus or trailer content and you want a single intake that right-sizes the output automatically.

How it works

  1. 1You start the run manually and point it at the episode audio in Dropbox.
  2. 2ElevenLabs transcribes the audio and returns the duration.
  3. 3A logic step branches on episode length against a threshold you set.
  4. 4For long episodes, the LLM writes full show notes and selects quotes, and generate-image renders quote cards.
  5. 5For short episodes, the LLM writes a brief summary only.
  6. 6The output step files the resulting assets to Notion under the episode.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DropboxFiles and folders.
  2. 2
    Connect ElevenLabsText-to-speech, voice cloning.
  3. 3
    Connect Image generationManaged Nano Banana image renders, metered per image.
  4. 4
    Connect NotionPages, databases, comments.
  5. 5
    Connect OpenAIModels, embeddings, files.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.