CONTENT CREATION

Podcast Episode to Show Notes, Chapters, and Clip Timestamps

When a new episode audio file lands in Dropbox, transcribe it, then generate publish-ready show notes, timestamped chapter markers.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps4
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew audio file in Dropbox episode folderDropboxDropbox
  • ActionTranscribe audio with timestampsElevenLabsElevenLabs
  • ActionGenerate summary, chapters, and clip candidatesOpenAI
  • OutputCreate populated show-notes page in NotionNotionNotion

What it does

Turns a finished episode recording into everything the publishing team needs in one pass: a clean summary, chapter markers with timestamps, and a shortlist of the most clip-worthy moments for social. The output lands in a structured Notion page ready for review.

When to use it

Use it the moment an editor drops the final mixed audio into a shared Dropbox folder. It removes the manual listen-through where someone scrubs the timeline writing chapters and hunting for clips, cutting episode turnaround from hours to minutes.

How it works

  1. 1A new audio file appearing in the watched Dropbox folder triggers the flow.
  2. 2ElevenLabs transcribes the audio into a timestamped, speaker-labeled transcript.
  3. 3An OpenAI step reads the transcript and drafts the episode summary, three to seven chapter markers with start times, and five clip candidates ranked by hook strength, each with a start/end timestamp and a one-line reason.
  4. 4A Notion page is created from the show-notes template and populated with the summary, chapters, and clip table.

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 OpenAIModels, embeddings, files.
  4. 4
    Connect NotionPages, databases, comments.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.