Automation library · Content

Find and render short video clips from transcripts

Started by an event in a connected app, and works across Google Drive and n8n data table. It hands the judgement calls to OpenAI. 24 steps, 4 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAI

Download free
24 stepsLarge: read it before trusting it with anything live
4Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 1Model 3Logic 11Service 9

The steps in the order they run, from what starts it.

  1. 1New video or transcript arrivesGoogle Drive triggerStarts it
  2. 2Clip finder modelLm Chat Open AiModel
  3. 3Candidate clip schemaOutput Parser StructuredModel
  4. 4SettingsSetLogic
  5. 5Ask the model for candidate clipsAgentModel
  6. 6Download the transcript fileGoogle DriveService
  7. 7Did the model find any candidates?IfLogic
  8. 8Parse the transcriptCodeLogic
  9. 9Log unparsable source to dead letterData TableService
  10. 10Split into individual candidate clipsSplit OutLogic
  11. 11Prepare the honest empty summarySetLogic
  12. 12Skip clips already processedData TableService
  13. 13Log the run summaryData TableService
  14. 14Run the quality gateCodeLogic
  15. 15Did the clip pass the quality gate?IfLogic
  16. 16Combine every clip's gate resultAggregateLogic
  17. 17Render the clipHttp RequestService
  18. 18Record the clip in the review queueData TableService
  19. 19Build the honest run summaryCodeLogic
  20. 20Did the render produce a valid file?IfLogic
  21. 21Log the failed render to dead letterData TableService
  22. 22Record the clip in the drafts queueData TableService
  23. 23Should this clip publish automatically?IfLogic
  24. 24Publish the clipHttp RequestService

How it's built

Starts on
An event in a connected app
Steps
24, with 4 branches
Size
Large: read it before trusting it with anything live
Connects to
Google Drive, n8n data table
Model
OpenAI

Questions

What does it need to run?

An n8n account, plus your own Google Drive account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 24 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 24 steps before you point it at anything that matters.