Automation library · Content

Generate cinematic videos from text prompts with OpenAI

Started by an event in a connected app, and works across Google Sheets and YouTube. It hands the judgement calls to OpenAI. 34 steps, 4 branches, 5 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAI

34 stepsLarge: read it before trusting it with anything live
4Branches: places the flow splits
5Loops or waits
2Services it connects to

The flow

Starts it 1Model 9Logic 12Service 12

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

  1. 1Structured Output ParserOutput Parser StructuredModel
  2. 2Structured Output Parser1Output Parser StructuredModel
  3. 3OpenAI Chat ModelLm Chat Open AiModel
  4. 4OpenAI Chat Model1Lm Chat Open AiModel
  5. 5Structured Output Parser2Output Parser StructuredModel
  6. 6OpenAI Chat Model2Lm Chat Open AiModel
  7. 7When clicking ‘Execute workflow’Manual triggerStarts it
  8. 8Generate Full Narrative from PromptAgentModel
  9. 9Break Narrative into {{n}} ScenesAgentModel
  10. 10Describe Each Scene for VideoAgentModel
  11. 11Get DataGoogle SheetsService
  12. 12Verify number of sceneCodeLogic
  13. 13Call Fal.ai API (Seedance)Http RequestService
  14. 14Scene countIfLogic
  15. 15Loop Over ItemsSplit In BatchesLogic
  16. 16Split OutSplit OutLogic
  17. 17Start adding audio to the videoHttp RequestService
  18. 18Wait for the videoWaitLogic
  19. 19Loop Over Items1Split In BatchesLogic
  20. 20Get the video statusHttp RequestService
  21. 21Aggregate videos with audioAggregateLogic
  22. 22Wait for adding the audioWaitLogic
  23. 23Video statusSwitchLogic
  24. 24Start merging videosHttp RequestService
  25. 25Get audio statusHttp RequestService
  26. 26Get the videoHttp RequestService
  27. 27Wait for the merge to completeWaitLogic
  28. 28Audio statusSwitchLogic
  29. 29Get merge videos statusHttp RequestService
  30. 30Get video with audioHttp RequestService
  31. 31Merge videos statusSwitchLogic
  32. 32Get merged videoHttp RequestService
  33. 33Get the video1Http RequestService
  34. 34YouTubeYou TubeService

How it's built

Starts on
An event in a connected app
Steps
34, with 4 branches, 5 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
Google Sheets, YouTube
Model
OpenAI

Questions

What does it need to run?

An n8n account, plus your own Google Sheets and YouTube accounts, 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 34 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 34 steps before you point it at anything that matters.