Automation library · Content

Create news anchor avatar videos from Slack with OpenAI

Started by an event in a connected app, and works across Slack and n8n data table. It hands the judgement calls to OpenAI. 33 steps, 5 branches, 2 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAI

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

The flow

Starts it 1Model 4Logic 12Service 16

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

  1. 1When Slack Message ReceivedSlack triggerStarts it
  2. 2Generate Script with OpenAILm Chat Open AiModel
  3. 3Revise Script with OpenAILm Chat Open AiModel
  4. 4Parse Slack MessageCodeLogic
  5. 5News Script GeneratorAgentModel
  6. 6Revise Script via FeedbackAgentModel
  7. 7Check User Message ValidityIfLogic
  8. 8Store Draft ScriptData TableService
  9. 9Notify Script Generation FailureSlackService
  10. 10Update Script DraftData TableService
  11. 11Notify Script Revision FailureSlackService
  12. 12Query Pending Session DataData TableService
  13. 13Ignore Non-User InputNo OpLogic
  14. 14Post Draft Script to SlackSlackService
  15. 15Post Revised Script to SlackSlackService
  16. 16Check Pending Session ExistenceIfLogic
  17. 17Check User ConfirmationIfLogic
  18. 18Confirm Session StatusData TableService
  19. 19Create HeyGen VideoHttp RequestService
  20. 20Log HeyGen Job IDData TableService
  21. 21Notify HeyGen FailureSlackService
  22. 22Poll for Video StatusSplit In BatchesLogic
  23. 23End Polling LoopNo OpLogic
  24. 24Wait 15 SecondsWaitLogic
  25. 25Verify HeyGen Video StatusHttp RequestService
  26. 26Check Video CompletionIfLogic
  27. 27Handle Video Creation FailureNo OpLogic
  28. 28Video Creation CompleteNo OpLogic
  29. 29Check Polling TimeoutIfLogic
  30. 30Post Failure Notice to SlackSlackService
  31. 31Post Video Link to SlackSlackService
  32. 32Record Session FailureData TableService
  33. 33Mark Session as CompleteData TableService

How it's built

Starts on
An event in a connected app
Steps
33, with 5 branches, 2 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
Slack, n8n data table
Model
OpenAI

Questions

What does it need to run?

An n8n account, plus your own Slack 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 33 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 33 steps before you point it at anything that matters.