Automation library · Content

Create AI videos with HeyGen

Started by another system calling it, and works across Baserow. It hands the judgement calls to OpenAI. 59 steps, 9 branches, 6 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAI

Download free
59 stepsLarge: read it before trusting it with anything live
9Branches: places the flow splits
6Loops or waits
1Service it connects to

The flow

Starts it 2Model 5Logic 37Service 15

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

  1. 1Structured Output ParserOutput Parser StructuredModel
  2. 2OpenAI Chat ModelLm Chat Open AiModel
  3. 3WebhookWebhookStarts it
  4. 4OpenAI Chat Model1Lm Chat Open AiModel
  5. 5When Executed by Another WorkflowExecute Workflow triggerStarts it
  6. 6Basic LLM ChainChain LlmModel
  7. 7Basic LLM Chain ManualChain LlmModel
  8. 8BodySetLogic
  9. 9Baserow ErrorBaserowService
  10. 10Scenes MappingSetLogic
  11. 11Update ScriptBaserowService
  12. 12Execute Workflow4Execute WorkflowLogic
  13. 13Should Process?IfLogic
  14. 14Stop and ErrorStop And ErrorLogic
  15. 15Split OutSplit OutLogic
  16. 16Switch ScriptTypeSwitchLogic
  17. 17Baserow ProcessingBaserowService
  18. 18loop_over_scenesSplit In BatchesLogic
  19. 19IfIfLogic
  20. 20If_with_avatarIfLogic
  21. 21Leo - Improve PromptHttp RequestService
  22. 22Execute WorkflowExecute WorkflowLogic
  23. 23AggregateAggregateLogic
  24. 24CodeCodeLogic
  25. 25Leo - Generate ImageHttp RequestService
  26. 26Execute Workflow5Execute WorkflowLogic
  27. 27CaptionsAI1Http RequestService
  28. 28If_with_heygenIfLogic
  29. 29Wait1WaitLogic
  30. 30Execute Workflow3Execute WorkflowLogic
  31. 31Wait6WaitLogic
  32. 32CAPTIONS Execute ERROR1Execute WorkflowLogic
  33. 33HeyGenHttp RequestService
  34. 34json2video : Video RenderingHttp RequestService
  35. 35Leo - Get imageIdHttp RequestService
  36. 36CaptionsAI : Check Poll1Http RequestService
  37. 37Wait4WaitLogic
  38. 38heygen Execute ERRORExecute WorkflowLogic
  39. 39WaitWaitLogic
  40. 40json2video Execute ERRORExecute WorkflowLogic
  41. 41BackgroundTypeIfLogic
  42. 42cap_responseSwitchLogic
  43. 43HeyGen : Check VideoHttp RequestService
  44. 44json2video : Check Video RenderingHttp RequestService
  45. 45Runway - Create VideoHttp RequestService
  46. 46output imageSetLogic
  47. 47Code Add SubCodeLogic
  48. 48CAPTIONS Execute ERRORExecute WorkflowLogic
  49. 49heygen_responseSwitchLogic
  50. 50heygen Execute ERROR2Execute WorkflowLogic
  51. 51j2v_responseSwitchLogic
  52. 52Wait2WaitLogic
  53. 53Execute Workflow2Execute WorkflowLogic
  54. 54Code HeygenCodeLogic
  55. 55BaserowBaserowService
  56. 56json2video Execute ERROR1Execute WorkflowLogic
  57. 57Runway - Get VideoHttp RequestService
  58. 58outputSetLogic
  59. 59Execute Workflow6Execute WorkflowLogic

How it's built

Starts on
Another system calling it
Steps
59, with 9 branches, 6 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
Baserow
Model
OpenAI

Questions

What does it need to run?

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

What starts it?

It starts on another system calling it.

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 59 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 59 steps before you point it at anything that matters.