Automation library · Content

AI-powered YouTube shorts automation: Create & publish

Started by an incoming Telegram message, and works across Telegram and YouTube. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 46 steps, 5 branches, 3 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
46 stepsLarge: read it before trusting it with anything live
5Branches: places the flow splits
3Loops or waits
2Services it connects to

The flow

Starts it 1Model 6Logic 19Service 20

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

  1. 1OpenAI Chat ModelLm Chat Open AiModel
  2. 2Telegram TriggerTelegram triggerStarts it
  3. 3Structure Model OutputOutput Parser StructuredModel
  4. 4Track Conversation MemoryMemory Buffer WindowModel
  5. 5Discuss Ideas 💡AgentModel
  6. 6If Message From UserIfLogic
  7. 7If No Video IdeaIfLogic
  8. 8Telegram: Conversational ResponseTelegramService
  9. 9Telegram: Approve IdeaTelegramService
  10. 10If Idea ApprovedIfLogic
  11. 11Telegram: Processing StartedTelegramService
  12. 12Idea DeniedSetLogic
  13. 13Set API KeysSetLogic
  14. 14If All API Keys SetIfLogic
  15. 15Input VariablesSetLogic
  16. 16Telegram: API Keys MissingTelegramService
  17. 17Ideator 🧠Open AiModel
  18. 18Missing API KeysStop And ErrorLogic
  19. 19ScriptSetLogic
  20. 20Convert Script to AudioHttp RequestService
  21. 21Chunk ScriptHttp RequestService
  22. 22Upload to CloudinaryHttp RequestService
  23. 23Split OutSplit OutLogic
  24. 24Merge Videos and AudioMergeLogic
  25. 25Image Prompter 📷Open AiModel
  26. 26Generate Render JSONHttp RequestService
  27. 27Aggregate PromptsAggregateLogic
  28. 28Request ImagesHttp RequestService
  29. 29Set JSON VariableSetLogic
  30. 30Merge Video VariablesMergeLogic
  31. 31Generating ImagesWaitLogic
  32. 32Send to CreatomateHttp RequestService
  33. 33Telegram: Approve Final VideoTelegramService
  34. 34Get ImagesHttp RequestService
  35. 35Generating Final VideoWaitLogic
  36. 36If Final Video ApprovedIfLogic
  37. 37Request VideosHttp RequestService
  38. 38Get Final VideoHttp RequestService
  39. 39Convert Video to Base64Http RequestService
  40. 40Telegram: Video DeclinedTelegramService
  41. 41Generating VideosWaitLogic
  42. 42Decode Base64 to FileConvert To FileService
  43. 43Get VideosHttp RequestService
  44. 44Upload to YouTubeYou TubeService
  45. 45Aggregate VideosAggregateLogic
  46. 46Telegram: Video UploadedTelegramService

How it's built

Starts on
An incoming Telegram message
Steps
46, with 5 branches, 3 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
Telegram, YouTube
Model
OpenAI
Retrieval
Answers are drawn from documents you supply, not from the model alone

Questions

What does it need to run?

An n8n account, plus your own Telegram 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 incoming Telegram message.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 46 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 46 steps before you point it at anything that matters.