Automation library · Content

Generate AI songs + music videos with Gemini and OpenAI

Started by an incoming Telegram message, and works across Google Drive, Google Sheets and Telegram. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 57 steps, 3 branches, 7 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: Gemini, OpenAIRetrieval

Download free
57 stepsLarge: read it before trusting it with anything live
3Branches: places the flow splits
7Loops or waits
3Services it connects to

The flow

Starts it 3Model 11Logic 13Service 30

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

  1. 1OpenAI Chat ModelLm Chat Open AiModel
  2. 2Simple MemoryMemory Buffer WindowModel
  3. 3OpenAI Chat Model1Lm Chat Open AiModel
  4. 4Structured Output ParserOutput Parser StructuredModel
  5. 5Structured Output Parser1Output Parser StructuredModel
  6. 6Google Gemini Chat ModelLm Chat Google GeminiModel
  7. 7Track Ideas Agent Telegram TriggerTelegram triggerStarts it
  8. 8Append Music Tracks to GSheetsGoogle Sheets ToolService
  9. 9Get Rows: Confirm Tracks in GSheetsGoogle Sheets ToolService
  10. 10SerpAPI: Browse the internet for Music IdeasTool Serp ApiModel
  11. 11Google Sheets Trigger: Start Processing TracksGoogle Sheets triggerStarts it
  12. 12Render Video TriggerGoogle Sheets triggerStarts it
  13. 13AI Music AgentAgentModel
  14. 14Lyrics AI AgentAgentModel
  15. 15Cover Image and Video Prompts AI AgentAgentModel
  16. 16Switch Text or Voice InputSwitchLogic
  17. 17Get one Pending RowGoogle SheetsService
  18. 18Get Pending Render RowGoogle SheetsService
  19. 19Send Message to UserTelegramService
  20. 20Music Generation API RequestHttp RequestService
  21. 21Generate Cover Image 1:1Http RequestService
  22. 22Generate Cover Image 3:1Http RequestService
  23. 23Set Field to "text"SetLogic
  24. 24Download Voice NoteTelegramService
  25. 25Render Audio Track + VideoHttp RequestService
  26. 26WaitWaitLogic
  27. 27Wait1WaitLogic
  28. 28Wait2WaitLogic
  29. 29Transcribe Voice NoteOpen AiModel
  30. 30Wait3WaitLogic
  31. 31Get Music Generation StatusHttp RequestService
  32. 32get_image_url1Http RequestService
  33. 33get_image_urlHttp RequestService
  34. 34Set FieldSetLogic
  35. 35Send URL to GDrive Script and UploadHttp RequestService
  36. 36Confirm Generation StatusSwitchLogic
  37. 37Get ImageHttp RequestService
  38. 38Get Image1Http RequestService
  39. 39Rename Uploaded VideoGoogle DriveService
  40. 40Download Audio TrackHttp RequestService
  41. 41Rate Limit Wait NodeWaitLogic
  42. 42Upload Cover Image 1:1 to DriveGoogle DriveService
  43. 43Upload to kraken to get urlHttp RequestService
  44. 44Update Music Video URL + Render StatusGoogle SheetsService
  45. 45Upload Audio Track to DriveGoogle DriveService
  46. 46MergeMergeLogic
  47. 47Convert Cover Image 3:1 to VideoHttp RequestService
  48. 48Send Video URL to UserTelegramService
  49. 49Update Audio URL in GSheetGoogle SheetsService
  50. 50Update Cover Photo & Video URLsGoogle SheetsService
  51. 511 minuteWaitLogic
  52. 52Send Status Updates on TelegramTelegramService
  53. 53Get Video Generation StatusHttp RequestService
  54. 54Confirm Generation Status1SwitchLogic
  55. 55Download VideoHttp RequestService
  56. 56Rate Limit Wait Node1WaitLogic
  57. 57Upload Converted Video to DriveGoogle DriveService

How it's built

Starts on
An incoming Telegram message
Steps
57, with 3 branches, 7 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
Google Drive, Google Sheets, Telegram
Model
Gemini, 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 Google Drive, Google Sheets and Telegram accounts, and a key for Gemini and 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 Gemini and 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 57 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 57 steps before you point it at anything that matters.