Automation library · Chat assistants

AI speech coach & generator with Telegram and Open AI

Started by an incoming Telegram message, and works across Telegram. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 16 steps, 2 branches: a working afternoon to understand properly.

MediumCalls a model: Gemini, OpenAIRetrieval

Download free
16 stepsMedium: a working afternoon
2Branches: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 1Model 5Logic 8Service 2

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

  1. 1Google Gemini Chat ModelLm Chat Google GeminiModel
  2. 2Recieve Telegram MessageTelegram triggerStarts it
  3. 3Store Conversation MemoryMemory Buffer WindowModel
  4. 4AI AgentAgentModel
  5. 5Check For Text or Voice MessageSetLogic
  6. 6Wipe Conversation MemoryMemory ManagerModel
  7. 7Code to remove unwanted characters from LLM responseCodeLogic
  8. 8If Voice MessageIfLogic
  9. 9Set prompt to start a new speechSetLogic
  10. 10Code to split output into chunks under 4000 charactersCodeLogic
  11. 11Download Audio FileTelegramService
  12. 12Route Flow Based on Message ContentSwitchLogic
  13. 13Respond to Telegram MessageTelegramService
  14. 14Transcribe Audio FileOpen AiModel
  15. 15Set prompt to generate a speech based on the feedbackSetLogic
  16. 16Set prompt to provide feedback on speechSetLogic

How it's built

Starts on
An incoming Telegram message
Steps
16, with 2 branches
Size
Medium: a working afternoon
Connects to
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 Telegram account, 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?

Plan an afternoon. 16 steps is enough that you should read each one before running it.

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 16 steps before you point it at anything that matters.