The flow
Starts it 1Model 6Logic 3Service 5
The steps in the order they run, from what starts it.
- 1Validate inputsLm Chat Google GeminiModel
- 2OpenRouter Chat ModelLm Chat Open RouterModel
- 3Check OutputLm Chat Google GeminiModel
- 4User Sends Message to BotTelegram triggerStarts it
- 5Analyze user InputAgentModel
- 6Analyze Transcript and Generate DubAgentModel
- 7Structured OutputOutput Parser StructuredModel
- 8Process Initialization AlertTelegramService
- 9Extract Youtube TranscriptBrowser ActService
- 10Send Summary Back to BotTelegramService
- 11Split Generated Dubbed ContentSplit OutLogic
- 12Define LanguageSetLogic
- 13Loop Over Generated ItemsSplit In BatchesLogic
- 14Convert text to speechEleven LabsService
- 15Send Dubbed Audio FileTelegramService
How it's built
- Starts on
- An incoming Telegram message
- Steps
- 15, 1 loop or waits
- Size
- Medium: a working afternoon
- Connects to
- Telegram
- Model
- Gemini, OpenRouter
Questions
What does it need to run?
An n8n account, plus your own Telegram account, and a key for Gemini and OpenRouter. 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 OpenRouter. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 15 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.
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 15 steps before you point it at anything that matters.