What this workflow does
This workflow is an automated Telegram study helper for signal processing students. It helps by turning voice messages into text, understanding student questions, and giving helpful answers inside Telegram. It saves a lot of time by combining transcription, research, and answering in one chat.
It stops you from switching apps and writing notes by hand, giving fast, clear study help directly in the chat.
Who should use this workflow
This is useful for students studying signal processing. It is for those who take voice notes during class and want those notes typed out fast.
Anyone who wants smart explanations for questions without searching on many different sites will find it helpful. Telegram users who prefer chatting over typing will benefit most.
Tools and services used
- Telegram Bot API: Receives and sends messages from the student.
- OpenAI: Transcribes voice messages and generates text answers.
- Google Gemini Language Model: Helps create better study explanations.
- Airtable: Stores past chat history for better memory and personalized answers.
- n8n Automation Platform: Runs the workflow handling all steps automatically.
How this workflow works (Inputs → Process → Outputs)
Inputs
The user sends a text or voice message to the Telegram bot.
Processes
- The Telegram Trigger listens for any new messages.
- A Switch node checks if message is text or voice.
- If voice, the voice file is fetched using Telegram node and sent to OpenAI to get text transcription.
- If text, the message text is mapped cleanly for processing.
- The text from either branch merges to one stream.
- Airtable is queried to retrieve past chat history (user memory).
- The combined current message and past memory are sent to the AI Agent node.
- AI Agent runs using OpenAI and Google Gemini models to give a detailed, clear study response.
- The AI answer is sent back to Telegram to reply to the user.
- User memory is saved back to Airtable for future conversations.
Outputs
The user gets text replies inside Telegram. The replies have transcription of voice notes or answers to study questions, including explanations or calculations if needed.
Beginner step-by-step: How to use this workflow in production inside n8n
Import the workflow
- Download the workflow file using the Download button on this page.
- Open the n8n editor where you want to run this automation.
- Use the Import from File option to upload the downloaded workflow.
Configure credentials and settings
- Add your Telegram Bot API credentials in the Telegram Trigger and other Telegram nodes.
- Add your OpenAI API key where the OpenAI nodes require it.
- Provide your Google Cloud credentials for using Google Gemini in AI Agent node.
- Enter Airtable API key and set the right base and table names to store chat memory.
- If needed, update emails, chat IDs, or folder names in the Telegram or Email nodes.
- Check any code expressions or URL fields for correctness (no changes needed if default).
Test the workflow
- Send a text message or voice note to your Telegram bot.
- Confirm the workflow triggers and sends a helpful reply back in Telegram.
- If any errors occur, check node logs and credentials.
Activate for production
- Once tested, activate the workflow to run automatically.
- Monitor activity logs in n8n regularly for smooth operation.
If you want to run this outside your computer or do self hosting n8n, see self-host n8n for help.
Common issues and edge cases
- No trigger when sending Telegram messages: Check Telegram Bot settings and webhook URL setup.
- Voice transcription fails: Make sure correct voice file ID is grabbed and OpenAI transcription is configured well.
- No AI response: Verify API keys for OpenAI and Google Gemini are valid.
- Airtable memory not found: Confirm Airtable API key and table ID are correct and not expired.
How to customize this workflow
- Add support for photos or documents by updating the Switch node to detect these message types.
- Change the AI Agent’s system prompt for other subjects like math or physics.
- Replace Airtable with Google Sheets or another database for storing user memory.
- Make AI ask follow-up questions automatically by adjusting AI Agent prompts.
- Add extra notifications to Slack or email if certain keywords appear in user messages.
Summary of results
✓ Saves many hours each week by automating transcription and answering inside Telegram.
✓ Gives clear, personalized study help using advanced AI models.
✓ Keeps track of past conversations for better learning.
✓ Works with voice and text messages without switching apps.
✓ Easy to import, configure, and activate inside n8n.