Your task
All challenges
Challenge 13
AI Agent: Photo to Summary
Send your Telegram bot a photo and get a short description of what it shows.
Your bonus task
Save your native language in the workflow – for example, English, Spanish, Ukrainian, or another language. Detect the language of any readable text in the photo. If it differs from your native language, include a translation into your native language alongside the summary. If there is no readable text, just say so.
Example use cases
- Understand a photo of a sign or menu while travelling.
- Get a quick description of a scene or screenshot.
Before you start
- 01
Sign up for n8n Cloud or open your n8n workspace.
- 02
Get Telegram, create a bot with BotFather, and add its token to an n8n Telegram credential. Open the bot and press Start.
- 03
Sign up for OpenRouter, create an API key, and add an OpenRouter credential in n8n. Choose an image-capable model, such as GPT-4o mini, and ensure your account can use it.
- 04
Prepare a photo without text, one with text in your native language, and one with text in another language. Send them as Telegram photos.
Nodes you'll use
What the workflow must do
- 01
A photo receives a short English summary in the same Telegram chat.
- 02
The description matches the image; unclear details or unreadable text are acknowledged rather than invented.
- 03
Bonus: the workflow stores a native language, translates foreign text into it, and skips translation for text already in that language or photos without readable text.
Tip
Need a tip?
Reveal up to five tips, one at a time.
Still stuck? Ask on the n8n community forum
Solution
See the workflow challenge answer
Reveal the completed workflow only when you are ready to compare it with your own.
Submit as solved
Ready to submit?
Submit when your team has a working workflow to demonstrate.