Track meals and macros via Telegram with Gemini AI

Find Your AI Training Job
Chat with DigiNo Toucan and get matched to remote roles in one minute.

Health coaches and dietitians want a client-facing meal tracker but can't justify building a mobile app. This AI automation turns Telegram into a fully functional nutrition logger with macro tracking and daily reports, and you can deliver it as a done-for-you service.

What This Automation Does

Accepts meal logs from clients via text message, voice note, or food photo inside Telegram, then uses Gemini AI to identify the food and estimate calories, protein, carbs, and fat automatically
Stores every meal entry and each client's calorie and protein targets inside a Google Sheets database, giving the coach a live, readable dashboard without any specialist software
Sends clients a personalised daily progress report inside Telegram, complete with visual progress bars showing how close they are to hitting their nutrition goals for the day
Handles new client onboarding through a simple Telegram conversation flow that sets goals without collecting sensitive health data like weight or height

Tools Used

Telegram
Google Gemini
Google Sheets
n8n

Work faster

Stop Typing and Start Speaking With Typeless

Typeless turns what you say into clean, formatted text in any app on Mac, Windows, Linux, iOS and Android, which it rates at 4x faster than typing. It strips filler words, keeps only your final phrasing when you change your mind mid-sentence, and works in 100+ languages. Emails, AI prompts, client messages and docs, done by voice.

Try Typeless →

Where to Get Hired for This Skill

On Contra, top freelancers across this stack have earned 173 combined verified reviews from real client projects.

Source: Contra freelancer search · refreshed 30 May 2026

Start Earning as a Freelancer on Contra

Contra is a commission-free professional network for independents. Browse live AI automation work and keep what you earn.

Join Contra Free →

How To Build It

Wire Telegram to receive multi-format input

Configure the automation to listen for incoming Telegram messages from clients, routing text, voice notes, and image attachments through separate processing paths so each input type is handled correctly before any AI analysis begins.

Transcribe voice and analyse food images

Pass audio messages through Gemini AI to convert speech to a readable meal description, and send food photos through the same model to identify dish contents and portion estimates, so every log format produces a structured meal record.

Calculate and store macro breakdowns in Google Sheets

After Gemini estimates the nutritional content, write calories, protein, carbs, and fats as a timestamped row in the client's meal log sheet, and update their running daily totals in a separate user profile sheet that holds their personal targets.

Build the onboarding and goal-setting conversation

Create a branching Telegram conversation that welcomes new clients, captures their daily calorie and protein targets through natural back-and-forth chat, and writes those preferences to their profile row in Google Sheets so the system references them in every subsequent interaction.

Generate and deliver daily progress reports

At a scheduled time each day, pull each client's meal log totals and goals from Google Sheets, pass them to Gemini AI to compose a personalised progress message with ASCII-style progress bars, and send the finished report back to the client's Telegram chat automatically.

Pitfalls

Gemini AI can misidentify ambiguous food photos, especially mixed dishes or homemade meals with no clear portion reference, which leads to macro estimates the client disputes. Build a quick correction command into the Telegram flow so clients can override a log without breaking the sheet structure.
Google Sheets API rate limits become a real problem once a coach has more than a handful of active clients logging multiple meals per day. Batch writes or a short queue between the AI step and the sheet write prevent failed rows that silently drop meal data.
Telegram bot tokens and Google OAuth credentials both expire or get revoked, usually at the worst possible moment. Document the re-auth steps clearly for the client and set a calendar reminder to rotate credentials before the standard expiry window closes.

FAQ

Can I build this without coding?

Yes. The logic relies on n8n's visual workflow builder with pre-built Telegram and Google Sheets connections. The only section that requires writing anything is the Gemini AI prompt, which is plain English instruction, not code.

How long does it take?

A focused first build, including setting up the Telegram bot, connecting Google Sheets, and testing all three input types, typically takes four to six hours. Subsequent client deployments using the same template run faster, usually under two hours once you have a reusable base.

What can I charge?

Pricing is your call based on your market, but this workflow solves a concrete operational problem for a professional audience that already spends money on client-management tools. Positioning it as a branded, done-for-you client tool rather than a generic bot supports a higher project rate than a simple integration job.

Which tool is required vs optional?

Telegram, Gemini AI, and Google Sheets are all required as the system is designed. Telegram handles all client interaction, Gemini powers food recognition and report writing, and Google Sheets is the database. You could swap Google Sheets for another spreadsheet backend, but replacing Telegram or Gemini would mean rebuilding core parts of the workflow.

This is original DigiNo analysis. The underlying automation pattern is a community workflow template – view the original on n8n.