--- title: "Telegram bot that sorts text and voice and describes photos" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/3d465f82-80ca-4ea4-93be-88f11c0bdd52" updated: "2026-11-12" --- # Telegram bot that sorts text and voice and describes photos > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow for a Telegram bot that handles text, voice notes and photos. It labels text and transcripts as a task or another message, and it describes photos with OpenAI. Telegram bot that sorts text and voice and describes photos is an n8n workflow in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow lets a Telegram bot understand three kinds of message. A text, or the transcript of a voice note, is labelled as a task or another message and sent back with that label. A photo is described in words. Thirty nodes do the work, beside ten sticky notes. ### Who it suits People who want to capture quick thoughts by text or voice and have photos explained. Skip it if you expect the workflow to create tasks in another app, since it only labels and replies. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Personal | Busy professionals | Capture to-dos by voice while on the move | A user records a reminder to send an invoice and gets it back labelled as a task. | | Field work | Site supervisors | Describe photos taken on site | A supervisor sends a photo of a delivery and reads a written description. | | Small business | Shop owners | Sort quick notes from the shop floor | An owner types a note about restocking cups and sees it labelled as a task. | | Accessibility | People with low vision | Have a photo explained in words | A user sends a photo of a shelf and reads what is on it. | You need a Telegram bot, an OpenAI key and an n8n that Telegram can reach over the internet. ### Where to use it Telegram posts every message to a web address, so your n8n needs a public HTTPS address. After that you use the bot from any Telegram chat with it. - n8n Cloud: import the file there and switch it on - Your own n8n server: the same file, with a public HTTPS address - Other labels: rewrite the two categories in the classifier nodes - Other photo questions: set a prompt in \`Analyze Image\` ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. The last step tells Telegram where to send messages, and three helper nodes can do it for you. What you need first | Need | Detail | | --- | --- | | n8n | A server or n8n Cloud with a public HTTPS address | | Telegram | A bot token from BotFather, for a Telegram credential | | OpenAI | An API key, for an OpenAI credential | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. In Telegram, ask BotFather for a new bot and copy its token. 3. Add a Telegram credential and select it in every Telegram node. 4. Add an OpenAI credential and select it in `Audio Classifier Model`, `Text Classifier Model`, `Transcribe Recording` and `Analyze Image`. 5. In `Validation`, replace the example first name, last name and numeric id with your own Telegram details. 6. In `Telegram Token & Webhooks`, replace `` with your token and keep the word bot in front of it. Replace `` in the two web addresses with your public n8n address. In the three status nodes, replace `` with your chat id. 7. Switch the workflow on and run `Set Webhook Production URL` from the editor to register the address with Telegram. 8. Send your bot a text, a voice note and a photo. ### How to use it Message the bot. A text comes back as “Task message” or “Other message” with your words in italics. A voice note does the same with its transcript. A photo comes back as a written description. Messages from anyone else get a short error reply. What to change for a different result | To change | Where | | --- | --- | | Who may use the bot | First name, last name and id in \`Validation\` | | The labels | The categories in \`Text Classifier\` and \`Text Classifier Audio\` | | What the bot says about photos | The prompt in \`Analyze Image\` | | The webhook address | The values in \`Telegram Token \& Webhooks\` | ### Example You send a voice note that says to book the dentist for Tuesday. The workflow downloads it, turns it into text, and the classifier files it under task. The bot replies with “Task message” and your words. You then send a photo of a cat on a sofa. The bot replies with a sentence that describes a cat on a sofa. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. A webhook is an address n8n listens on, and Telegram posts each new message to it. A classifier is an AI step that puts a text into one of your groups. **For experts.** `Message Router` has four outputs, one each for voice, text and photo plus a fallback that sends the error reply. The photo goes through `Extract from File to Base64` and `Convert to Image File` so that `Analyze Image` can read it as base64. `Validation` must pass the incoming fields on, or the router sees no message. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`Listen for Telegram Events\` | Webhook 2, POST on the path \`your-endpoint\` | The address is public, so the sender check is the only gate | | \`Validation\` | Set 3.4 with the include other fields option on | It holds the example name and id you replace | | \`Message Router\` | Switch 3.2, outputs for audio, text, image and everything else | The fallback sends the error reply | | \`Text Classifier\` | Text Classifier 1 with two categories, task and other | It uses \`Text Classifier Model\` on \`gpt-6-luna\` | | \`Name the voice file\` | Code 2, sets the file name and type | Telegram’s ending \`oga\` is not on OpenAI’s list of formats | | \`Transcribe Recording\` | HTTP Request 4.2, a POST to the transcription address | It uses model \`gpt-transcribe\` and the OpenAI credential | | \`Text Classifier Audio\` | Text Classifier 1 with the same two categories | It reads the transcript field \`text\` | | \`Extract from File to Base64\` | Extract From File 1, binary to property, keep source JSON | It keeps \`result.file\_path\` for the next node | | \`Analyze Image\` | OpenAI 1.6, Image, Analyze, from base64 | It uses \`gpt-6-luna\` and allows 1500 tokens | | \`Telegram Token \& Webhooks\` | Set 3.4 with the token and two addresses | It feeds the three helper requests | ### Good to know The original left its models unset, used a speech model that is ending, and had two flaws that stopped the flow. - Models: the two classifier models had no model set, so they ran on the node’s default \`gpt-5-mini\`, although they were named \`gpt-4o-mini\`. OpenAI’s deprecations page, read on 12 November 2026, lists \`gpt-5-mini\` as shutting down on 11 December 2026. The image step named \`gpt-4o-mini\`, and OpenAI lists the dated snapshot of that model for shutdown on 14 January 2027 with \`gpt-6-luna\` as the replacement. Mindket’s copy uses \`gpt-6-luna\` for all three, which OpenAI’s model page lists for text and image input - Speech to text: n8n’s OpenAI node always sends \`whisper-1\`, which OpenAI’s page lists for shutdown on 26 February 2027 with \`gpt-transcribe\` as a replacement. Mindket’s copy calls OpenAI’s transcription address with an HTTP Request node and \`gpt-transcribe\`. OpenAI’s speech to text guide lists \`ogg\` but not \`oga\`, the ending Telegram gives voice notes, so \`Name the voice file\` renames the file first - A message path that stopped: \`Validation\` did not pass the incoming fields on, so the router never saw the message and every message got the error reply. Mindket’s copy turns on the include other fields option - A file name that was missing: \`Convert to Image File\` reads \`result.file\_path\`, which \`Extract from File to Base64\` drops unless it keeps the source JSON. Mindket’s copy turns Keep Source to JSON on - The photo limit: \`Analyze Image\` allows 300 tokens by default, and OpenAI’s reasoning guide says a reasoning model counts its thinking in the limit, so the copy raises it to 1500 - Labels only: nothing creates a task anywhere, so add your own step after the task messages - Sizes: Telegram’s Bot API page says bots can download files up to 20 MB, and OpenAI’s guide allows 25 MB for audio - A public address: anyone who learns the webhook address can post a made-up update. Telegram can send a secret token in a header when you register the webhook, and the Webhook node can check it with Header Auth - Telegram’s HTML mode: the task and other messages repeat your text in HTML mode. Telegram’s documentation asks for \`\<\`, \`\>\` and \`\&\` to be escaped, so a text with them can fail to send - A caption: the photo’s caption is saved by \`Image Schema\` but no step uses it - Your bot token: it sits in \`Telegram Token \& Webhooks\` as plain text, so it is stored with the workflow and shows in execution data. Clear it after you register the webhook - Not run against Telegram or OpenAI: Mindket ran the flow with stand-ins for both and saw all three kinds of message reach a reply. The helper requests to Telegram were not run - Your data: texts, voice notes and photos go to OpenAI, and the chat runs through Telegram - Credentials: the JSON holds none, so add the Telegram and OpenAI credentials yourself ## README ```markdown # Telegram bot that sorts text and voice and describes photos An n8n workflow for a Telegram bot that handles text, voice notes and photos. A text, or the transcript of a voice note, is labelled by OpenAI as a task or another message and sent back with that label. A photo is described in words. ## What is inside - `workflow.json`: the workflow as n8n exports it, thirty working nodes and ten sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - `Validation` did not pass the incoming fields on, so the router saw no message and every message got the error reply. Its include other fields option is now on. - `Extract from File to Base64` now keeps the source JSON, because `Convert to Image File` reads `result.file_path` from it. - The two classifier models had no model set and were named `gpt-4o-mini`. They are now `Audio Classifier Model` and `Text Classifier Model` on `gpt-6-luna`. - `Analyze Image` now uses `gpt-6-luna` with a limit of 1500 tokens. - n8n's OpenAI node, which always sends `whisper-1`, is replaced in `Transcribe Recording` by an HTTP Request node that uses `gpt-transcribe`. A new Code node, `Name the voice file`, renames the downloaded file to `voice.ogg` before it goes out. - The bot token, the host of the two webhook addresses and three chat ids are now placeholders. ## Before you start - An n8n instance with a public HTTPS address, on n8n Cloud or on your own server. - A Telegram account and a bot token from BotFather. - An OpenAI API key. ## Set it up 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. In Telegram, ask BotFather for a new bot and copy its token. 3. Add a Telegram credential and select it in every Telegram node. 4. Add an OpenAI credential and select it in `Audio Classifier Model`, `Text Classifier Model`, `Transcribe Recording` and `Analyze Image`. 5. In `Validation`, replace the example first name, last name and numeric id with your own Telegram details. The id is the number under message, from, id in the data `Listen for Telegram Events` receives. 6. In `Telegram Token & Webhooks`, replace `` with your token and keep the word bot in front of it. Replace `` in the two web addresses with your public n8n address. If you change the webhook path `your-endpoint`, change it in both addresses too. In the three status nodes, replace `` with your chat id. 7. Switch the workflow on and run `Set Webhook Production URL` from the editor to register the address with Telegram. `Get Telegram Webhook Info` shows the result in your chat. 8. Send your bot a text, a voice note and a photo. ## How a run goes 1. `Listen for Telegram Events` receives the update, and `Validation` with `Check User & Chat ID` compares the sender with your details. Anyone else gets the reply from `Error message`. 2. `Message Router` sorts the message by kind. 3. A text goes through `Edit Fields` to `Text Classifier`, which sends `Text Task Message` or `Text Other Message`. 4. A voice note goes through `Get Audio File`, `Name the voice file` and `Transcribe Recording`, then `Text Classifier Audio`, which sends `Audio Task Message` or `Audio Other Message`. 5. A photo goes through `Image Schema`, `Get Image`, `Extract from File to Base64` and `Convert to Image File` to `Analyze Image`, and `Image Message` sends the description. 6. The helper nodes under `Telegram Token & Webhooks` run only when you run them by hand. ## What to change for a different result - Who may use the bot: the first name, last name and id in `Validation`. - The labels: the categories in `Text Classifier` and `Text Classifier Audio`. - What the bot says about photos: set a prompt in `Analyze Image`. - The webhook address: the values in `Telegram Token & Webhooks`. ## Good to know - The two classifier models ran on the node's default `gpt-5-mini`, which OpenAI's deprecations page, read on 12 November 2026, lists for shutdown on 11 December 2026. The image step named `gpt-4o-mini`, and the page lists the dated snapshot of that model for shutdown on 14 January 2027 with `gpt-6-luna` as the replacement. OpenAI's model page lists text and image input for `gpt-6-luna`. - The same page lists `whisper-1` for shutdown on 26 February 2027 with `gpt-transcribe` as a replacement. OpenAI's speech to text guide lists `ogg` among its formats but not `oga`, the ending Telegram gives voice notes. - OpenAI's reasoning guide says a reasoning model counts its thinking in the token limit, and `Analyze Image` allows 300 tokens by default, so the copy raises it to 1500. - Nothing creates a task anywhere. The workflow only labels and replies. - Telegram's Bot API page says bots can download files up to 20 MB, and OpenAI's guide allows 25 MB for audio. - Anyone who learns the webhook address can post a made-up update. Telegram can send a secret token in a header when you register the webhook, and the Webhook node can check it with Header Auth. - The task and other messages repeat your text in HTML mode, and Telegram's documentation asks for `<`, `>` and `&` to be escaped, so a text that holds them can fail to send. - The caption of a photo is saved by `Image Schema`, but no step uses it. - The bot token sits in `Telegram Token & Webhooks` as plain text, so it is stored with the workflow and shows in execution data. Clear it after you register the webhook. - Not run against Telegram or OpenAI. The flow was run with stand-ins for both: all three kinds of message reached a reply. The helper requests to Telegram were not run. - Texts, voice notes and photos go to OpenAI, and the chat runs through Telegram. ``` ## What is in it 3 files, 35 KB, downloaded as a zip. ```text NOTICE.md 631 B README.md 6 KB workflow.json 29 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 21 steps, starting when its webhook is called - Not reached: 7 nodes no run reaches: Set Webhook Test URL, Get Telegram Webhook Info, Test Webhook Status, Production Webhook Status, Set Webhook Production URL and 2 more - AI: 3 steps call an AI model: Text Classifier Audio, Text Classifier and Analyze Image - Sign-ins: Signs in to: Telegram, OpenAI and api.telegram.org - API keys: No API key is left in the file; 1 blank in it for your own key - Step types: Mindket’s checker reads all 11 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/3d465f82-80ca-4ea4-93be-88f11c0bdd52) - [Its page on Mindket](https://mindket.com/p/3d465f82-80ca-4ea4-93be-88f11c0bdd52)