# Transcribing Telegram voice messages with Whisper and Gemini: n8n workflow

> Started by an incoming Telegram message, and works across Telegram. It hands the judgement calls to Gemini and OpenAI.

Source: https://millionrounds.com/workflow/transcribing-telegram-voice-messages-with-whisper-and-gemini (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Documents and files](https://millionrounds.com/workflows?category=Documents+and+files#library)

# Transcribing Telegram voice messages with Whisper and Gemini

Started by an incoming Telegram message, and works across Telegram. It hands the judgement calls to Gemini and OpenAI. 20 steps, 4 branches: a working afternoon to understand properly.

Medium Calls a model: Gemini, OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ftranscribing-telegram-voice-messages-with-whisper-and-gemini)

**20 steps** Medium: a working afternoon

**4** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 1 Model 2 Logic 9 Service 8

The steps in the order they run, from what starts it.

- 1 **Telegram Trigger1** Telegram trigger *Starts it*
- 2 **Access Check** If *Logic*
- 3 **Determining The Type Of Document** Switch *Logic*
- 4 **MSG - Access denied!** Telegram *Service*
- 5 **Assigning file_id For Voice** Set *Logic*
- 6 **Assigning file_id For Audio** Set *Logic*
- 7 **MSG - No file!** Telegram *Service*
- 8 **Transcription Decision Node** If *Logic*
- 9 **Get File GPT** Telegram *Service*
- 10 **MSG - File not recognized** Telegram *Service*
- 11 **Transcription by OpenAi** Open Ai *Model*
- 12 **MSG - Starting transcription. Please wait.** Telegram *Service*
- 13 **Assignment of variable TEXT** Set *Logic*
- 14 **Get File Gemini** Telegram *Service*
- 15 **Checking the length of a message** If *Logic*
- 16 **Transcription by Gemini** Google Gemini *Model*
- 17 **MSG - Output** Telegram *Service*
- 18 **Text Division** Code *Logic*
- 19 **Assignment of variable TEXT1** Set *Logic*
- 20 **MSG - Output with chunking** Telegram *Service*

## How it's built

- **Starts on:** An incoming Telegram message
- **Steps:** 20, with 4 branches
- **Size:** Medium: a working afternoon
- **Connects to:** Telegram
- **Model:** Gemini, OpenAI

## Questions

What does it need to run?

An n8n account, plus your own Telegram account, and a key for Gemini and OpenAI. 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 OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 20 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.

**Before you run it**

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 20 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ftranscribing-telegram-voice-messages-with-whisper-and-gemini)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also documents and files, with the same services where possible, closest in size first.

- [**Process voice, images & documents with OpenAI and MongoDB** 21 steps · calls a model · Gmail, Telegram](https://millionrounds.com/workflow/process-voice-images-and-documents-with-openai-and-mongodb)
- [**Backup n8n workflows to GitHub and Google Drive with Gmail** 19 steps · Gmail, Google Drive](https://millionrounds.com/workflow/backup-n8n-workflows-to-github-and-google-drive-with-gmail)
- [**Automate a 'Chat with Gemini and Pinecone** 18 steps · calls a model · Pinecone, Telegram](https://millionrounds.com/workflow/automate-a-chat-with-gemini-and-pinecone)
- [**Build a Reels swipe file from Instagram with Apify and Groq** 18 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/build-a-reels-swipe-file-from-instagram-with-apify-and-groq)
- [**Document parsing & data extraction with Mistral** 18 steps · calls a model · Gmail, Telegram](https://millionrounds.com/workflow/document-parsing-and-data-extraction-with-mistral)
- [**Telegram chat with PDF** 18 steps · calls a model · Pinecone, Telegram](https://millionrounds.com/workflow/telegram-chat-with-pdf)