# AI interpreter and translator for WhatsApp – translate voice: n8n workflow

> Started by another system calling it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Groq and OpenAI.

Source: https://millionrounds.com/workflow/ai-interpreter-and-translator-for-whatsapp-translate-voice (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)

# AI interpreter and translator for WhatsApp – translate voice

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Groq and OpenAI. 44 steps, 5 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Groq, OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-interpreter-and-translator-for-whatsapp-translate-voice)

**44 steps** Large: read it before trusting it with anything live

**5** Branches: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 1 Model 19 Logic 15 Service 9

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

- 1 **Webhook** Webhook *Starts it*
- 2 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 3 **Calculator** Tool Calculator *Model*
- 4 **Groq Chat Model** Lm Chat Groq *Model*
- 5 **OpenAI Chat Model1** Lm Chat Open Ai *Model*
- 6 **OpenAI Chat Model2** Lm Chat Open Ai *Model*
- 7 **Calculator1** Tool Calculator *Model*
- 8 **Think** Tool Think *Model*
- 9 **Think1** Tool Think *Model*
- 10 **OpenAI Chat Model3** Lm Chat Open Ai *Model*
- 11 **Calculator2** Tool Calculator *Model*
- 12 **Think2** Tool Think *Model*
- 13 **Who Sent?** If *Logic*
- 14 **AI Agent1** Agent *Model*
- 15 **Text Classifier** Text Classifier *Model*
- 16 **Text Classifier1** Text Classifier *Model*
- 17 **AI Agent** Agent *Model*
- 18 **AI Agent2** Agent *Model*
- 19 **Your Number** If *Logic*
- 20 **Format Phone** Code *Logic*
- 21 **Code1** Code *Logic*
- 22 **Filter** Filter *Logic*
- 23 **WhatsApp** Http Request *Service*
- 24 **Audio2** If *Logic*
- 25 **PrefixMap** Code *Logic*
- 26 **International** Filter *Logic*
- 27 **WhatsApp2** Http Request *Service*
- 28 **Code** Code *Logic*
- 29 **GET Media** Http Request *Service*
- 30 **Text Mapping2** Set *Logic*
- 31 **Filter the Country** Filter *Logic*
- 32 **Audio** If *Logic*
- 33 **WhatsApp1** Http Request *Service*
- 34 **Convert to File2** Convert To File *Service*
- 35 **Audio1** If *Logic*
- 36 **GET Media2** Http Request *Service*
- 37 **Text Mapping** Set *Logic*
- 38 **OpenAI2** Open Ai *Model*
- 39 **GET Media1** Http Request *Service*
- 40 **Text Mapping1** Set *Logic*
- 41 **Convert to File1** Convert To File *Service*
- 42 **Convert to File** Convert To File *Service*
- 43 **OpenAI1** Open Ai *Model*
- 44 **OpenAI** Open Ai *Model*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 44, with 5 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Groq, OpenAI

## Questions

What does it need to run?

An n8n account, and a key for Groq and OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls Groq and OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 44 steps it is large: read it before trusting it with anything live.

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 44 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%2Fai-interpreter-and-translator-for-whatsapp-translate-voice)
- **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.

## Workflows like it

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

- [**Create restorable n8n Docker backups in Google Drive with SSH** 44 steps · Google Drive](https://millionrounds.com/workflow/create-restorable-n8n-docker-backups-in-google-drive-with-ss)
- [**Document Q&A system with Voyage-Context-3 and MongoDB Atlas** 43 steps · calls a model · MongoDB](https://millionrounds.com/workflow/document-q-and-a-system-with-voyage-context-3-and-mongodb-at)
- [**AI WhatsApp Chatbot with Voice and Image** 47 steps · calls a model · Google Sheets](https://millionrounds.com/workflow/ai-whatsapp-chatbot-with-voice-and-image)
- [**Automated document ingestion & vectorization with RAG** 47 steps · calls a model · Google Docs, Google Drive](https://millionrounds.com/workflow/automated-document-ingestion-and-vectorization-with-rag)
- [**Sign PDF documents with PAdES** 48 steps](https://millionrounds.com/workflow/sign-pdf-documents-with-pades)
- [**AI agent to chat with Google Drive** 49 steps · calls a model · Google Drive, Supabase](https://millionrounds.com/workflow/ai-agent-to-chat-with-google-drive)