# Multimodal Political AI Chatbot for WhatsApp: Text, Voice: n8n workflow

> Started by an incoming WhatsApp message, and works across Google Drive, Pinecone and WhatsApp.

Source: https://millionrounds.com/workflow/multimodal-political-ai-chatbot-for-whatsapp-text-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)

# Multimodal Political AI Chatbot for WhatsApp: Text, Voice

Started by an incoming WhatsApp message, and works across Google Drive, Pinecone and WhatsApp. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 37 steps, 3 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fmultimodal-political-ai-chatbot-for-whatsapp-text-voice)

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

**3** Branches: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 3 Model 14 Logic 8 Service 12

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

- 1 **WhatsApp Trigger** Whats App trigger *Starts it*
- 2 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 3 **Simple Memory** Memory Buffer Window *Model*
- 4 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 5 **Google Drive File Updated** Google Drive trigger *Starts it*
- 6 **Google Drive File Created** Google Drive trigger *Starts it*
- 7 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 8 **Embeddings OpenAI2** Embeddings Open Ai *Model*
- 9 **OpenAI Chat Model1** Lm Chat Open Ai *Model*
- 10 **Input type** Switch *Logic*
- 11 **AI Agent1** Agent *Model*
- 12 **Default Data Loader1** Document Default Data Loader *Model*
- 13 **Download File From Google Drive** Google Drive *Service*
- 14 **Pinecone Vector Store** Vector Store Pinecone *Model*
- 15 **Pinecone Vector Store (Retrieval)** Vector Store Pinecone *Model*
- 16 **Vector Store Tool** Tool Vector Store *Model*
- 17 **Text** Set *Logic*
- 18 **Get Audio Url** Whats App *Service*
- 19 **Get Image Url** Whats App *Service*
- 20 **Only PDF File** If *Logic*
- 21 **Not supported** Whats App *Service*
- 22 **From audio to audio?** If *Logic*
- 23 **Download Audio** Http Request *Service*
- 24 **Download Image** Http Request *Service*
- 25 **Get File Url** Whats App *Service*
- 26 **Incorrect format** Whats App *Service*
- 27 **Generate Audio Response** Open Ai *Model*
- 28 **Send message** Whats App *Service*
- 29 **Transcribe Audio** Open Ai *Model*
- 30 **Analyze Image** Open Ai *Model*
- 31 **Download File** Http Request *Service*
- 32 **Fix mimeType for Audio** Code *Logic*
- 33 **Audio** Set *Logic*
- 34 **Image** Set *Logic*
- 35 **Extract from File** Extract From File *Service*
- 36 **Send audio** Whats App *Service*
- 37 **File** Set *Logic*

## How it's built

- **Starts on:** An incoming WhatsApp message
- **Steps:** 37, with 3 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Drive, Pinecone, WhatsApp
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Google Drive, Pinecone and WhatsApp accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming WhatsApp message.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 37 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 37 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%2Fmultimodal-political-ai-chatbot-for-whatsapp-text-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.

## Connects to

Each opens the other workflows that use it.

[Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[Pinecone](https://millionrounds.com/workflows?service=Pinecone#library)[WhatsApp](https://millionrounds.com/workflows?service=WhatsApp#library)

## Workflows like it

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

- [**Verify onboarding compliance documents with OpenAI** 37 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/verify-onboarding-compliance-documents-with-openai)
- [**My solution for the "Agentic Arena Community Contest" with RAG** 34 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/my-solution-for-the-agentic-arena-community-contest-with-rag)
- [**Send, chase, and e-signature with Airtable and TurboDocx** 33 steps · Airtable, Gmail](https://millionrounds.com/workflow/send-chase-and-e-signature-with-airtable-and-turbodocx)
- [**AI knowledge assistant with Gemini and OpenAI** 32 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/ai-knowledge-assistant-with-gemini-and-openai)
- [**AI-powered WhatsApp chatbot for text, voice, images, and PDF** 32 steps · calls a model · Google Docs, WhatsApp](https://millionrounds.com/workflow/ai-powered-whatsapp-chatbot-for-text-voice-images-and-pdf)
- [**Document-based RAG chat assistant with Google Drive** 32 steps · calls a model · Google Drive, Supabase](https://millionrounds.com/workflow/document-based-rag-chat-assistant-with-google-drive)