Convert PDF documents to AI podcasts with Google Gemini and text-to-speech
Needs changesWhat this workflow does
This AI workflow has 8 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Google Gemini Chat Model. It also calls generativelanguage.googleapis.com over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- 📄 Extract Text from PDF (Extract from File): extracts data from a file (pdf)
- 🤖 Generate Podcast Script (Basic LLM Chain): sends a prompt to an LLM, with model: Google Gemini Flash 2.
- ⚙️ Prepare TTS Request (Code): runs custom JavaScript code
- 🎙️ Convert Text to Speech With Gemini (HTTP Request): calls generativelanguage.googleapis.com (POST)
- 🔧 Process Audio Response (Code): runs custom JavaScript code
- 💾 Save Podcast Audio (Write Binary File): uses Write Binary File
Services it uses
HTTP calls to: generativelanguage.googleapis.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- Write Binary File in 💾 Save Podcast Audio: replace with Read/Write Files from Disk.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| Write Binary File 💾 Save Podcast Audio | Read/Write Files from Disk |
Nodes used (7)
- Manual Trigger
n8n-nodes-base.manualTrigger - Extract from File
n8n-nodes-base.extractFromFile - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Write Binary File
n8n-nodes-base.writeBinaryFile
From the author
Convert PDF documents to AI-generated podcasts with Google Gemini and Text-to-Speech Transform any PDF document into an engaging, natural-sounding podcast using Google's Gemini AI and advanced Text-to-Speech technology. This automated workflow extracts text…