Library / Image, Video & Audio
Image, Video & Audio
Convert PDFs to AI Podcasts with Gemini and Text-to-Speech
When you upload a PDF, this extracts the text, has Gemini write a podcast script and converts it to speech audio.
What it does
## 🎯 Main Template Overview What this workflow does: - Extracts text from uploaded PDF files - Generates conversational podcast script using AI - Converts script to natural-sounding audio - Saves final podcast as WAV file Setup required: - Google Gemini API key (for AI script generation) - Google PaLM API credentials (for TTS) - File upload capability
The steps
- 🎬 Start: Upload PDF File
- 📄 Extract Text from PDF
- 🤖 Generate Podcast Script
- Google Gemini Flash 2.0
- ⚙️ Prepare TTS Request
- 🎙️ Convert Text to Speech With Gemini
- 🔧 Process Audio Response
- 💾 Save Podcast Audio
Similar automations