Convert RSS feeds into a podcast with Google Gemini, Kokoro TTS, and FFmpeg
Ready for 3.0What this workflow does
This AI workflow has 28 nodes and runs on a schedule (every day at 08:00). Along the way it connects Google Gemini Chat Model and Telegram. It also calls tts-kokoro.mfxikq.easypanel.host over HTTP.
How it runs
Trigger: On a schedule (every day at 08:00).
- Fetch RSS 1: Folha de SP (RSS Read): reads an RSS feed
- Fetch RSS 2: GE (RSS Read): reads an RSS feed
- Clean Up Fields (Edit Fields (Set)): sets 5 fields: title, pubDate, link…
- Clean Up Fields (Edit Fields (Set)): sets 5 fields: title, pubDate, link…
- Merge: merges the data from its input branches
- Filter: keeps only the items that match a condition
- Prepare Data for AI (Code): runs custom JavaScript code
- Create Temp Directory (Execute Command): runs a shell command on the n8n host
- Generate Text Digest (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
- Generate Podcast Script (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
…plus 15 more steps. See the full node list below.
Services it uses
HTTP calls to: tts-kokoro.mfxikq.easypanel.host
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (14)
- Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Schedule Trigger
n8n-nodes-base.scheduleTrigger - RSS Read
n8n-nodes-base.rssFeedRead - Edit Fields (Set)
n8n-nodes-base.set - Merge
n8n-nodes-base.merge - Filter
n8n-nodes-base.filter - Code
n8n-nodes-base.code - Execute Command
n8n-nodes-base.executeCommand - AI Agent
@n8n/n8n-nodes-langchain.agent - Telegram
n8n-nodes-base.telegram - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - If
n8n-nodes-base.if - HTTP Request
n8n-nodes-base.httpRequest - Read/Write Files from Disk
n8n-nodes-base.readWriteFile
From the author
🎧 Daily RSS Digest & Podcast Generation This workflow automates the creation of a daily sports podcast from your favorite news sources. It fetches articles, uses AI to write a digest and a two-person dialogue, and produces a single, merged audio file with…