Transform podcasts into viral social media clips with Gemini AI and multi-platform posting
Ready for 3.0What this workflow does
This AI workflow has 45 nodes and runs when someone submits an n8n form (“Required Links”). Along the way it connects Google Gemini Chat Model. It also calls lemolex.app.n8n.cloud, api.assemblyai.com and api.openai.com over HTTP.
How it runs
Trigger: When someone submits an n8n form (“Required Links”).
- Download Audio Stage (HTTP Request): calls lemolex.app.n8n.cloud (POST)
- Download Audio Stage (HTTP Request): calls lemolex.app.n8n.cloud
- If: checks a condition and branches into true / false
- Download Audio Stage (HTTP Request): calls an HTTP API
- Wait: waits 30 seconds
- Transcribe Podcast Audio (HTTP Request): calls api.assemblyai.com (POST)
- Submit Job (HTTP Request): calls api.assemblyai.com (POST)
- Wait: waits 1 minutes
- Check Status (HTTP Request): calls an HTTP API
- If: checks a condition and branches into true / false
…plus 30 more steps. See the full node list below.
Services it uses
HTTP calls to: lemolex.app.n8n.cloud, api.assemblyai.com, api.openai.com, api.andynocode.com, api.upload-post.com
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 (11)
- HTTP Request
n8n-nodes-base.httpRequest - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Split Out
n8n-nodes-base.splitOut - If
n8n-nodes-base.if - Edit Fields (Set)
n8n-nodes-base.set - Wait
n8n-nodes-base.wait - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - n8n Form Trigger
n8n-nodes-base.formTrigger - Code
n8n-nodes-base.code - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches
From the author
🎯 Automatically Create and Post Engaging Clips (with Audience Retention Videos) from Podcasts Using AI! 🚀 Effortlessly transform long-form podcast content into highly engaging, viral-read clips with this end-to-end automation template. Designed for content…