Generate two-host PDF podcasts with GPT-5, Smallest AI, and Gmail
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
Community nodes
These come from third-party npm packages. In n8n 3.0 unverified community packages are off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
n8n-nodes-smallestai(Synthesize Host A Audio, Synthesize Host B Audio)
Nodes used (11)
- n8n Form Trigger
n8n-nodes-base.formTrigger - Extract from File
n8n-nodes-base.extractFromFile - OpenAI
@n8n/n8n-nodes-langchain.openAi - Split Out
n8n-nodes-base.splitOut - Switch
n8n-nodes-base.switch - Smallestai
n8n-nodes-smallestai.smallestai - Edit Fields (Set)
n8n-nodes-base.set - Merge
n8n-nodes-base.merge - Sort
n8n-nodes-base.sort - Code
n8n-nodes-base.code - Gmail
n8n-nodes-base.gmail
What it does
Generate two-host AI podcast episodes from any PDF — in 9 Indian languages or your own cloned voice — powered by Smallest AI. Turn whitepapers, research reports, blog drafts, lecture notes, or company memos into NotebookLM-style audio briefings. Native Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Marathi, Gujarati, and Punjabi support makes this the only n8n template that ships authentic Indian-language podcast generation out of the box. Good to know - Lightning V3.1 generates ~100ms time-to-first-byte; a 5-page PDF produces a 4-minute podcast in roughly 60 seconds total - Smallest AI offers a free tier — get an API key - Voice cloning lets you cast yourself or a colleague as one of the hosts using just a 10-second voice sample - Pure JavaScript audio concatenation — no FFmpeg required, works on n8n Cloud How it works - Upload a PDF via the form trigger - Extract text and pass it to GPT-5 to generate a structured 2-host script in JSON - Split the script and route each turn to the matching host's TTS branch - Smallest AI Lightning synthesizes each turn at 24 kHz with sub-100ms latency - A Code node concatenates all WAV chunks into a single audio file in correct conversational order - The finished podcast is emailed to the address you specify Set up steps - Install the n8n-nodes-smallestai community node via Settings → Community Nodes - Connect Smallest AI, OpenAI, and Gmail credentials (~5 minutes) - Pick voice IDs for Host A and Host B in the two Synthesize Host nodes (defaults: avery and devansh) - Update the recipient email in the Gmail node - Sticky notes inside the workflow walk you through each section Requirements - Smallest AI account — free tier available at smallest.ai - OpenAI API key — GPT-5 or GPT-4o-mini both work - Gmail OAuth2 credential for delivery - n8n-nodes-smallestai community node installed Customising this workflow - Swap the Form trigger for a Webhook to integrate with other apps or chatbots - Change the LLM system prompt to alter podcast format (interview, debate, monologue, kids' story) - Edit english in the prompt to generate podcasts in any of Smallest AI's supported languages — try arjun + aanya for Hindi, arvind + niharika for Tamil - Use cloned voices from the Voice Clone resource for personalized hosts - Replace Gmail with Slack, Telegram, or Drive Upload for different delivery channels