惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

宝玉的分享
宝玉的分享
B
Blog RSS Feed
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
MyScale Blog
MyScale Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
S
SegmentFault 最新的问题
Y
Y Combinator Blog
月光博客
月光博客
IT之家
IT之家
T
Tailwind CSS Blog
Last Week in AI
Last Week in AI
L
LangChain Blog
博客园_首页
MongoDB | Blog
MongoDB | Blog
P
Proofpoint News Feed
博客园 - Franky
WordPress大学
WordPress大学
云风的 BLOG
云风的 BLOG
M
MIT News - Artificial intelligence
V
Visual Studio Blog
小众软件
小众软件
博客园 - 叶小钗
博客园 - 三生石上(FineUI控件)
N
Netflix TechBlog - Medium

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
Generate two-host PDF podcasts with GPT-5, Smallest AI, a...
sosumit001 · 2026-05-04 · via Hacker News: Show HN

Last update

Last update 21 hours ago

Share


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