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

雷峰网
雷峰网
博客园 - 聂微东
酷 壳 – CoolShell
酷 壳 – CoolShell
宝玉的分享
宝玉的分享
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
罗磊的独立博客
Hugging Face - Blog
Hugging Face - Blog
T
Tailwind CSS Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
IT之家
IT之家
博客园_首页
博客园 - 三生石上(FineUI控件)
博客园 - 叶小钗
Apple Machine Learning Research
Apple Machine Learning Research
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
量子位
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
人人都是产品经理
人人都是产品经理
美团技术团队
小众软件
小众软件
Jina AI
Jina AI
S
SegmentFault 最新的问题
博客园 - Franky
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
Generate two-host PDF podcasts with GPT-5, Smallest AI, a...
sosumit001 · 2026-05-04 · via Hacker News - Newest: "AI"

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