TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Podcastfy AI – Open-source tool to generate AI audio conversations

14 点作者 highlanderNJ7 个月前

3 条评论

etewiah7 个月前
Nice. I asked a few days ago about alternatives to NotebookLM with an API and didn&#x27;t get good answers.<p>I have started creating some audio podcasts of popular hacker news threads here:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;etewiah&#x2F;gipety-for-hacker-news">https:&#x2F;&#x2F;github.com&#x2F;etewiah&#x2F;gipety-for-hacker-news</a><p>Will probably do a &quot;Show HN&quot; about it tomorrow or friday. If I get the chance I will try to do a couple using podcastfy (I agree with the other comment though - the name could be better..)<p>Great work - thanks for sharing.
评论 #41860455 未加载
highlanderNJ7 个月前
I am excited to release Podcastfy.ai: An open-source Python package and CLI tool that transforms multi-modal content into engaging, multi-lingual audio conversations using GenAI; akin to Google&#x27;s NotebookLM but open, programmatic, and customizable. You can simply &#x27;pip install podcastfy&#x27; and start using it today!<p>You can run it on a paper, your CV, a website or even on artwork images if you like as well as the combination of the above!<p>I was intrigued by Google&#x27;s newest GenAI product: NotebookLM, especially its “deep dive” podcast feature that converts uploaded content into a two-person AI-generated audio conversation. As Andrej Karpathy put it, &quot;NotebookLM [...] is a re-imagination of the UX of working with LLMs&quot; and I do agree!<p>While exploring NotebookLM, however, I got a bit frustrated with its UI which added friction to the process, leaving me yearning for more automation and customization options. This sparked a question: Could we replicate the essence of NotebookLM&#x27;s podcast feature as a customizable API?<p>To address this, I developed Podcastfy – a weekend project built using Cursor dot com - akin to NotebookLM’s podcast feature but open, programmatic, and customizable by anyone.<p>Key Features: - Generates conversational content from multiple sources (e.g. URLs, YouTube, and PDFs) and modalities (images+text) - Customizes transcript and audio generation (e.g., style, language, structure, length) - Provides sulti-language support for global content creation<p>Technical Highlights: - Flexible LLM integration with LangChain, supporting both cloud-based and local models - Support for advanced text-to-speech models (OpenAI, ElevenLabs, and Microsoft Edge) - Seamless CLI and Python package integration for automated workflows<p>The Verdict:<p>While NotebookLM&#x27;s AI-generated voices remain unparalleled in quality, this project did solve my original problem and showcased the fascinating possibilities of building GenAI products today. It&#x27;s now live on GitHub, and I&#x27;d love for you to check it out and even contribute!<p>What would you like to Podcastfy today?<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;souzatharsis&#x2F;podcastfy">https:&#x2F;&#x2F;github.com&#x2F;souzatharsis&#x2F;podcastfy</a>
tikkun7 个月前
This is great!<p>I think it&#x27;d popular more easily if:<p>rename it, and give it a new tagline<p>eg Opencast or something. and tagline: Open-source alternative to NotebookLM&#x27;s podcast feature