@vista8: Last night I casually tested Knowly developed by the @Ethan_Yang_AI team. Tried interpreting YouTube videos and arXiv papers – the results were stunning. Except for a rather limited free quota and slightly slow vector processing. In terms of both product interaction and interpretation quality, it's no less impressive than NotebookLM. With a Chrome extension that has only a few users but has already been selected by Google as a featured pick, its strength is evident. Official site in comments https://t.co/62NkT3pO4G
Summary
Introduces Knowly AI tool, capable of interpreting YouTube videos and arXiv papers with impressive results. Interaction and interpretation quality rival NotebookLM. Comes with a Chrome extension already featured by Google. Drawbacks: limited free quota and slightly slow vector processing.
View Cached Full Text
Cached at: 05/14/26, 10:34 AM
Last night, I happened to try out knowly, developed by @Ethan_Yang_AI’s team.
I tested it with YouTube videos and arXiv papers — the results were impressive.
Apart from the slightly limited free quota and somewhat slow vector processing,
both the product interaction and the interpretation quality are on par with NotebookLM.
The accompanying Chrome extension has barely any users yet, but it’s already been featured by Google — that says a lot about its quality.
Official site in the comments: https://t.co/62NkT3pO4G
Similar Articles
@levinomad: How I quickly learn from a 2-hour long video in just 10 minutes. Currently, many primary sources of AI knowledge are on YouTube, like Andrej Karpathy, but their videos are too long to watch. Notebook LM's note-taking tools are too weak. Currently, http://le…
Introduces a tool called LearnSmart, which can convert long videos (such as Andrej Karpathy's AI lectures) into editable notes and mind maps, helping users learn quickly.
@yhslgg: Old Yang shares another gem open-source tool—KrillinAI, 10,000 stars on GitHub, a must-see for multilingual audio/video content! In a nutshell: from video download to subtitle translation, AI dubbing, video compositing, the entire pipeline is covered, and it can even auto-generate platform covers, supporting Bilibili, Douyin, Xiaohongshu, YouTube…
KrillinAI is an open-source tool that integrates the entire workflow of video downloading, subtitle translation, AI dubbing, and video compositing. It supports context-aware translation, voice cloning, auto layout, and cover generation, and is compatible with multiple AI models, suitable for multilingual audio/video content creation and distribution.
@Etudecn: https://x.com/Etudecn/status/2073072648922481000
The article criticizes that most users are currently using AI inefficiently, points out that there are faster methods that are not widely known, and mentions AI tools such as Claude, GPT, and Mira.
@hank_aibtc: Whoa, this thing really blew my mind. Dug up a local tool called KrillinAI, free, video translation, precise subtitles, ultra-natural voiceover, voice cloning, the whole pipeline in one go. Chinese-English translation is especially stable, Whisper recognition accuracy is ridiculously high, LLM translates segment by segment without losing context, CosyV…
Introducing KrillinAI, a free locally-run video translation tool that supports precise subtitles, natural voiceover, and voice cloning. It integrates Whisper, LLM, and CosyVoice, and supports Win/Mac and yt-dlp.
@grgerwcwetwet: Recommending an open-source project: qiaomu-anything-to-notebooklm. Someone built a hardcore tool with Claude, and after seeing it, I just want to say: Knowledge management folks should definitely bookmark this. You can throw in any content—WeChat public accounts, YouTube, podcasts, PDFs, Word, Excel…
Recommending an open-source project qiaomu-anything-to-notebooklm, based on Claude to automatically organize multi-source content (WeChat public accounts, YouTube, PDFs, etc.) and generate podcasts, PPTs, mind maps, all through natural language operations.