InertiaRSS Track and read blogs, news, and tech you care about
Read Original Open in InertiaRSS

Recommended Feeds

博客园 - 司徒正美
V
V2EX
T
Tailwind CSS Blog
有赞技术团队
有赞技术团队
aimingoo的专栏
aimingoo的专栏
Apple Machine Learning Research
Apple Machine Learning Research
IT之家
IT之家
Blog — PlanetScale
Blog — PlanetScale
A
About on SuperTechFans
月光博客
月光博客
T
The Blog of Author Tim Ferriss
宝玉的分享
宝玉的分享
Martin Fowler
Martin Fowler
博客园 - 聂微东
The GitHub Blog
The GitHub Blog
V
Visual Studio Blog
WordPress大学
WordPress大学
酷 壳 – CoolShell
酷 壳 – CoolShell
Engineering at Meta
Engineering at Meta
GbyAI
GbyAI

阮一峰的网络日志

科技爱好者周刊(第 396 期):互联网通信的替代方案 科技爱好者周刊(第 396 期):互联网通信的替代方案 - 阮一峰的网络日志 科技爱好者周刊(第 395 期):软件开发的第三种方式 科技爱好者周刊(第 395 期):软件开发的第三种方式 - 阮一峰的网络日志 科技爱好者周刊(第 393 期):脑腐状态 科技爱好者周刊(第 392 期):axios 投毒与好莱坞式骗术 科技爱好者周刊(第 391 期):AI 的贫富分化 科技爱好者周刊(第 390 期):没有语料,大模型就是智障 套壳中国大模型撑起500亿美元估值?扒一扒 Cursor 的"套壳"疑云 科技爱好者周刊(第 389 期):未来如何招聘程序员 科技爱好者周刊(第 388 期):测试是新的护城河 零安装的"云养虾":ArkClaw 使用指南 科技爱好者周刊(第 387 期):你是领先的 科技爱好者周刊(第 386 期):当外卖员接入 AI 字节全家桶 Seed 2.0 + TRAE 玩转 Skill 科技爱好者周刊(第 385 期):马斯克害怕中国车企吗? 智谱旗舰 GLM-5 实测:对比 Opus 4.6 和 GPT-5.3-Codex 科技爱好者周刊(第 384 期):为什么软件股下跌 科技爱好者周刊(第 383 期):你是第几级 AI 编程 Kimi 的一体化,Manus 的分层 科技爱好者周刊(第 382 期):独立软件的黄昏 AI native Workspace 也许是智能体的下一阶段 科技爱好者周刊(第 381 期):中国 AI 大模型领导者在想什么 科技爱好者周刊(第 380 期):为什么人们拥抱"不对称收益" 科技爱好者周刊(第 379 期):《硅谷钢铁侠》摘录 我如何用 AI 处理历史遗留代码:MiniMax M2.1 升级体验 科技爱好者周刊(第 378 期):预测是新的互联网热点 科技爱好者周刊(第 377 期):14万美元的贫困线 科技爱好者周刊(第 376 期):太空数据中心的争议 科技爱好者周刊(第 375 期):一扇门的 Bug 终于有人做了 Subagent,TRAE 国内版 SOLO 模式来了 科技爱好者周刊(第 374 期):6GHz 的问题 VS Code 使用国产大模型 MiniMax M2 教程 科技爱好者周刊(第 373 期):数据模型是新产品的核心 国产大模型接入 Claude Code 教程:以 Doubao-Seed-Code 为例 科技爱好者周刊(第 372 期):软件界面如何设计 大模型比拼:MiniMax M2 vs GLM 4.6 vs Claude Sonnet 4.5 科技爱好者周刊(第 371 期):一个乐观主义者的专访 科技爱好者周刊(第 370 期):正确的代码高亮 错误处理:异常好于状态码 科技爱好者周刊(第 369 期):Tim 与罗永浩的对谈 科技爱好者周刊(第 368 期):不要这样管理软件团队 一天之内,智谱和 Anthropic 都发了最强编程模型 科技爱好者周刊(第 367 期):Nano Banana 的几个妙用 科技爱好者周刊(第 366 期):旧金山疯狂的 AI 广告 科技爱好者周刊(第 365 期):流量变现正在崩塌 科技爱好者周刊(第 364 期):最难还原的魔方 科技爱好者周刊(第 363 期):最好懂的神经网络解释 科技爱好者周刊(第 362 期):GitHub 工程师谈系统设计 科技爱好者周刊(第 361 期):暗网 Tor 安全吗?
Google's NotebookLM can now generate Chinese podcasts
阮一峰 · 2025-05-01 · via 阮一峰的网络日志

Two days ago, Google released an announcement .

Its AI note-taking product NotebookLM, now supports generating podcasts in 50 languages (originally only supported English).

I really have to share this news; finally, we can generate Chinese podcasts. This is the feature I've always wanted, and I believe many of you would want it too.

Let me demonstrate it for you all to hear the results, which will surprise you.

First, visit its official website , click on the settings in the upper right corner, and select "Output Language" (Output Language).

Switch to "Chinese (Simplified)".

Then, create a new notebook on the homepage. Generally, one learning topic corresponds to one notebook.

As a demonstration, I created a notebook titled "Chinese Novels." After entering it, I uploaded Lu Xun's "The True Story of Ah Q" on the Source (Raw Materials) tab.

Note that the file format for uploads is currently limited to PDF, TXT, and Markdown.

Additionally, after testing, I found that if the uploaded PDF is a scanned image, it will automatically perform text recognition.

Next, switch to the Studio (Studio) tab and click the Generate (Generate) button to start creating the podcast.

After a few minutes, the podcast is ready, featuring a man and a woman discussing the materials you uploaded.

Give it a listen and see if it doesn't resemble those carefully prepared live podcasts.

NotebookLM can not only upload text materials but also generate podcasts for websites and YouTube videos.

I randomly found a YouTube English video about the photography capabilities of domestic flagship phones.

Below is the generated podcast.

After listening, I felt that there was no need to watch the video. Moreover, Chinese podcasts are easier to grasp the key points than English videos.

In short, with Chinese podcasts, any dull learning material can become an accessible podcast program. You can listen while walking, resting, exercising, or driving, increasing both the time and ways of learning.

It is worth noting that free accounts can only generate three podcasts per day, and more require payment.

Besides podcasts, NotebookLM's AI note-taking feature is also very useful.

You can upload your own learning materials, or use it to search for learning materials on a specific topic.

Below are the learning materials on PostgreSQL databases that I found using it.

After selecting the learning materials, you can chat with them.

It will also automatically generate various notes: study guides, content summaries, common questions, timelines, and more.

That's the basic usage of NotebookLM.

My review is that NotebookLM is a revolutionary note-taking tool and belongs to the few AI products that are truly highly useful.

It will change the way of taking notes and learning, and every learner should be aware of such a tool.

It is a product of Google, and it seems there are no competitors yet. Hope domestic manufacturers can produce alternatives.

(End)