Google is turning your favorite AI podcast hosts into polyglots

• Google’s NotebookLM now supports Audio Overviews in over 50 languages
• Users can generate AI podcasts based on uploaded information in their preferred languages
• The Gemini 2.5 Pro-powered feature maintains the same casual, conversational style regardless of language

It seems the AI ‘podcasters’ you create with Google’s NotebookLM have been playing a lot of Duolingo. The AI-generated hosts of the Audio Overview feature can now perform in more than 50 languages. Audio Overview is the NotebookLM feature that transforms the documents, videos, books, and other information you give it into an audio show hosted by a couple of AI voices.

When you make the Audio Overview now, you can go to the settings and pick an Output Language ahead of generating the audio. You can also switch languages on the fly, generate summaries for friends or students in their native tongue, or prep multilingual study guides without hiring a translator or braving the often messy results of Google Translate.

The addition may not seem like a big deal among other AI spectacles, but it’s potentially huge. Language plays a gatekeeper for so many things, especially technology. Now, Google can entice those who might be interested in playing with its AI toy without them having to learn a whole new language.

An entire global audience of people studying, teaching, researching, or just interested in learning new things can now better navigate a Google platform previously limited by English exclusivity. Teachers, for instance, can upload a hodgepodge of resources in different languages and generate a digestible audio recap in whatever language their students are most comfortable with.

Global AI podcasts

The feature is only in beta, and Google is keen to caution that there are still some problems. The voices might stumble, and you might encounter weird or wrong translations, especially in less frequently used languages. But the synthetic personalities will still discuss your research paper sources or complete home makeover guide and riff, recap, and remark on the content; it’s just that English won’t be the only tongue they do it in.

That tone matters. One of the reasons Audio Overviews clicked with users in the first place is that they don’t sound like a monotone robot trying to teach you tax law. The AI hosts crack jokes, pause for effect, and express amazement in (usually) appropriate spots.

There’s something deeply satisfying about hearing your own research about ancient Rome explained to you in Latin. It definitely makes learning the language feel more exciting. Amo audire podcasts novis linguis.

You might also like

• One of my favorite AI tools is getting an iPhone app, and here’s why you should install it
• I used NoteBookLM to help with productivity – here’s 5 top tips to get the most from Google’s AI audio tool
• Google will turn those long documents into your next favorite podcast
• I fed NotebookLM a 218-page research paper on string theory and the podcast results were mind-blowing

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He’s since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he’s continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.