In a move to support multilingual content, Google has expanded the "Audio Overviews" feature within its NotebookLM platform to include more than 50 languages, including French, Arabic, Turkish, and Hindi.
Launched last year, this feature turns documents and written content into audio summaries styled like podcasts. It offers users a new way to digest complex material through AI-generated conversational overviews.
According to Google, users can now choose the language they want to listen in, rather than being limited to their Google Account's default language.
The new language option can be enabled through NotebookLM settings by clicking the top-right corner and selecting "Output Language," which reveals the full expanded list.
Google emphasized that this is still an early stage in development, and improvements will continue based on user feedback.
The service has already expanded to over 200 countries and now includes interactive updates that allow users to control the playback experience, including real-time engagement with the virtual "hosts" of the summaries.
Moreover, Audio Overviews has been integrated into other tools, such as the Gemini chatbot and Google Docs, enabling users to convert different types of written content into dynamic audio.
The updated list now includes languages like Amazigh, Bengali, Greek, Norwegian, Urdu, and Tamil, along with other widely spoken European, Asian, and African languages. This opens new possibilities for educators, students, and researchers to access information in their native language or preferred study language.
For instance, Google gave an example of a teacher preparing a lesson on the Amazon rainforest. They could gather reference materials in different languages—such as a documentary in Portuguese, a research paper in Spanish, and reports in English—upload them to NotebookLM, and generate a unified podcast-style summary in the language of the classroom.
This update enhances learning and research experiences with the help of AI tools, offering users more flexibility and control over language, while laying the foundation for even broader developments in personalized audio content delivery worldwide.
