A new NotebookLM feature lets users listen to conversations based on their sources
Google's NotebookLM, an AI research assistant powered by Gemini 1.5 Pro, has introduced a new Audio Overviews feature that converts uploaded documents into AI-generated audio discussions between two speakers.
NotebookLM, the Google's personalized AI research assistant powered by Gemini 1.5 Pro recently got a feature called Audio Overviews. NotebookLM lets users upload the most important sources for their projects, so the assistant becomes an expert. Once the sources are uploaded, NotebookLM automatically generates a Notebook guide, which summarizes the contents of the Notebook, helps users create specific outputs like FAQs, study guides, and timelines, suggests questions that help the users understand their material better, and can be used to start a conversation with the assistant and obtain responses grounded on the Notebook's sources with in-line citations.
The Audio Overviews feature builds on these features, enabling users to turn their uploaded documents into AI-generated audio discussions between two speakers. The AI-powered speakers can summarize the content, draw connections between topics present in the material, and take turns speaking. The discussions can be downloaded for offline listening. To create an Audio Overview, users only need to navigate to a Notebook containing at least one source and click the 'Generate' button in the Notebook guide.
Users should be aware that the feature has some limitations: it may take some time to generate an Audio Overview if the Notebook is too large, the speakers can only use English, there may be some introduced inaccuracies, and the discussion cannot be interrupted.
