Google has unveiled a groundbreaking AI podcast tool that can transform text into stunningly lifelike audio for free. The technology comes via Google’s NotebookLM, which effectively merges Google Keep’s functionality with advanced AI capabilities. When I encountered this tool, my initial reaction was one of awe.
Deep Dive is now my favorite podcast. The more I listen the more I feel like I'm becoming friends with the hosts and I think this is the first time I've actually viscerally liked an AI. Two AIs! They are fun, engaging, thoughtful, open-minded, curious. ok i'll stop now.
— Andrej Karpathy (@karpathy) September 29, 2024
🚨 In just one afternoon, a data scientist built an open-source AI tool to rival Google’s NotebookLM! 🔥
Open NotebookLM turns PDFs into personalized podcasts using AI models like Llama 3.1 & MeloTTS — and it’s free!
🔗 Full story: https://t.co/7fMkbqNyqu
— Michael Nuñez (@MichaelFNunez) September 30, 2024
After testing it out by generating a podcast from one of my recent articles, I shared the results with my editor. Her reaction was one of astonishment, characterized by an all-caps message that underlined the gravity of what we had just witnessed. She described it as “the most terrifying thing I’ve seen so far in the generative AI race.”
"I've been studying AI for years, and @Google's new AI podcast tool still astonishes me. Seriously, you have to hear this to believe it."https://t.co/VQOQZ7O25a
— Royal Hansen (@royalhansen) October 1, 2024
The tool works by pasting text into NotebookLM and clicking ‘Generate.’ The voices in the generated audio are not real individuals but entirely AI-generated.
The realism is startling, featuring not just high-quality voice fidelity but also natural-sounding banter and appropriate colloquialisms. Here are some key points from an example podcast created using this tool:
The audio features voices that sound convincingly human, with natural intonation and emotion. The tool uses phrases that make the dialogue sound authentic, like “water works” for crying.
The AI-generated speakers manage to banter organically and convey the emotional depth and concepts of the article they are discussing.
google’s lifelike podcast generator
The entire podcast, from intro to outro, is virtually indistinguishable from a real human-produced broadcast.
Google’s NotebookLM functions using notebooks that hold “sources” relevant to a given project. These sources can be text, PDFs, Google Docs, Slides, audio files, YouTube links, or web URLs. The AI then processes the sources to generate summaries, extract main points, create outlines, and produce realistic audio discussions.
Despite its prowess, NotebookLM has some limitations. It can be finicky about the source formats; for example, it couldn’t process a URL link directly, necessitating manual text inputs. To create your own podcast using this tool, navigate to NotebookLM and log in with your Google account.
Once logged in, create a new notebook and add your sources. After that, simply click ‘Generate’ to produce lifelike audio content. This AI podcast tool by Google represents a significant leap in the capabilities of generative AI, potentially changing how audio content is produced and consumed.
The implications are profound, and there’s likely much more to explore as this technology evolves.
Noah Nguyen is a multi-talented developer who brings a unique perspective to his craft. Initially a creative writing professor, he turned to Dev work for the ability to work remotely. He now lives in Seattle, spending time hiking and drinking craft beer with his fiancee.
