A pair of undergraduate students have developed an open-source AI model capable of generating realistic, podcast-quality audio. This innovative creation is drawing comparisons to Google’s NotebookLM and positions itself as a competitor in the increasingly crowded synthetic speech market, currently dominated by companies like ElevenLabs, PlayAI, and Sesame. The readily accessible nature of this new model offers a compelling alternative and democratizes access to advanced speech synthesis technology, potentially disrupting the established players.

Photo by Buro Millennial on Pexels
Photos provided by Pexels