Google Research has introduced two new medical AI models: MedGemma 1.5 for image interpretation and MedASR for speech-to-text. The announcement positions both as next-generation tools for clinical settings.
MedGemma 1.5 is designed to interpret medical images, while MedASR addresses medical speech recognition. They are separate models but share a common goal of supporting healthcare workflows through generative AI.
According to the source, these are part of Google's broader generative AI initiatives in medicine. The blog highlights the importance of both visual and verbal data in medical practice.