Block has developed a new AI model named Dessa, which is specifically designed to process audio directly to understand nuances like emotions, sarcasm, and pauses. Unlike text-based models, Dessa analyzes speech in real-time. While it can run on a MacBook Pro M4 Max, the model is not yet available to the public. AI
IMPACT This model could enhance real-time audio analysis for applications requiring emotional intelligence, potentially improving user interaction in voice-based systems.
RANK_REASON The item describes a new AI model from a company, but it is not a frontier release from a major AI lab.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →