Check Out the Many Uncanny, Human-ish Voices From Block's New AI Model

Block released Dessa, an AI voice model trained solely on human conversation that processes and generates audio directly via speech-to-speech architecture to produce highly naturalistic, emotive human-like voices. The model can run locally on high-end Macs and is designed to enhance conversational AI realism and address emotional comprehension gaps.

This Wire brief sits within Fusion42's coverage of AI & ML.