Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech

Block's AI lab released Dessa, a full-duplex speech-to-speech model trained only on human conversation audio, according to MarkTechPost. Dessa runs locally on a MacBook Pro M4 Max, but Block published no model size, benchmarks or weights. The release gives developers a locally runnable conversational speech model while leaving its performance unverifiable against published evaluations.