Skip to content
turkai.ioA plain-language guide to AI
Voice and musicSource: TechCrunch

Block’s voice model Dessa laughs, pauses and sounds eerily human

Block, the company led by Jack Dorsey, unveiled Dessa, a full-duplex speech-to-speech model that can listen and talk at the same time. It generates speech with expressions such as laughs, pauses and cries, and holds conversations without a separate large language model. Block says Dessa can run locally on a MacBook M4 Max or better. It is not publicly available yet; Block has asked safety researchers to test it, especially for cases where a voice agent could deceive people.

  • AI voice
  • voice model
  • Dessa
  • Block

Summary written by turkai.io; the original article belongs to its publisher.