Skip to content
Live
Trending storyPast story

Block releases Dessa AI model

5 reports5 outlets21 days agoUpdate

The story so far

AI overview

Block has released an AI model Dessa, trained solely on human conversations, which occasionally exhibits awkward and eerie conversational behaviors. Dessa is a 'pure voice-to-voice model' that can run locally on MacBook Pro M4 Max or better devices, designed to enhance human-computer understanding and security through voice interaction. Block claims that Dessa is completely trained on human voice data without using any text data, directly processing audio to capture emotions, sarcasm, laughter, and pauses in real-time, supporting full-duplex communication. The model is currently not publicly available, and Block is recruiting AI safety researchers for testing.

AI-written from the reports · Updated 21 days ago

Coverage timeline

Follow the coverage to see every side of the story.

25 Oct
  1. ITHome · AI
    Block releases full-duplex AI voice model Dessa: full human-like feel, supports local operation on Apple MacBook

    Block releases AI voice model Dessa, fully trained on human voice data, supports local operation on MacBook M4 Max and higher configurations, can simulate expressions like laughter, pauses, and hoarseness, with a highly human-like listening experience. Dessa is a full-duplex model, capable of speaking and listening to user voice at the same time, its knowledge comes from the dialogue data used for training. Currently not open for trial, Block is sending test invitations to security researchers.

  2. TechCrunch · AI
    Block’s new voice model sounds eerily human

    Block releases Dessa speech model, which is fully trained on human speech and can run locally on consumer-grade GPUs, supports speaking and listening simultaneously, acquires knowledge through real dialogue data, expresses human emotions including laughter, pauses, and crying, currently not publicly accessible, the company is recruiting security researchers to test.

24 Oct
  1. The Decoder
    Block's new AI model Dessa was trained entirely on human speech to catch emotions text-based models miss

    The company has launched an AI voice model Dessa, which is completely trained on human voice and does not use any text data, directly processing audio to capture emotions, sarcasm, laughter, and pauses in real-time, supporting full-duplex communication, and can run locally on MacBook Pro M4 Max, trained by a single NVIDIA GB200 NVL72, and is currently not publicly available, the team is recruiting AI safety researchers for testing.

  2. The Verge · AI
    Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

    Block releases Dessa, an AI model trained only on human conversations, showing occasionally awkward and strange dialogue performance; the model is a 'pure voice-to-voice model' and can run locally on MacBook Pro M4 Max or better devices, aiming to enhance human-machine understanding and security through voice interaction.