Block Unveils Dessa Speech Model, Seeks Safety Researchers Before Public Access

1. 00:00
   TechCrunch · AI

   Block introduces Dessa, a local voice model with humanlike expression

   Block introduced Dessa, a full-duplex speech model that can talk and listen simultaneously, with expressions including laughter, pauses, and cries. Block says it was trained entirely on human speech using a single NVIDIA GPU and can run locally on a MacBook M4 Max or better. Dessa has no public access yet, and Block is inviting safety researchers to test it.

1. 22:09
   The Decoder

   Block unveils Dessa, a speech model trained entirely on human audio

   Block unveiled Dessa, an AI model it says was trained from scratch entirely on human speech without text data, processing audio directly to capture emotions, sarcasm, laughter, and pauses in real time. It supports simultaneous listening and speaking, runs locally on a MacBook Pro M4 Max, and was trained on a single NVIDIA GB200 NVL72. Dessa is not publicly available yet; the team is seeking AI security researchers to test for unexpected risks.

2. 03:32
   The Verge · AI

   Block announces Dessa, a speech-to-speech AI model trained on human conversation

   Jack Dorsey’s Block announced Dessa, an AI model trained from scratch solely on human conversation. The team describes it as a speech-to-speech model that can run locally on a MacBook Pro M4 Max “or better,” while shared demos show mostly natural exchanges with occasional awkward moments. Block plans to give a small group of AI safety researchers early access.

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.