Dessa, a full-duplex speech model developed by Block, is trained entirely on human speech and aims to capture nuanced vocal characteristics without relying on voice tags.
Claims
Dessa, a full-duplex speech model developed by Block, is trained entirely on human speech and aims to capture nuanced vocal characteristics without relying on voice tags.
Parent: AIEntity: DessaImpact: positiveDate: Oct 24, 2026 - Oct 25, 2026Target: Dessa's ability to capture nuanced vocal characteristics without voice tags
The release of Dessa by Block raises concerns about its potential to deceive callers and the ethical implications of such advanced AI capabilities.
Parent: AIEntity: DessaImpact: negativeDate: Oct 24, 2026 - Oct 25, 2026Target: The ethical implications of Dessa's potential to deceive callers
Source posts
Jack Dorsey's Block has released Dessa, a full-duplex speech model trained entirely on human speech on a single Nvidia GPU, running locally on consumer hardware. Unlike rivals that bolt emotion on with voice tags, Dessa builds nuance into the voice itself. No public access yet, and Block has asked safety researchers to test whether it can deceive callers. https://techcrunch.com/2026/10/24/blocks-new-voice-model-sounds-eerily-human/ #Tech #Startup #News #AI
0 boosts · 0 favs · 0 replies · Oct 24, 2026
#tech#startup#news#ai
Block's latest #AI model Dessa was trained entirely on human speech — and it shows
Jack Dorsey and Block, Inc. just took us one step closer to the singularity and it's simultaneously awesome and terrifying.
https://mashable.com/tech/block-unveils-new-ai-model-dessa-trained-entirely-on-human-speech
#NLP #Tech
0 boosts · 0 favs · 0 replies · Oct 25, 2026
#tech#nlp#ai