What happened
Jack Dorsey's Block announced Dessa, an AI model trained 'from scratch on nothing but human conversation' that the team calls a 'true speech-to-speech model' and says can run locally on a MacBook Pro M4 Max 'or better.'
Why it matters
Dessa is meant to keep human timing and emotion in voice AI rather than flattening speech into text, and Block says it will give early access to 'a small group of AI safety researchers.'
WHO IT HITSVoice AI developers and AI safety researchers are the first audiences: Block is giving 'a small group of AI safety researchers' early access, while anyone building conversational voice interfaces may watch whether a locally runnable speech-to-speech model changes their design choices.
Summaries like this, every morning.
Block's Dessa is presented as an attempt to build a voice model without a text step: the team says today's voice AI 'flattens what we say into text and can't keep up with human timing.' The stated motivation is threefold: 'curiosity (aka fun), better understanding between humans and AI, and safety.' On safety, the team describes a scenario where a voice AI keeps going while a person is in serious pain, saying Dessa is 'a step toward fixing it.' The demonstrations Block shared include a guessing game over voice and a conversation with OpenAI's GPT-Live-1 voice model in which Dessa comes across as more natural, though the team itself notes the model is 'just very hard' to build and the examples can be 'a little awkward and uncanny.'
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
