aifollow.news
Search
Dessa can listen while speaking and vary its voice, pace and emotion during a conversation. Block says it can run locally on a MacBook with an M4 Max or higher configuration. The company is inviting safety researchers to test risks of voice agents deceiving people; public trials are not yet available.
Coverage of the same occurrence shares a node; subsequent developments have their own nodes.
Block announced Dessa, saying it was trained from scratch solely on human conversation and can hold a two-way speech conversation. In a chat Block shared, the exchange was mostly natural, though the model initially mistook the speaker for someone named “Ronaldo.” The excerpt does not establish Block’s claim that it is the first such model.
By original publication time, with each report's bookmarks and feedback preserved.
Dessa can listen while speaking and vary its voice, pace and emotion during a conversation. Block says it can run locally on a MacBook with an M4 Max or higher configuration. The company is inviting safety researchers to test risks of voice agents deceiving people; public trials are not yet available.
Block introduced Dessa, a voice model that can listen and speak at the same time. The company says it can convey details such as pauses and laughter directly through speech and run locally on a consumer-grade computer such as a MacBook M4 Max or better. Dessa is not publicly accessible yet, and Block is inviting safety researchers to test it.
Block announced Dessa, saying it was trained from scratch solely on human conversation and can hold a two-way speech conversation. In a chat Block shared, the exchange was mostly natural, though the model initially mistook the speaker for someone named “Ronaldo.” The excerpt does not establish Block’s claim that it is the first such model.