Current outcome
Block's Dessa is a full-duplex speech model trained solely on human conversation recordings that runs locally on MacBook Pro with M4 Max or higher; it is available only as early access to select AI safety researchers, with no parameter count, benchmark results, or model weights released.
Progress timeline
2 material updates- #01
Dessa: the most authentic full-duplex speech model ever built
Block's Dessa is presented as the most authentic full-duplex speech model yet, combining low-latency expressive conversation with local inference on a MacBook Pro M4 Max and training on just one NVIDIA GB200 NVL72.
Source evidence: dsr12
- #02
Block推出Dessa：只听人说话就能学会聊天，还能在MacBook本地运行
New coverage adds key details: Dessa was trained from scratch solely on human conversation recordings, without text data or pretrained language models; it is currently available only as early access to select AI safety researchers, with no parameter count, benchmark results, or model weights released.
State after update: Block's Dessa is a full-duplex speech model trained solely on human conversation recordings that runs locally on MacBook Pro with M4 Max or higher; it is available only as early access to select AI safety researchers, with no parameter count, benchmark results, or model weights released.
Source evidence: theblockbeats