Event ·Multi-source

Block 推出语音模型 Dessa，直接处理音频以识别情绪与讽刺

Block（Square 和 Cash App 母公司）发布了语音模型 Dessa，直接处理音频输入，不经过文本转录环节。该模型专为识别语音中的情绪、讽刺和停顿设计，可实时运行。Dessa 能在 MacBook Pro M4 Max 上本地部署运行。目前模型尚未对外公开。

Current read

Square 母公司 Block 做了个叫 Dessa 的语音模型，不走文字转录，直接听音频抓情绪、讽刺和停顿，一台 MacBook Pro M4 Max 就能跑。

3 sources47° AI heatLast updated 2026/10/24 14:09:46

Evidence

3 sources

Primary sourceDecoder

2026/10/24 14:09:46View source

Related source 1AIGCLINK

2026/10/24 03:24:49View source

Related source 2TestingCatalog

2026/10/23 22:56:26View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story