English(EN) 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

Jack Dorsey 的 Block 发布 Dessa，一个类人语音模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-24 16:12

Jack Dorsey 创立的公司 Block 揭晓了 Dessa，一个新颖的全双工语音模型。该模型独一无二，因为它仅使用单个 Nvidia GPU 和人类语音进行训练，并且可以在消费级硬件上本地运行。Dessa 通过将情感细微差别直接集成到语音合成中，而不是依赖外部标签来区分自己。虽然尚未公开发布，但 Block 正在寻求安全研究人员来评估其被用于欺骗的可能性。 AI

影响该模型在消费级硬件上运行以及将情感细微差别直接集成到语音中的能力，可能带来更自然、更易于访问的 AI 语音交互。

排序理由这是由一位知名科技人物创立的公司发布的产品，但它不是来自主要 AI 实验室的前沿 AI 模型发布。

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是由一位知名科技人物创立的公司发布的产品，但它不是来自主要 AI 实验室的前沿 AI 模型发布。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — mastodon.social TIER_1 English(EN) · [email protected] · 2026-10-24 16:12

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

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, a…

链接 techcrunch.com/…/blocks-new-voice-model-s…

本文如何被排名

报道来源 [1]

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

相关实体

相关话题