PulseAugur
中
实时 19:34:59
English(EN) Jack Dorsey's Block has unveiled Dessa, a full-duplex speech-to-speech model that listens and talks at once, with emotion, pauses and laughter produced by the v

Jack Dorsey 的 Block 公司发布 Dessa,一款类人本地语音 AI

Jack Dorsey 的公司 Block 开发了 Dessa,这是一款新颖的全双工语音模型,能够在消费级硬件上本地运行。该 AI 模型通过仅以人类语音进行训练,旨在产生类人语音,包括自然的停顿、笑声和情感语调。Block 目前正在寻找安全研究人员在 Dessa 公开之前对其进行测试,目标是探索其对社交音频、创作者配音工作和配音行业的潜在影响。 AI

影响 这款本地类人语音 AI 可能会显著改变社交音频、配音和配音行业。

排序理由 这是来自一家公司的产品发布,而不是前沿 AI 实验室的发布。

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Jack Dorsey 的 Block 公司发布 Dessa,一款类人本地语音 AI

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是来自一家公司的产品发布,而不是前沿 AI 实验室的发布。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
29 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. Mastodon — mastodon.social TIER_1 English(EN) · spookyd ·

    Jack Dorsey 的 Block 发布 Dessa,一款可本地运行的全双工语音模型,听起来非常像真人,带有笑声、停顿和情感。仅在 sp 上训练

    Jack Dorsey's Block released Dessa, a full-duplex voice model that runs locally and sounds strikingly human, with laughs, pauses and emotion. Trained only on speech, it's not public yet, and Block is seeking safety researchers to test it. # AI # VoiceAI Read more: https:// techcr…

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Jack Dorsey 的 Block 发布 Dessa,一款可同时进行语音到语音对话的全双工模型,能表达情感、停顿和笑声

    Jack Dorsey's Block has unveiled Dessa, a full-duplex speech-to-speech model that listens and talks at once, with emotion, pauses and laughter produced by the voice itself rather than bolted on as tags. Trained only on human speech on a single Nvidia GPU, it runs locally on consu…