PulseAugur
中
实时 10:27:40
English(EN) Gradium AI has released a new default text-to-speech model achieving an 81.0% human-rated pass rate on a 500-sentence hard-case set across five languages. The m

Gradium AI 发布新的 TTS 模型，难句通过率为 81%

作者 PulseAugur 编辑部 · [2 个来源] ·

Gradium AI 发布了一款新的默认文本转语音模型，据报告在五种语言的难句测试集中达到了 81.0% 的人工评级通过率。该新模型显著优于其前代产品，提供 216 毫秒的首音频时间，比之前快了 170 毫秒。为提高透明度和促进进一步研究，该公司已在 Hugging Face 上公开了其 500 个句子的评估数据集。 AI

影响 此次发布为文本转语音模型的准确性和速度树立了新的标杆，可能影响更强大的语音代理在客户服务和其他应用中的开发。

排序理由 Gradium AI 发布新的默认 TTS 模型，包含性能指标和比较。[lever_c_demoted from frontier_release: ic=2 ai=1.0]

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 →

Gradium AI 发布新的 TTS 模型，难句通过率为 81%

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
Significant
Gradium AI 发布新的默认 TTS 模型，包含性能指标和比较。[lever_c_demoted from frontier_release: ic=2 ai=1.0]
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
58 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. MarkTechPost TIER_1 English(EN) · Michal Sutter ·

    Gradium AI 发布全新默认 TTS 模型：216 毫秒首次音频延迟下硬语料通过率达 81.0%

    <p>Speed and accuracy usually pull against each other in text-to-speech. Gradium AI's new default model reports both: an 81.0% human-rated pass rate on 500 hard sentences across five languages, at 216 ms P50 time-to-first-audio on Coval. The evaluation set is open on Hugging Face…

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

    Gradium AI 发布了新的默认文本转语音模型，在五种语言的 500 个句子难例集上实现了 81.0% 的人工评级通过率。该模型

    Gradium AI has released a new default text-to-speech model achieving an 81.0% human-rated pass rate on a 500-sentence hard-case set across five languages. The model delivers 216ms median time-to-first-audio, 170ms faster than its predecessor. The evaluation set is openly availabl…

相关实体

相关话题