PulseAugur
中
实时 02:09:59
English(EN) 🎨 Kokoro 82M v1.0 is the top downloadable TTS model, but trails Qwen-Audio-3.0-TTS-Plus by 173 ELO in blind human preference. https:// olud.ai/media-leaderboard

Kokoro 82M v1.0 领跑开源 TTS,接近商业级质量

Kokoro 82M v1.0 已被公认为领先的开源文本转语音模型。在盲人偏好测试中,它仅以微弱劣势落后于商业模型,比 SpeechifyAI 的 Simba 3.2 低 174 ELO,比 Qwen-Audio-3.0-TTS-Plus 低 173 ELO。这一表现表明,可下载模型正在迅速接近商业产品的质量。 AI

影响 这一发展标志着开源 TTS 能力的重大进步,有可能使高质量语音合成的获取民主化。

排序理由 发布了具有基准性能数据的新开源模型。

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 →

Kokoro 82M v1.0 领跑开源 TTS,接近商业级质量

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
Research
发布了具有基准性能数据的新开源模型。
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
57 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 — fosstodon.org TIER_1 English(EN) · [email protected] ·

    🎨 Kokoro 82M v1.0 是顶级的开源 TTS 模型,在盲人偏好测试中仅以 174 ELO 分之差落后于 Simba 3.2 (SpeechifyAI)。这一差距表明可下载模型有多接近

    🎨 Kokoro 82M v1.0 is the top open-source TTS model, just 174 ELO behind Simba 3.2 (SpeechifyAI) in blind human preference. That gap shows how close a downloadable model gets to a commercial one. Click to see the full leaderboard. https:// olud.ai/media-leaderboard.html # OpenSour…

  2. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    🎨 Kokoro 82M v1.0 是下载量最高的 TTS 模型,但在盲人偏好测试中以 173 ELO 的劣势落后于 Qwen-Audio-3.0-TTS-Plus。https:// olud.ai/media-leaderboard

    🎨 Kokoro 82M v1.0 is the top downloadable TTS model, but trails Qwen-Audio-3.0-TTS-Plus by 173 ELO in blind human preference. https:// olud.ai/media-leaderboard.html # OpenSource # GenerativeAI # StableDiffusion # AI