PulseAugur
实时 05:01:02
English(EN) Supertone Releases Supertonic v3: On-Device Text-to-Speech Model with 31-Language Support, Fewer Reading Failures, and Expression Tags

Supertone 发布 Supertonic 3 TTS,支持 31 种语言,内联表达能力

Supertone 推出了 Supertonic 3,这是一个更新的设备端文本转语音模型,现在支持 31 种语言,远超其之前的五种语言。新版本提高了准确性,减少了重复和跳过等错误,并引入了用于内联控制笑声或叹息等情绪的表情标签。尽管功能有所扩展,该模型仍保持紧凑,参数量约为 9900 万,适合在资源受限的设备上部署,无需 GPU。 AI

影响 增强了设备端 TTS 功能,可在更广泛的语言和设备上实现更自然、更具表现力的语音界面。

排序理由 该集群描述了一个具有新功能和扩展语言支持的开源文本转语音模型新版本的发布。[lever_c_demoted from research: ic=1 ai=1.0]

在 MarkTechPost 阅读 →

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

Supertone 发布 Supertonic 3 TTS,支持 31 种语言,内联表达能力

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
该集群描述了一个具有新功能和扩展语言支持的开源文本转语音模型新版本的发布。[lever_c_demoted from research: ic=1 ai=1.0]
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
117 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 [1]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Supertone 发布 Supertonic v3:支持 31 种语言、减少阅读失败且带有表情标签的设备端文本转语音模型

    <p>The Seoul-based speech AI company ships its third generation of its on-device TTS engine, adding expressive tags, improved reading stability, and a 6× increase in language coverage — all while keeping the inference contract unchanged for existing integrations.</p> <p>The post …