Together AI 宣布发布 Cartesia Sonic 3.5，这是一款专为实时应用设计的新型文本转语音 (TTS) 模型。该模型具有低于 90 毫秒的延迟，支持 42 种语言，并具备上下文感知发音和准确的文本跟随功能。开发者现在可以通过 Together AI 的语音查找器工具访问超过 150 种 Cartesia Sonic 3.5 语音，以便在部署前进行比较和选择。 AI
影响 通过低延迟和广泛的语言支持增强了实时 TTS 功能，可能改善语音代理交互。
排序理由 前沿实验室的模型发布公告。
在 X — Together (inference / OSS) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Try Sonic 3.5 in voice finder: https://t.co/5L8df8yzQM Model page: https://t.co/0cvwZAsguA
Sonic 3.5 is built for real-time TTS where latency, pronunciation, and delivery matter. → Sub-90ms latency → Native support for 42 languages → Accurate transcript following for codes, IDs, and structured speech → Context-aware pronunciation for words like read, bass, and bow
Cartesia Sonic 3.5 is now available on Together AI. We added 150+ @cartesia Sonic 3.5 voices to voice finder, so developers can listen, compare, and pick the right voice for real-time agents before deploying on Together AI. https://t.co/U3dk6hcMub