🚨 AI News | TestingCatalog· @testingcatalog · X·· 2026-06-16精选AI 评分75
AI 导读
Cartesia 推出 Sonic 3.5 和 Ink 2 两个模型，作为单一实时语音栈，分别负责文本转语音和语音转文本。Ink 2 在 Artificial Analysis 的流式语音转文字排行榜上排名第一。Sonic 3.5 在实时文本转语音中位列榜首，首音频延迟约 82ms。Cartesia 成为目前唯一同时拥有 #1 听与说模型的提供商。
推荐理由
Cartesia 同时发布实时语音合成和识别两个模型的迭代版，双双登顶第三方基准，80ms 首音频延迟让语音代理的交互感接近真人，做实时语音应用的开发者可以重点看一下。
正文 · 原文
Cartesia shipped Sonic 3.5 and Ink 2, two models built to run as a single real-time voice stack, with transcription on one side and speech on the other.
Ink 2 ranks first for accuracy on Artificial Analysis's streaming speech-to-text board.
Sonic 3.5 places at the top of the real-time text-to-speech view at around 82ms to first audio.
We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice agents today. New architectures enable new frontiers for speed and quality. We're now the only provider to have #1 models for both speaking and listening.在 X 查看被引用的帖子
来源：🚨 AI News | TestingCatalog · x.com