Sonic-3.5 和 Ink-2 语音模型发布，声称登顶流式榜单

精选理由

Karan Goel 发了两个新模型，Sonic-3.5 做 TTS 排名第一，Ink-2 做 STT 也是第一，说是唯一一家听说都做到顶的。做语音智能体的话看看。

AI 摘要

Karan Goel 团队发布 Sonic-3.5（文本转语音）和 Ink-2（语音转文本）两种流式模型。新架构实现了速度和质量的突破，将两者推向各自类别的榜首。该团队自称是目前唯一同时拥有排名第一的语音输入和输出模型的提供商。

原文 · Jerry Liu

congrats on the release!

congrats on the release! Karan Goel @krandiash 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. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 6 👀 454 📊 1 ⚡

查看原推