FishAudio发布开源TTS模型Drama 3
Really cool, open weight, TTS model, just dropped.
Really cool, open weight, TTS model, just dropped.
非常酷，开源权重的 TTS 模型，刚刚发布。
Fixing one bad word in a TTS clip usually means regenerating the whole line, and the take you liked goes with it.
修复 TTS 片段中的一个坏词通常意味着重新生成整行，而你喜欢的那一遍也会随之消失。
@FishAudio just released Drama 3, it's open-weight, and the most emotive and controllable TTS model in the world
@FishAudio 刚刚发布了 Drama 3，它是开源权重的，也是全球最具情感表现力和可控性的 TTS 模型
> lets users restyle single words mid-sentence
> 允许用户在句子中途对单个词进行风格重塑
> Directions go inside square brackets in plain language, such as “barely holding it together,” and they can be written in English or the user’s own language.
> 指令以自然语言形式放在方括号内，例如“勉强维持”，可以使用英语或用户自己的语言编写。
> paired tags such as Whisper, Slower or Forceful wrap only the selected words, so a line can turn from steady to hushed halfway through.
> 成对的标签如 Whisper、Slower 或 Forceful 仅包裹所选单词，因此一句话可以在中途从平稳转为低语。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力