VITS TT TT TTT TTT T TT TT T T TTT TTT TTT
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
在 SSML 标记中折行文本以精确控制 :
<speak><prosody rate="slow">Slow speech</prosody></speak>
标记选中模式的理解度 - 单击将一个输入到文本中, 发生时 :
这个模型读的是简单的文字, 所以内嵌标签会被忽略。 对于基于标签的情感, 请切换到像 Orpheus 或 Bark 这样的表达模式 。
定义自定义发音( Word = 发音) :
关于 VITS
VITS — Variational Inference with adversarial learning for end-to-end Text-to-Speech — was introduced by Jaehyeon Kim and collaborators in 2021 and became a foundational architecture for modern neural speech. Rather than the older two-stage pipeline, it synthesizes audio in a single parallel end-to-end pass, pairing a variational autoencoder with normalizing flows and a GAN-style adversarial training process to lift naturalness. At about 25M parameters and trained on ~585 hours, it produces natural prosody at fast inference speeds and supports multiple speakers. It serves as a solid general-purpose, free baseline and underpins many later models such as Piper and MeloTTS.
最佳: General-purpose text-to-speech with natural prosody
全部浏览 VITS 声音一眼看一眼,
- 开发者
- Jaehyeon Kim et al.
- 许可证
- MIT
- 级别
- free
- 速度
- fast
- 语音克隆
- 否 无
- 语言
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- 最大字符
- 2000