CosyVoice3 TT TT TTT TTT T TT TT T T TTT TTT TTT
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
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 CosyVoice3
CosyVoice3 is the newest generation from Alibaba's FunAudioLLM team and a clear step up from CosyVoice 2. It introduces bi-streaming inference with roughly 150ms latency and instruction-based control, letting you steer emotion, speed, and volume through prompts. Speaker similarity for zero-shot voice cloning is improved, and coverage spans 9 languages plus 18 Chinese dialects. An RL-tuned variant pushes prosody to a state-of-the-art level. With a 5,000-character ceiling, fast generation, and strong cloning, it's geared toward multilingual production TTS and real-time applications.
最佳: Multilingual production TTS, real-time applications, voice cloning
全部浏览 CosyVoice3 声音一眼看一眼,
- 开发者
- Alibaba (FunAudioLLM)
- 许可证
- Apache 2.0
- 级别
- standard
- 速度
- fast
- 语音克隆
- 是
- 语言
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- 最大字符
- 5000