CosyVoice 2 TTS
Alibaba Tongyi Lab's streaming TTS reaching human-parity naturalness with near-zero latency and zero-shot cloning.
SSML-i siltidesse teksti segamine täpseks kontrollimiseks:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Sildid valitud mudelil mõistavad ~ klõpsa ühe kukutamiseks teksti, kus see juhtub:
See mudel loeb lihtsat teksti, nii et sisemisi silte ignoreeritakse. Sildil põhinevate emotsioonide puhul lülituge ekspressiivsele mudelile nagu Orpheus või Bark.
Kohandatud häälduste määramine (sõna = hääldus):
Info CosyVoice 2
CosyVoice 2, from Alibaba's Tongyi Lab, was designed to make high-quality speech viable in real time. It uses a finite scalar quantization approach combined with flow matching to support streaming synthesis at extremely low latency, while reaching human-comparable naturalness that outperforms many commercial systems in subjective tests. Beyond quality, it offers zero-shot voice cloning from about 3 seconds of audio, cross-lingual synthesis, and fine-grained emotion control. Covering 8 languages with a 1,000-character cap, it's a strong fit for voice assistants, streaming TTS, and other real-time applications.
Parim: Real-time applications, streaming TTS, voice assistants
Kõigi sirvimine CosyVoice 2 hääledPõgusalt
- Arendaja
- Alibaba (Tongyi Lab)
- Litsents
- Apache 2.0
- Määramistasand
- standard
- Kiirus
- medium
- Hääle kloonimine
- Jah
- Keeled
- English, Chinese, Japanese, Korean, French, German, Italian, Spanish
- Maks. märgid
- 1000