CosyVoice 2

CosyVoice 2 TTS

Alibaba Tongyi Lab's streaming TTS reaching human-parity naturalness with near-zero latency and zero-shot cloning.

_Gün tertibi 5000 karakter çäk

Metini SSML taglarda dolap dogry kontrol üçin:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Saýlanan model aňlaýan taglar — birini metinde goýmak üçin basyň:

Bu model ýönekeý metin okaýar, şonuň üçin hatda taglar gözden düşürilýär. Tag-based emotions for, switch to an expression model like Orpheus or Bark.

Öz sözleriň terjimesini belli et (söz = terjime):

-12 +12
0.5x 2.0x
Piper, VITS, MeloTTS bilen azat
Siziň döreden audioňyz şu ýerde görüner. Bir model saýlaň, metin girin we döred
Ses mübärek bejerildi
0:00
Ses ýükle .srt ýükle Baglanyşyk 24 sagadyň içinde gutarýar
TTS.ai-ni söýýäňmi? Dostlaryňa aýt!

Habar 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.

Muňa iň gowy: Real-time applications, streaming TTS, voice assistants

Ehlini _Gözle CosyVoice 2 sesler

Bir seretseň

Developer
Alibaba (Tongyi Lab)
Lisenziýa
Apache 2.0
_Göçür
standard
Tizlik
medium
Ses klonlamak
Diller
English, Chinese, Japanese, Korean, French, German, Italian, Spanish
Maks. karakterler
1000

CosyVoice 2 sesler

Chinese Female

Chinese
_Öň bellenen Female

Chinese Male

Chinese
_Öň bellenen Male

English Female

English
_Öň bellenen Female

English Male

English
_Öň bellenen Male

French Female

French
_Öň bellenen Female

German Female

German
_Öň bellenen Female

Italian Female

Italian
_Öň bellenen Female

Japanese Female

Japanese
_Öň bellenen Female

Korean Female

Korean
_Öň bellenen Female

Spanish Female

Spanish
_Öň bellenen Female

CosyVoice 2 TTS - Gynançly Soraglar

Yes. CosyVoice 2 uses finite scalar quantization for streaming synthesis at very low latency, which is what makes it suitable for voice assistants and real-time applications.

Yes. It offers zero-shot voice cloning from roughly 3 seconds of reference audio, plus cross-lingual synthesis and emotion control.

Yes. CosyVoice 2 is Apache 2.0 licensed. It supports 8 languages: English, Chinese, Japanese, Korean, French, German, Italian, and Spanish.
← Ehli Sesler