CosyVoice 2

CosyVoice 2 TTS

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

Tia sahihi kwa kiwango cha tabia 5,000

Pakua maandishi yako katika tovuti ya SSML kwa ajili ya udhibiti sahihi:

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

Tag anaelewa mfano unaochaguliwa na unajibu ujumbe huu:

Mfano huu unasomeka maandishi rahisi, kwa hiyo alama za vidole hupuuzwa. Kwa hisia za ndani za watu, geukia kigezo kinachoonesha hisia kama Orfeus au Bark.

Matamshi ya desturi (neno = matamshi):

-12 +12
0.5x 2.0x
Nikiwa huru na Piper, VITS, MelloTTTS
Unaweza kuchagua mfano, maandishi, na kidofo kinachoitwa Genete.
Edio Iliyorekebishwa kwa Mafanikio
0:00
Paketi ya Audio Paketisha.srt Kiungo kinakufa mnamo 24
Safu huru: matumizi ya kibinafsi. Hati ya biashara kutoka dola 5/mo
Fanya hii sauti yako mwenyewe Chokoa sauti kwa sekunde 30
Waeleze rafiki zako kuhusu mapenzi ya TTS.ai?

Habari 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.

Bora kwa: Real-time applications, streaming TTS, voice assistants

Ng'ombe wote CosyVoice 2 sauti

Kutupia jicho

Mbuni
Alibaba (Tongyi Lab)
Lenzi
Apache 2.0
Tier
standard
Mwendo
medium
Kufanyizwa kwa Sauti
Ndiyo
Lugha
English, Chinese, Japanese, Korean, French, German, Italian, Spanish
Wahusika wa Max
1000

CosyVoice 2 sauti

Chinese Female

Chinese
Kiwango Female

Chinese Male

Chinese
Kiwango Male

English Female

English
Kiwango Female

English Male

English
Kiwango Male

French Female

French
Kiwango Female

German Female

German
Kiwango Female

Italian Female

Italian
Kiwango Female

Japanese Female

Japanese
Kiwango Female

Korean Female

Korean
Kiwango Female

Spanish Female

Spanish
Kiwango Female

CosyVoice 2 TTS ngumuSTEGAQ

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.
← Sauti zote