CosyVoice 2

CosyVoice 2 ټي ټي اېس

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

ننوتل د 5,000 لوښه حد

د دقیق کنټرول لپاره په SSML نښانونو خپل متن واچوئ:

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

توري د ټاکل شوي ماډل پوهیږي - کلیک وکړئ چې ستاسو په متن کې یو راښکته کړئ چیرې چې دا پیښیږي:

دا ماډل لوستل ساده متن، نو inline نښانونه په پام کې نه نيول کيږي. د نښان پر بنسټ احساس، د يو څرګند ماډل لکه Orpheus يا Bark بدل.

دوديزه لوستنه پېژندل (ويې = لوستنه):

-12 +12
0.5x 2.0x
د پيپر، VITS، MeloTTS سره وړيا
ستاسو توليد شوي غږيز به دلته ښکاره شي. يو ماډل وټاکئ، ليکنه وليکﺉ، او توليد کېکاږﺉ.
غږ په برياليتوب سره جوړ شو
0:00
غږيز رالېښنې .srt ډاونلوډ تړنه په 24h کې پای ته رسیږي
وړیا طبقه: شخصي کارولو. د $ 5 / mo څخه سوداګریز جواز
TTS.ai مینه؟ خپل ملګرو ته ووایاست!

په اړه 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.

غوره د: Real-time applications, streaming TTS, voice assistants

ټول لټول CosyVoice 2 غږونه

په يوه کتنه کې

جوړوونکی
Alibaba (Tongyi Lab)
منښتليک
Apache 2.0
:د پاڼې نوم
standard
چټکتيا
medium
غږ کلونول
هو
ژبې
English, Chinese, Japanese, Korean, French, German, Italian, Spanish
ټولوجګه لوښه
1000

CosyVoice 2 غږونه

Chinese Female

Chinese
تلواله Female

Chinese Male

Chinese
تلواله Male

English Female

English
تلواله Female

English Male

English
تلواله Male

French Female

French
تلواله Female

German Female

German
تلواله Female

Italian Female

Italian
تلواله Female

Japanese Female

Japanese
تلواله Female

Korean Female

Korean
تلواله Female

Spanish Female

Spanish
تلواله Female

CosyVoice 2 د پوښتنو ځوابول

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.
← ټول غږونه