CosyVoice 2

CosyVoice 2 Mga TNT

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

Mag-sign up para sa 5,000 character na limitasyon

I-wrap ang iyong teksto sa SSML tags para sa tumpak na kontrol:

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

Tags ang napili modelo nauunawaan — i-click upang ihulog ang isa sa iyong teksto kung saan ito ay nangyayari:

Ang modelong ito ay nagbabasa ng karaniwang teksto, kaya inline tags ay hindi pinapansin. Para sa tag-based na damdamin, lumipat sa isang makahulugang modelo tulad ng Orpheus o Bark.

Tukuyin ang mga pasadyang mga panlapi (word = panlapi):

-12 +12
0.5x 2.0x
Libreng may Piper, VITS, MeloTTS
Ang iyong ginawang audio ay lilitaw dito. Pumili ng modelo, ipasok ang teksto, at i-click ang Bumuo.
Audio nabuo Matagumpay
0:00
I-download ang Audio I-download ang.srt Link expires sa 24h
Free tier: personal na paggamit. Komersyal na lisensya mula sa $5/buwan
I-love TTS.ai? Ibahagi sa iyong mga kaibigan!

Tungkol sa 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.

Pinakamahusay para sa: Real-time applications, streaming TTS, voice assistants

Mag-browse ng lahat CosyVoice 2 Mga boses

Sa isang sulyap

Developer
Alibaba (Tongyi Lab)
Lisensya
Apache 2.0
Mga hayop
standard
Bilis
medium
Pag-clone ng boses
Oo
Wika
English, Chinese, Japanese, Korean, French, German, Italian, Spanish
Max character
1000

CosyVoice 2 Mga boses

Chinese Female

Chinese
Pangkalahatang Female

Chinese Male

Chinese
Pangkalahatang Male

English Female

English
Pangkalahatang Female

English Male

English
Pangkalahatang Male

French Female

French
Pangkalahatang Female

German Female

German
Pangkalahatang Female

Italian Female

Italian
Pangkalahatang Female

Japanese Female

Japanese
Pangkalahatang Female

Korean Female

Korean
Pangkalahatang Female

Spanish Female

Spanish
Pangkalahatang Female

CosyVoice 2 Mga katanungan at sagot

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.
← Lahat ng mga boses