CosyVoice 2

CosyVoice 2 TTS

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

Inscríbete para el límite de 5.000 caracteres

Envuelva su texto en etiquetas SSML para un control preciso:

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

Etiquetas el modelo seleccionado entiende — haga clic para soltar uno en su texto donde sucede:

Este modelo lee texto plano, por lo que las etiquetas en línea son ignoradas. Para la emoción basada en etiquetas, cambie a un modelo expresivo como Orfeo o Bark.

Definir pronunciaciones personalizadas (palabra = pronunciación):

-12 +12
0.5x 2.0x
Libre con Piper, VITS, MeloTTS
Su audio generado aparecerá aquí. Elija un modelo, introduzca texto y haga clic en Generar.
Audio generado con éxito
0:00
Descargar audio Descargar.srt Enlace expira en 24h
Nivel libre: uso personal. Licencia comercial desde $5/mes
Haz de esto tu propia voz Clonar una voz en 30 segundos
¿Te gusta TTS.ai? ¡Cuéntaselo a tus amigos!

Acerca de 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.

Lo mejor para: Real-time applications, streaming TTS, voice assistants

Examinar todo CosyVoice 2 voces

De un vistazo

Desarrollador
Alibaba (Tongyi Lab)
Licencia
Apache 2.0
Nivel
standard
Velocidad
medium
Clonación de voz
Idiomas
English, Chinese, Japanese, Korean, French, German, Italian, Spanish
Máx. caracteres
1000

CosyVoice 2 voces

Chinese Female

Chinese
Estándar Female

Chinese Male

Chinese
Estándar Male

English Female

English
Estándar Female

English Male

English
Estándar Male

French Female

French
Estándar Female

German Female

German
Estándar Female

Italian Female

Italian
Estándar Female

Japanese Female

Japanese
Estándar Female

Korean Female

Korean
Estándar Female

Spanish Female

Spanish
Estándar Female

CosyVoice 2 TTS — Preguntas más frecuentes

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.
← Todas las voces