CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Incluír o texto en etiquetas SSML para un control preciso:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Etiquetas que o modelo escollido entende - prema para deixar unha no texto onde ocorre:
Este modelo le texto simple, polo que se ignoran as etiquetas inline. Para emocións baseadas en etiquetas, cambie a un modelo expresivo como Orpheus ou Bark.
Definir pronunciacións personalizadas (palabra = pronunciación):
Acerca de CosyVoice3
CosyVoice3 is the newest generation from Alibaba's FunAudioLLM team and a clear step up from CosyVoice 2. It introduces bi-streaming inference with roughly 150ms latency and instruction-based control, letting you steer emotion, speed, and volume through prompts. Speaker similarity for zero-shot voice cloning is improved, and coverage spans 9 languages plus 18 Chinese dialects. An RL-tuned variant pushes prosody to a state-of-the-art level. With a 5,000-character ceiling, fast generation, and strong cloning, it's geared toward multilingual production TTS and real-time applications.
Mellor para: Multilingual production TTS, real-time applications, voice cloning
Examinar todo CosyVoice3 vocesDe un vistazo
- Desenvolvente
- Alibaba (FunAudioLLM)
- Licenza
- Apache 2.0
- Tier
- standard
- Velocidade
- fast
- Clonaxe de voz
- Si
- Linguas
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Caracteres máximos
- 5000