CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Metini SSML taglarda dolap dogry kontrol üçin:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Saýlanan model aňlaýan taglar — birini metinde goýmak üçin basyň:
Bu model ýönekeý metin okaýar, şonuň üçin hatda taglar gözden düşürilýär. Tag-based emotions for, switch to an expression model like Orpheus or Bark.
Öz sözleriň terjimesini belli et (söz = terjime):
Habar 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.
Muňa iň gowy: Multilingual production TTS, real-time applications, voice cloning
Ehlini _Gözle CosyVoice3 seslerBir seretseň
- Developer
- Alibaba (FunAudioLLM)
- Lisenziýa
- Apache 2.0
- _Göçür
- standard
- Tizlik
- fast
- Ses klonlamak
- Eý
- Diller
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Maks. karakterler
- 5000