CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Za natančen nadzor zavijte svoje besedilo v oznake SSML:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Oznake izbranega modela razume – kliknite, da spustite enega v svoje besedilo, kjer se zgodi:
Ta model bere navadno besedilo, zato se v vrstici ignorirajo. Za čustva, ki temeljijo na tag, preklopite na izražen model, kot je Orfeus ali Bark.
Opredelitev posebnih izgovorov (beseda = izgovor):
O projektu 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.
Najboljše za: Multilingual production TTS, real-time applications, voice cloning
Brskaj vse CosyVoice3 glasoviNa pogled
- Razvijalec
- Alibaba (FunAudioLLM)
- Licenca
- Apache 2.0
- Stopnja
- standard
- Hitrost
- fast
- kloniranje glasu
- Da, da.
- Jeziki
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Največ znakov
- 5000