CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Ukufaka umbhalo wakho kumathegi we-SSML ukulawula okucacile:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Amathegi amamodeli akhethiwe aqonda - chofoza ukuwasusa kusihloko sakho lapho kwenzeka khona:
Le modeli ifunda umbhalo ojwayelekile, ngakho amathegi e-inline akhohlwa. Ukwenza umbono osekelwe kumathegi, shintsha kwimodeli ebonisa umbono njenge-Orpheus noma i-Bark.
Chaza ukuchaza okujwayelekile (igama = ukuchaza):
Ngo 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.
Okungcono kakhulu: Multilingual production TTS, real-time applications, voice cloning
Khangela konke CosyVoice3 izizwiNgombono ocacile
- Umthuthukisi
- Alibaba (FunAudioLLM)
- Ilayisense
- Apache 2.0
- I-Tiger
- standard
- Isivinini
- fast
- Ukuklona umsindo
- Yebo
- Izilimi
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Amaphawu aphezulu
- 5000