CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Itzulbiratu zure testua SSML etiketetan kontrol zehatzagoa lortzeko:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Hautatutako modeloak ulertzen dituen etiketak — egin klik testuan jartzeko:
Eredu honek testu arrunta irakurtzen du, beraz, lerro-barneko etiketei ez zaie jaramonik egiten. Etiketetan oinarritutako emozioetarako, aldatu Orpheus edo Bark bezalako adierazpen-modelo batera.
Definitu ahoskera pertsonalizatuak (hitza = ahoskera):
Honi buruz 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.
Honako hauentzako onena: Multilingual production TTS, real-time applications, voice cloning
Arakatu dena CosyVoice3 ahotsakBegirada batean
- Garatzailea
- Alibaba (FunAudioLLM)
- Lizentzia
- Apache 2.0
- Tier
- standard
- Abiadura
- fast
- Ahots klonaketa
- Bai
- Hizkuntzak
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Gehienezko karaktereak
- 5000