CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Oorvloei jou teks in SSML etiket vir presiese beheer:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Merk die gekose model verstaan ooit die woord ooit om een in jou teks te laat val waar dit gebeur:
Hierdie model lees gewone teks, so inlyn etiket word geignoreer. Vir etiket-gebaseerde emosie, wissel na 'n uitdrukkingende model soos Orpheus of Bark.
Definieer pasmaak uitspraak (woord = uitspraak):
Aangaande 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.
Beste vir: Multilingual production TTS, real-time applications, voice cloning
Blaai deur almal CosyVoice3 stemmeMet'n blik
- Ontwikkelingvloeistof is minDeveloper
- Alibaba (FunAudioLLM)
- Lisensie
- Apache 2.0
- Tier
- standard
- Spoed
- fast
- Stem kloning
- Ja
- Tale
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Voeg- agteraan- by Taal
- 5000