CosyVoice 2 TTS-värden
Alibaba Tongyi Lab's streaming TTS reaching human-parity naturalness with near-zero latency and zero-shot cloning.
Radera din text i SSML-taggar för exakt kontroll:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Taggar den valda modellen förstår — klicka för att släppa en i din text där det händer:
Den här modellen läser vanlig text, så inline-taggar ignoreras. För taggbaserade känslor, byt till en uttrycksfull modell som Orpheus eller Bark.
Definiera egna uttal (ord = uttal):
Om jag inte kan CosyVoice 2
CosyVoice 2, from Alibaba's Tongyi Lab, was designed to make high-quality speech viable in real time. It uses a finite scalar quantization approach combined with flow matching to support streaming synthesis at extremely low latency, while reaching human-comparable naturalness that outperforms many commercial systems in subjective tests. Beyond quality, it offers zero-shot voice cloning from about 3 seconds of audio, cross-lingual synthesis, and fine-grained emotion control. Covering 8 languages with a 1,000-character cap, it's a strong fit for voice assistants, streaming TTS, and other real-time applications.
Bäst för: Real-time applications, streaming TTS, voice assistants
Bläddra alla CosyVoice 2 rösterMed en blick
- Utvecklare
- Alibaba (Tongyi Lab)
- Licens
- Apache 2.0
- Nivå
- standard
- Varvtal
- medium
- Röstkloning
- Ja, det är jag.
- Språk
- English, Chinese, Japanese, Korean, French, German, Italian, Spanish
- Max tecken
- 1000