CosyVoice 2 TTS
Alibaba Tongyi Lab's streaming TTS reaching human-parity naturalness with near-zero latency and zero-shot cloning.
Whāriki i tōna kupu i roto i ngā tohu SSML mō te whakahaere tika:
<speak><prosody rate="slow">Slow speech</prosody></speak>
E mōhio ana ngā tohu ki te tauira i kōwhiria - ka kōwhiria kia whakawātea tētahi ki roto i tōna kupu i reira ka puta ai:
Ka pānui tēnei tauira i te kupu noa, nā reira ka whakakāhoretia ngā tohu ā-waitara. Mō te āhua o te tohu-taihi, ka huri ki tētahi tauira whakamārama pēnei i a Orpheus, Bark rānei.
Ka tautuhia ngā tohutohu ā-ringa (wāhi = tohutohu):
Mo 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.
Pai mo: Real-time applications, streaming TTS, voice assistants
Ka tirohia katoa CosyVoice 2 ngā oroI te tirohanga
- Ka whakawhanakehia
- Alibaba (Tongyi Lab)
- Ka taea te whakawātea
- Apache 2.0
- Karaka
- standard
- Āhuatanga
- medium
- Whakakōrero reo
- He
- reo
- English, Chinese, Japanese, Korean, French, German, Italian, Spanish
- Kāri nui rawa
- 1000