CosyVoice 2 ສຽງເປັນຂໍ້ຄວາມ
Alibaba Tongyi Lab's streaming TTS reaching human-parity naturalness with near-zero latency and zero-shot cloning.
ວາງຂໍ້ຄວາມຂອງທ່ານໄວ້ໃນແທັກ SSML ເພື່ອຄວບຄຸມຢ່າງລະອຽດ:
<speak><prosody rate="slow">Slow speech</prosody></speak>
ແທັກທີ່ຕົວແບບທີ່ໄດ້ເລືອກເຂົ້າໃຈ — ກົດເພື່ອປ່ອຍພວກມັນລົງໃນຂໍ້ຄວາມຂອງທ່ານບ່ອນທີ່ມັນເກີດຂຶ້ນ:
ແບບນີ້ອ່ານຂໍ້ຄວາມປົກກະຕິ, ສະນັ້ນແທັກໃນແຖບຈະບໍ່ຖືກລະບຸໄວ້. ສຳລັບຄວາມຮູ້ສຶກທີ່ອີງໃສ່ແທັກ, ປ່ຽນໄປຫາແບບທີ່ສະແດງອອກຄື Orpheus ຫຼື Bark.
ຕັ້ງຄ່າການອອກສຽງແບບສ່ວນຕົວ (ຄໍາ = ການອອກສຽງ):
ກ່ຽວກັບ 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.
ດີທີ່ສຸດ ສຳ ລັບ: Real-time applications, streaming TTS, voice assistants
ຄົ້ນຫາທັງໝົດ CosyVoice 2 ສຽງເບິ່ງຢ່າງໄວວາ
- ຜູ້ພັດທະນາ
- Alibaba (Tongyi Lab)
- ໃບອະນຸຍາດ
- Apache 2.0
- ສັດ
- standard
- ໄວ
- medium
- ການປິດສຽງ
- ແມ່ນ
- ພາສາ
- English, Chinese, Japanese, Korean, French, German, Italian, Spanish
- ຕົວອັກສອນສູງສຸດ
- 1000