June 25th.NetEaseThere was a announcement yesterday to launch "The Son 4.0."TTS Voice synthesis engine Confucius 4-TTS. Officially, it's the first in the industry to support 14 languages with no accent and no reference to textOpen SourceModel.
Confucius 4-TTS supports voice cloning of zero samples. 3 seconds of audio material provided by users, without reference to text and prior training, the model completes sound cloning; official nameClone SoundSIMILAR TO THE ORIGINAL ACOUSTIC IS MORE THAN 85% AND THE CLONING MISSION IS AS ACCURATE AS 97%。
THE MODEL SUPPORTS 14 LANGUAGES SUCH AS CHINESE, ENGLISH, SPANISH, FRENCH, GERMAN, KOREAN, THAI AND VIETNAMESE. OFFICIALLY, ITS FOCUS IS ON TRANSLINGUAL PRONUNCIATION: AFTER UPLOADING THE CHINESE AUDIO, AI CAN GENERATE FOREIGN LANGUAGES SUCH AS JAPANESE, ENGLISH, ETC。
GitHub: gethub.com/netease-youudao/Confucus4-TTS