News
Neutral
Tether Unveils On-Device AI Voice Recognition Model for Enhanced Privacy

Tether, the issuer of USDT, has unveiled a 254-million-parameter on-device AI voice recognition model called 'QVAC TranscribePsy,' capable of running directly on devices without cloud transmission. The model processes real-time audio conversion instantly on the device, maximizing data privacy protection by eliminating the need to send audio data to external servers. Tether reported that benchmark tests conducted across six major smartphones showed the model outperformed key competitor models in processing speed.
Korean Source
This article is an English localization of a Korean-language crypto news report. Original headline: 테더, 온디바이스 AI 음성인식 모델 공개..AI 확장