@patrickcmiller@infosec.exchange
2026-09-27 07:42 UTC
Google’s new Gemini TTS models can clone a voice from 30 seconds of audio https://thenextweb.com/news/gemini-tts-3-8-flash-voice-design-cloning
Replies (1)
-
@Cali@infosec.exchange 2026-09-27 07:44
@patrickcmiller@infosec.exchange “Flash TTS can also recreate a voice from a 30-second sample after a consent check”…. Ah i see the latest high quality deepfake engine has dropped