Tags: synthetic speech

Google introduced Gemini 3.1 Flash Live, a real‑time voice model designed to sound more like a person. In Scale AI’s Audio MultiChallenge the model scored 36.1 percent, trailing non‑conversational audio models that exceed 50 percent. The new system embeds SynthID watermarks that are invisible to listeners but detectable for verification. Early partners—including Home Depot and Verizon—reported positive results. Developers can access the model via AI Studio, the Gemini API, and Gemini Enterprise for Customer Experience, with the technology appearing in Gemini Live and Search Live features. Read more

Researchers from Tianjin University and the Chinese University of Hong Kong found that while listeners often fail to consciously distinguish real human speech from synthetic AI voices, their brains begin to tag subtle acoustic differences after brief exposure. Using EEG caps, the study revealed early neural responses that separate real and AI speech within milliseconds, highlighting a gap between unconscious perception and conscious decision‑making. The findings suggest the auditory system is already adapting to AI‑generated voices, offering hope for future tools that could help people translate these neural cues into reliable detection of deepfake audio. Read more