From United Press International: 2024-03-31 11:10:11

OpenAI introduces Voice Engine, an AI model that can clone a person’s voice with just a 15-second audio sample. The technology has shown promising results, including restoring voices for those with speech impairments. OpenAI emphasizes responsible deployment and is in discussion about wider use. Practical applications include reading assistance and educational content generation. Voice Engine can also support non-verbal communication and has been utilized by companies like HeyGen and Livox. Additionally, OpenAI recently unveiled Sora, a video-generating model that raises concerns about deepfake audio and video creation.



Read more at United Press International: OpenAI can clone voices with just 15 seconds of audio