From Indian Express: 2024-03-31 01:16:08

OpenAI introduces ‘Voice Generation’ AI model, replicating any voice with a 15-second sample. Available for limited users, including governments, media, and education sectors.

Text-to-voice AI model by OpenAI has real-world applications like reading assistance, content translation, and helping non-verbal individuals, patients recover their voices.

Voice Engine model by OpenAI can create emotive and realistic voices with just a 15-second audio sample. Available via text-to-speech API and ChatGPT Voice for select users.

OpenAI emphasizes cautious release of Voice Generation model, aiming to prevent misuse and educate the public on AI capabilities. Samples of generated voices already shared by the company.

Before public release, OpenAI is focusing on protecting individual voices in AI, educating the public on AI limitations, and helping users distinguish between real and AI-generated voices.



Read more at Indian Express: OpenAI previews ‘Voice Generation’ AI model that can clone any voice with a 15-second audio sample | Technology News