Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
OpenAI has developed Voice Engine, a new artificial intelligence model capable of generating speech that closely resembles a source speaker's voice from just a 15-second audio sample. This text-to-speech AI tool, which has been in development since late 2022, aims to create emotive and realistic voices. Early evaluations and pilot programs have shown promising results, demonstrating the model's ability to produce convincing human-like speech. However, OpenAI has expressed concerns over the potential risks associated with the technology, particularly the possibility of its use in creating deepfakes, leading the organization to hold back on a wide release due to deepfake risks.
Voice Engine is a new text-to-speech AI model for creating synthetic voices. OpenAI has said a wide release would be too risky. https://t.co/ILL6t3NjnC
OpenAI has introduced Voice Engine, an AI tool that can emotionally and realistically read texts in the voice of any person based on a 15-second speech sample. The tool has been developed for about two years, but it is not yet publicly available, as it can potentially be used to… https://t.co/LAFAWMiYe4
OpenAI is sharing early results from a test for a feature that can read words aloud in a convincing human voice — highlighting a new frontier for artificial intelligence and raising the specter of deepfake risks. https://t.co/fRKGB8fjdQ
