From YM Cinema: 2024-04-08 05:31:33

OpenAI has developed ‘Voice Engine’, allowing users to upload a 15-second voice sample to create a synthetic copy. No public release date yet to address potential misuse and verify safety.

OpenAI’s Voice Engine uses a text input and 15-second audio sample to generate realistic speech. It is used for translation in videos and podcasts to reach wider audiences authentically. Safety measures are in place to prevent misuse, especially in sensitive areas like elections.

OpenAI acknowledges the risks of using Voice Engine to manipulate public opinion. Partnering with various sectors, they have strict usage policies to prevent impersonation without consent. Safety measures include voice authentication and prevention of voices too similar to prominent figures.

OpenAI’s Voice Engine simplifies voiceover recording for content creators by mimicking voices using a 15-second sample. However, concerns arise over potential misuse and safety, delaying its public release for further testing and refinement.



Read more at YM Cinema: OpenAI Presents ‘Voice Engine’: Generate Natural Sounding Based on Your Voice