OpenAI, the creator of ChatGPT, has released ‘speech Engine’, a speech copying tool, just months after debuting its video generator Sora.
The corporation intend to keep it under wraps for fear of nefarious use and an increase in incidents of copying and fraudulent content online.
Voice Engine generates natural-sounding speech from text and a 15-second audio clip, closely like the original speaker.
OpenAI stated in a blog post that partners testing Voice Engine have agreed to standards that need clear and informed agreement from everyone whose voice is copied using the tool. The AI-generated voices will be readily identified for audiences.
This will be provided to non-readers and children, to generate natural-sounding and emotive voices representing a wider range of speakers than possible while learning and at educational institutions.
This is to enable creators and businesses which use media like videos and podcasts to reach more people around the world in their own voices.
Voice Engine will preserve the native accent of the original speaker: for example, generating English with an audio sample from a French speaker would produce speech with a French accent.
“We are engaging with US and international partners from across government, media, entertainment, education, civil society and beyond to ensure we are incorporating their feedback as we build,” it added.