Page 9 - Voice Engine News Today

Bringing Taiwan to the World and the World to Taiwan

OpenAI's new powerful model can create a realistic clone of your voice based on just 15 seconds of your speech. However, the company hesitates to release the tool amid concerns about its misuse.

OpenAI announces Voice Engine, a voice cloning technology, that can mimic speakers with a 15 second audio sample. Pros and Cons are highlighted.

A new language model unveiled by ChatGPT creator OpenAI can clone a person's voice using just seconds worth of audio, the company revealed as it shared preliminary insights from studying the technology's capabilities.

The ChatGPT parent company is testing dramatically improved text-to-speech technology with select developers. Experts warn that realistic voice generation raises serious safety questions.

The start-up is sharing the technology, Voice Engine, with a small group of early testers as it tries to understand the potential dangers.

OpenAI on Friday revealed a voice-cloning tool it plans to keep tightly controlled until safeguards are in place to thwart audio fakes meant to dupe listeners.A model called "Voice Engine" can essentially duplicate someone's speech based on a 15-second audio sample, according to an OpenAI blog post sharing results of a small-scale test of the tool.

OpenAI's new tool in pilot, Custom Voices, allows developers to create a clone of any voice with a 15-second sample.

Voice Engine can clone voices with 15 seconds of audio, but OpenAI is warning of potential harms.

The maker of ChatGPT said it would not release its new Voice Engine programme yet because of the dangers of misuse.