A 15-second voice clip can synthesize someone's voice. OpenAI has released a small-scale open Voice Engine model.

OpenAI The company recently issued an announcement to open Voice Engine Access rights,The model can create synthetic speech based on a 15-second clip of someone's speech.

OpenAI stated in a press release: "By opening up small-scale deployments, we can help us advance product implementation based on existing methods and safeguards, and think about how to use Voice Engine in various industries during the process of continuous trial and exploration."

OpenAI said it has now opened access to companies including education technology company Age of Learning, visual storytelling platform HeyGen, frontline health software maker Dimagi, AI communications app developer Livox and health system Lifespan.

In these samples released by OpenAI, you can hear Age of Learning using the technology to generate canned voice-over content, as well as reading “real-time, personalized responses” written by GPT-4 to students.

statement:The content of the source of public various media platforms, if the inclusion of the content violates your rights and interests, please contact the mailbox, this site will be the first time to deal with.
Information

Huawei Cloud signs contract with Guizhou, aiming to become "the world's largest and leading intelligent computing center"

2024-3-31 8:26:41

Information

To prevent chatbots from "spreading rumors", Google Deepmind and Stanford University researchers launched AI fact-checking tools

2024-4-1 9:27:45

Search