Skip to main content

OpenAI Previews 'Voice Engine' Audio Tool That Can Clone Human Voices With 15 Seconds of Audio | Technology News

OpenAI Previews 'Voice Engine' Audio Tool That Can Clone Human Voices With 15 Seconds of Audio OpenAI has previewed a new Voice Engine audio tool that is capable of cloning human voices with 15 seconds of audio. The new Voice Engine tool can create speech that sounds like individual people, complete with their specific cadence and intonations, according to the Sam Altman-led company.

Labels:

Comments

Post a Comment

Popular posts from this blog

OpenAI Said to Be Working on Weekly and Lifetime ChatGPT Subscription Plans | Technology News

OpenAI Said to Be Working on Weekly and Lifetime ChatGPT Subscription Plans OpenAI might be working on introducing more duration-based subscription plans. A tipster shared strings of code from the ChatGPT app and found mentions of a weekly and a lifetime subscription for the artificial intelligence (AI) chatbot. These tiers could be part of the ChatGPT Plus plan. Notably, the pricing details of the tiers are currently unclear.
Post a Comment
Read more

OpenAI Adds a Library Feature in ChatGPT to Let Users Find Their AI-Generated Images in One Place | Technology News

OpenAI Adds a Library Feature in ChatGPT to Let Users Find Their AI-Generated Images in One Place OpenAI is rolling out a new library feature in ChatGPT that will allow users to check all their images generated using artificial intelligence (AI) in a single view. Announced on Wednesday, the new feature is available to all registered ChatGPT users across all its interfaces. The San Francisco-based AI firm said that the library will act as a space to let users brows...
Post a Comment
Read more

Alibaba Releases Open-Source Wan 2.1 Suite of AI Video Generation Models, Claimed to Outperform OpenAI’s Sora | Technology News

Alibaba Releases Open-Source Wan 2.1 Suite of AI Video Generation Models, Claimed to Outperform OpenAI’s Sora Alibaba released a suite of artificial intelligence (AI) video generation models on Wednesday. Dubbed Wan 2.1, these are open-source models that can be used for both academic and commercial purposes. The Chinese e-commerce giant released the models in several parameter-based variants. Developed by the company’s Wan team, these models were first introduced in January...
Post a Comment
Read more