The Web Desk – In an innovation in generative AI for voice, Meta has created Voicebox, a cutting-edge AI model that can produce speech in ways that it wasn’t particularly trained to, such editing, sampling, and stylizing.

Voicebox can create high-quality audio clips and edit pre-recorded audio while maintaining the style and content of the original recording. For example, it can take out automobile horns or dog barking. The model can speak in six different languages and is bilingual as well.

Future virtual assistants and non-player characters in the metaverse could have real-sounding voices thanks to versatile generative AI models like Voicebox.

Related posts:

Default ThumbnailAfter State Media reports, Alibaba’s stock drops and then recovers Default ThumbnailIn its Virtual Land Sale, the Bored Ape NFT firm raises around $285 million in cryptocurrency Default ThumbnailXiaomi alleges the Indian agency of threatening ‘physical violence’ throughout the investigation Default ThumbnailAdmins of WhatsApp groups have been given greater privileges Default ThumbnailNvidia will pay a $5.5 million fine for ‘inadequate cryptomining disclosures’ Default ThumbnailDue to internet disruptions, Pakistan’s telecom sector loses 2.49 billion rupees Default ThumbnailApple has purchased nearly the entire supply of TSMC’s 3nm chips. Default ThumbnailA potential partnership between Tesla and Samsung may dominate the electric car industry. Default ThumbnailOpenAI Introduces the ChatGPT App for Smartphones Default ThumbnailSunwalk Group of China has begun work on a project to lay 16,000 km of fibre optic cable in Pakistan.