Tag

Voicebox

All articles tagged with #voicebox

legaltech2 years ago

Amazon Hit with $46.7 Million Verdict in Voice-Assistant Patent Case

Amazon has been ordered by a Delaware federal court to pay $46.7 million for infringing on four patents owned by VB Assets, previously known as VoiceBox Technologies, with its Echo smart speakers and Alexa virtual assistant. The lawsuit claimed that VoiceBox had developed a similar prototype to Echo and Alexa before Amazon's products were announced. The judgment comes at a challenging time for Alexa, as it faces uncertainty and attempts to increase revenue. Amazon has the option to appeal the judgment, while VoiceBox can seek reimbursement for related costs.

ai2 years ago

Voicebox AI: The Ultimate Text-to-Speech Solution

Meta has unveiled Voicebox, its generative text-to-speech model that promises to do for the spoken word what ChatGPT and Dall-E, respectfully, did for text and image generation. The system was trained on more than 50,000 hours of unfiltered audio and can generate more conversational sounding speech, regardless of the languages spoken by each party. Voicebox is reportedly capable of actively editing audio clips, eliminating noise from the speech and even replacing misspoken words. Meta's AI reportedly outperformed the current state of the art both in intelligibility and "audio similarity" while operating as much as 20 times faster than today's best TTS systems. However, neither the Voicebox app nor its source code is being released to the public at this time.

ai2 years ago

Meta's Voicebox AI: Revolutionizing Speech Generation.

Meta has developed Voicebox, a versatile AI model that can perform speech generation tasks like editing, sampling, and stylizing that it wasn't specifically trained to do through in-context learning. The model can produce high-quality audio clips, edit pre-recorded audio, and is multilingual, capable of producing speech in six languages. Voicebox's versatility enables a variety of tasks, including in-context text-to-speech synthesis, speech editing and noise reduction, cross-lingual style transfer, and diverse speech sampling.