News
Alibaba’s Marco-Voice pairs voice cloning with controllable emotion for more natural and expressive synthetic speech in ...
Microsoft’s VibeVoice is an open-source text-to-speech model for podcast-length, multi-speaker audio that captures the ...
Recently, Ping An Bank (000001) was granted an invention patent entitled "Method, Device, Storage Medium, and Electronic Equipment for Voice-to-Text Conversion" with application number CN202210691995.
New Benchmark C3T: A Breakthrough Tool for Evaluating Language Model Comprehension under Voice Input
With the widespread application of voice interfaces, artificial intelligence systems not only need to process spoken language ...
Join the event trusted by enterprise leaders for nearly two decades. VB Transform brings together the people building real enterprise AI strategy. Learn more A two-person startup by the name of Nari ...
Not so long ago, generative AI could only communicate with human users via text. Now it's increasingly being given the power of speech -- and this ability is improving by the day. On Thursday, AI ...
18don MSN
Microsoft’s new AI can turn plain text into a full podcast — and it’s freakishly good at it
Microsoft's road to total AI domination continues with an interesting looking open-source project called VibeVoice. This text-to-speech model can generate conversational audio with multiple speakers, ...
Last month I wrote about the ways in which search is changing, including the rise of voice search. Where search was once ...
GlobalData on MSN
Microsoft unveils MAI-Voice-1 and MAI-1 Preview models
MAI-Voice-1 aims to offer high-fidelity audio generation, while MAI-1 Preview enhances instruction-following via advanced GPU training.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results