"VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as ...

Microsoft announced this week that it wrapped up the development of VALL-E 2, the second iteration of its VALL-E artificial intelligence speech generator. According to the researchers behind the ...

Microsoft created a text-to-speech AI generation model that was so good at replicating human voices the company deemed it too unsafe to bring to market.