New research shows models can be directly edited to hide selected voices, even when users specifically ask for them.

ElevenLabs' 'most expressive' v3 model can speak with a huge range of emotions in more than 70 languages. Try it for yourself.

Microsoft introduces a voice conversion feature in Azure AI Speech, allowing users to transform recorded voices into ...

If OpenAI can break into the speech-to-text market in a major way, it could be quite profitable for the Microsoft-backed company. According to one report, the segment could be worth $5.4 billion ...

TikTok's text-to-speech voice isn't a robot — this woman claims it's her. Kat Callaghan, an Ontario-based radio host on the local station 91.5 FM "The Beat," revealed that she's the voice behind ...

Voice technology leader aiOla has raised $25 million in a Series A2 round, with United Airlines Ventures (UAV) joining as a ...

Whatever the case, Meta used the scraped text and speech to create the training dataset for SeamlessM4T, called SeamlessAlign. Researchers aligned 443,000 hours of speech with texts and created ...

My colleagues in the speech-to-text industry and I have challenged our teams to future-proof our technology by building resilient technologies that can withstand the growth and pivoting of our ...