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

VibeVoice is a new open-source AI tool that can generate a full 90 minute audio podcast recording with multiple speakers from ...

Microsoft’s VibeVoice is an open-source text-to-speech model for podcast-length, multi-speaker audio that captures the authentic conversational “vibe.” ...

A key aspect of Microsoft's (MSFT) position as a prominent player in the fiercely competitive but fast-growing space of ...

The company has already invested billions into OpenAI but is now laying out its own five-year roadmap to ensure it remains ...

To date, Copilot has primarily depended on OpenAI's models. Microsoft has invested enormous amounts of money in OpenAI, and ...

VibeVoice can produce up to 90 minutes of synthetic dialogue with as many as four distinct speakers.

In its latest blog, Microsoft announced the launch of a new speech generation AI model, MAI-Voice-1, for Copilot and Podcasts features.

Microsoft and OpenAI released their respective AI models on the same day, signaling the start of a new round of competition in the artificial intelligence field. Microsoft introduced its ...

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.

Microsoft is developing and testing proprietary large language models, signaling a shift from its previous heavy reliance on OpenAI technology.