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

Microsoft's road to total AI domination continues with an interesting looking open-source project called VibeVoice. This text ...

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

VALL-E 2 is a text-to-speech (TTS) generator that can reproduce the voice of a human speaker using just a few seconds of audio. Microsoft researchers said VALL-E 2 was capable of generating ...