Context—
VibeVoice 1.5B is Microsoft's open-weights framework for expressive, long-form, multi-speaker conversational audio such as podcasts. It uses continuous acoustic and semantic speech tokenizers at a 7.5 Hz frame rate and a next-token diffusion design, in which a language model follows the text and dialogue flow and a diffusion head generates the acoustic detail. It synthesizes speech up to 90 minutes long with up to 4 distinct speakers.