Skip to content
SN / AI RESEARCH TERMINAL
Online

Public index / static delivery / reviewed releases only

Types / R03

Model / weights

Released models, checkpoints, and weight announcements.

CAT / STATUS

1 reviewed record

Published
  1. 01
    Dia 1.6B →

    Dia is a 1.6-billion-parameter model for generating multi-speaker dialogue from tagged transcripts, with optional audio conditioning and nonverbal cues.

    model or weights

Return to types