MiniMax (official)· @MiniMax_AI · X·· 12 天前AI 评分62
AI 导读
MiniMax 联合 FastVideo 和 nuvalab 推出了开源实时音视频生成模型 FastH3-Omni，支持单提示词生成带同步音频的视频。该模型具备首尾帧条件控制、音频输入与对话能力以及最多 3 张参考图输入，并在 Reactor API 提供独家预览至 2026 年 10 月 20 日。
正文 · 原文
FastH3-Omni on Reactor - video with synchronized audio, from a single prompt.
Your daydreams have a sound department now.
Introducing FastH3-Omni. The fastest and highest-quality open-source version of realtime H3 by @MiniMax_AI, post-trained by FastVideo @haoailab with @nuvalab. Exclusive preview on the Reactor API until 10.20.2026. • First and last frame conditioning • Audio input + strong dialogue • Up to 3 reference images • Frontier-level performance在 X 查看被引用的帖子
来源：MiniMax (official) · x.com