audio-sync

Pika introduces H3 Flex, a post-trained MiniMax H3 text-to-video model that generates in six steps (vs. 50), supports up to 12 reference files, exports five audio stems, finishes at up to 4K, and is released with open weights — ranking #1 among open-weights models on DesignArena's leaderboard.

Pika 发布开源权重的视频生成模型 Pika H3 Flex，支持六步采样生成带同步音频的视频，最多可输入 12 个参考，本地推理支持 480p/768p，通过 Pika API 可扩展至 4K 与音频分轨。