Premiere 推出 Generative Media 工具，可在时间线内直接生成视频和音频

Adobe正在彻底改造编辑人员在其Premiere专业视频编辑软件中与AI交互的方式。其新的生成媒体工具使得在项目时间线上生成视频、音效、音乐和声景变得更加容易，而无需离开项目时间线。生成器本身并非全新；最大的变化是您可以多么轻松地访问它们，而不会中断工作流程。

编辑人员现在无需在浏览器或外部应用程序之间跳转以寻找缺失的B-roll或音频元素，只需突出显示视频或音频轨道上的空白间隙，即可生成具有上下文感知、可完全编辑的片段，而无需离开项目。编辑人员可以直接在时间线上选择多个底层模型——包括Adobe Firefly、Google Veo、Runway、Luma和Kling——以最佳匹配其项目风格。

Premiere还获得了新的AI音频工具（测试版），能够分离重叠的说话者、自动在语音下调音乐音量，并独立调整对白和环境音。Adobe还将其AI助手引入After Effects（同样为测试版），让编辑人员可以使用自然语言命令重新组织项目、修复技术问题，并创建效果，而无需自己编写表达式。

Adobe is overhauling how editors interact with AI in its Premiere professional video editing software. Its new Generative Media tool makes it easier to generate video, sound effects, music, and soundscapes without ever leaving the project timeline. The generators themselves aren’t entirely new; the big change is how easily you can access them without breaking your workflow.

Instead of jumping between browsers or external apps to find missing B-roll or audio elements, editors can now highlight an empty gap on the video or audio track and generate context-aware, fully editable clips without leaving the project. Editors can choose from multiple underlying models directly in the timeline — including Adobe Firefly, Google Veo, Runway, Luma, and Kling — to best match their project’s style.

Premiere is also getting new AI audio tools (in beta) that can separate overlapping speakers, automatically duck music under speech, and independently adjust dialogue and ambience. And Adobe is bringing its AI Assistant to After Effects (also in beta) that lets editors use plain-language commands to reorganize projects, fix technical problems, and create effects without writing expressions themselves.