自动生成字幕只是工作流的第一步。Adobe Speech to Text v2.1.6深刻理解创作者的个性化需求，将自动化的便捷性与完整的创造性控制权完美结合。
The latest version of Adobe Speech to Text, v2.1.6, comes with a range of exciting features that enhance the editing experience. Some of the key features include:
While v2.1.6 does not auto-translate, it now supports . You can generate an English transcript, then export it as an .SRT and import it into Adobe's new Translate Captions service (separate cloud credit). The tight integration means you can have Spanish hard subs in 10 minutes.
Adobe’s roadmap for late 2025 suggests . The current v2.1.6 is a bridge technology. By version 3.0 (expected Q4 2025), we anticipate: Adobe Speech to Text v2.1.6 for Premiere Pro 2025
The software detects and labels different speakers (e.g., "Speaker 1," "Speaker 2"), allowing for global name changes across the entire transcript. Multi-Language Support: It supports over 27 languages
: Choose to transcribe a specific track or the entire mix.
While v2.1.6 brings stability, it retains the powerhouse features that make Premiere Pro's transcription industry-leading: Text-Based Editing: The tight integration means you can have Spanish
在文本面板（Text Panel）中点击“转录”选项卡图标，打开“生成静态转录”对话框，设置以下选项：选择视频中对话的语言并下载必要的语言包（若尚未安装）；设定是否分离说话人标签；指定音频分析源（可仅转录标记为“对话”的音频剪辑，也可从特定音频轨道进行转录）；以及可选项“入点到出点转录”以精准控制转录范围。
Set your parameters for Maximum Characters per Line and Minimum Duration in Seconds.
Select from standard presets like Subtitle or CEA-708 . By version 3
: Includes support for over 18 languages, including English, Spanish, French, German, Japanese, and more.
Are you encountering any specific during the installation?