AirCaption

AirCaption is a desktop application for generating captions and subtitles from audio and video files using AI. The tool runs OpenAI's Whisper model entirely offline on the user's computer, ensuring media and captions never leave the device. Users can generate captions in up to 67 languages, then review and edit the text and timing of captions before exporting them as SRT, VTT, TXT files, or directly to video. It also supports importing and editing existing SRT and VTT files. The application includes hotkeys for efficient editing and a queue feature for batch processing entire folders of media files. AirCaption is available for Mac (including Apple Silicon) and Windows.

Who It’s For

AirCaption is aimed at content creators and professionals who need accurate, private transcription and captioning. The website lists video editors, podcasters, language learners, legal professionals, marketers, researchers, event organizers, online course creators, and journalists as typical users.

Key Features

• Offline processing: No internet required; all computation happens locally.
• AI-powered transcription: Uses the latest OpenAI Whisper models.
• Multi-language support: Captions in up to 67 languages.
• Caption editing: Edit both text and timing with a built-in editor.
• Hotkeys: Keyboard shortcuts for faster editing workflows.
• Import/export: Import SRT and VTT files; export as SRT, VTT, TXT, or to video.
• Batch queue: Drag and drop folders for bulk transcription.