Whisper Mate supports batch transcription of audio or video files into text using the Whisper AI model. With the built-in subtitle editor, you can preview transcription results segment by segment.

All transcription operations are processed locally, so your privacy is secure.

Features:

• Translate audio or video files
• Capture and translate audio from Zoom, Skype, Teams, and other apps (this feature requires macOS 13.0 or later and Screen Recording permission)
• Translate subtitles using the free DeepL API
• Built-in subtitle editor for correcting translated content
• Export to SRT, VTT, CSV, JSON, and SEGMENT formats
• Set a speaker for each subtitle
• Most operations support batch selection and invocation, such as batch task execution, batch translation of subtitle lines, and batch speaker assignment
• Drag and drop files to start transcription
• Search transcription content by entering text
• The editor can synchronize the playback range to preview audio or video files
• Export the media segment corresponding to selected subtitles as a new media file
• Export videos with hardcoded subtitles; you can record the original video and customize subtitle styles
• View subtitles directly in the video preview (subtitle styles can be customized in the settings panel)
• Record audio from the microphone and perform real-time transcription (requires macOS 13 or later)
• Subtitle merge function that can merge a specified segment range and subtitles into one line
• Audio recorded by the app is automatically saved as a file and can be converted into a new transcription project
• Copy subtitle lines and modify their content or time range to finely adjust the entire subtitle
• Adjust the playback speed of media files
• Paste copied files into the processing queue using ⌘+V
• Show CPU usage percentage during whisper processing
• Archive projects via the context menu (keep the working project list tidy)
• Support Google Translate in subtitle translation management
• Preview media files and subtitle positions in full screen
• Open media files using the “Open With” function in Finder
• Support multilingual conversion
• Customize frequently used conversion or translation languages
• Added a new voice separation method to improve speaker separation
• Integrated Large Language Model (LLM) features into the new inspector panel and simplified configuration options
• LLM now supports translating an entire SRT subtitle file or returning a revised SRT version that can be directly replaced in the subtitle editor
• Video export now supports exporting clips as GIF animations
• Optimized the subtitle editor layout
• Added quick subtitle text editing in the bottom tab of the right inspector
• GPT-based translation and LLM features are now compatible with Gemini, DeepSeek, and OpenRouter API
• Added a feature to batch extract video thumbnails at subtitle start timestamps; thumbnails are displayed in the subtitle editor
• Added keyframe detection for scene changes, with markers displayed on the waveform editor