The latest update to MacWhisper, a popular AI-powered transcription application for Mac, brings significant design improvements and new features that enhance its usability and functionality.
Major design overhaul: MacWhisper 11 introduces a completely redesigned interface centered around a new collapsible sidebar that provides quick access to essential features and settings.
- The new sidebar organizes display settings, AI prompts, translations, transcript information, and speaker management in an easily accessible format
- Users can now adjust text size, colors, and padding options to customize their transcript viewing experience
- The sidebar can be collapsed to provide a more focused view of transcripts
- Individual speakers can be added on a per-transcript basis directly from the sidebar
Enhanced functionality: The update brings several practical improvements that streamline the transcription workflow.
- Word-level highlighting during playback is now available for transcripts created with WhisperKit models
- Voice Activity Detection has been added for WhisperKit models, improving transcription speed
- The search function now displays the total number of matching words in transcripts
- Users can control playback speed using keyboard shortcuts and adjust font sizes with standard command keys
Dictation capabilities: MacWhisper’s dictation feature has been refined to provide a more seamless experience across the operating system.
- The app now offers speech-to-text functionality that works in any text field on Mac
- Dictation is reported to be more than four times faster than typing
- Users can choose to use the right option key for dictation control
- The feature includes AI integration for automatic real-time text rewrites
Privacy and integration: MacWhisper maintains its commitment to user privacy while expanding integration options.
- The app supports on-device AI services including LM Studio and Ollama
- Users can now choose to run the app exclusively from the menu bar without requiring the main application to be open
- Dictations are designed not to appear in clipboard history managers
Technical refinements: Version 11/11.1 includes numerous quality-of-life improvements that enhance the overall user experience.
- The HTML export feature now automatically adapts to light and dark mode
- Video playback speed synchronizes with audio playback adjustments
- The app intelligently defaults to the next best model if a Whisper model fails to load
- Export previews now display complete transcripts
Looking ahead: While MacWhisper 11 represents a significant evolution in transcription software, its enhanced AI integration and focus on user experience suggest future updates may continue to push the boundaries of what’s possible in automated transcription technology, particularly in areas of real-time processing and accessibility.
Recent Stories
DOE fusion roadmap targets 2030s commercial deployment as AI drives $9B investment
The Department of Energy has released a new roadmap targeting commercial-scale fusion power deployment by the mid-2030s, though the plan lacks specific funding commitments and relies on scientific breakthroughs that have eluded researchers for decades. The strategy emphasizes public-private partnerships and positions AI as both a research tool and motivation for developing fusion energy to meet data centers' growing electricity demands. The big picture: The DOE's roadmap aims to "deliver the public infrastructure that supports the fusion private sector scale up in the 2030s," but acknowledges it cannot commit to specific funding levels and remains subject to Congressional appropriations. Why...
Oct 17, 2025Tying it all together: Credo’s purple cables power the $4B AI data center boom
Credo, a Silicon Valley semiconductor company specializing in data center cables and chips, has seen its stock price more than double this year to $143.61, following a 245% surge in 2024. The company's signature purple cables, which cost between $300-$500 each, have become essential infrastructure for AI data centers, positioning Credo to capitalize on the trillion-dollar AI infrastructure expansion as hyperscalers like Amazon, Microsoft, and Elon Musk's xAI rapidly build out massive computing facilities. What you should know: Credo's active electrical cables (AECs) are becoming indispensable for connecting the massive GPU clusters required for AI training and inference. The company...
Oct 17, 2025Vatican launches Latin American AI network for human development
The Vatican hosted a two-day conference bringing together 50 global experts to explore how artificial intelligence can advance peace, social justice, and human development. The event launched the Latin American AI Network for Integral Human Development and established principles for ethical AI governance that prioritize human dignity over technological advancement. What you should know: The Pontifical Academy of Social Sciences, the Vatican's research body for social issues, organized the "Digital Rerum Novarum" conference on October 16-17, combining academic research with practical AI applications. Participants included leading experts from MIT, Microsoft, Columbia University, the UN, and major European institutions. The conference...