Version 3.8 – Stability & Accessibility BUG FIXES • FluidAudio updated to 0.12.3 with improved download progress tracking • Fixed memory leak: diarization models (~300 MB) now correctly released after transcription • Fixed enhancement UI getting stuck in loading state when enhancement fails • Cancelling a transcription no longer shows an error dialog • After app restart, model reloading now shows progress instead of a silent freeze • Fixed recording resume silently failing while UI showed it as active ACCESSIBILITY • Action bar buttons on iPhone now have proper VoiceOver labels • Recording timer, tab bar icons, and more elements now scale with Dynamic Type • Additional decorative elements correctly hidden from screen readers SECURITY • Session transcripts and audio files are now protected with iOS complete file protection, encrypted when the device is locked LOCALIZATION • Fixed status messages during model download shown in German to English, French, and Dutch users Privacy first: All processing remains 100% on-device.

Version 3.7 – FluidAudio 0.12 & Liquid Glass Design FLUIDAUDIO 0.12 UPDATE • Major upgrade to FluidAudio 0.12 speaker recognition engine • Streaming audio processing for better memory efficiency • Improved speaker identification accuracy • New speaker count settings: specify 2-10 expected speakers • Orphaned word recovery: words near segment boundaries no longer lost IPHONE RELIABILITY • Fixed speaker recognition producing empty results on iPhone • Automatic fallback when word-level timing data is unavailable • Chunked audio enhancement prevents out-of-memory on long files • ML models released after use to free ~1.5 GB of memory LIQUID GLASS DESIGN • Completely redesigned with iOS 26 Liquid Glass • Beautiful glass effects with smooth morphing animations • Tab bar with fluid transitions between views • Cleaner iPad/Mac layout with streamlined toolbar KEYBOARD SHORTCUTS • ⌘, for Settings • ⌘I to Import files • ⌘R to start Recording • Perfect for iPad with keyboard and Mac ACCESSIBILITY • Improved VoiceOver support throughout • Better labels for swipe actions • Enhanced screen reader navigation Privacy first: All processing remains 100% on-device.

Version 3.6 – Speaker Editing & Audio Enhancement SPEAKER NAME EDITING • Rename speakers with a simple tap – change "Speaker 1" to actual names • Names persist across the entire transcript • Makes meeting notes more readable and professional AUDIO ENHANCEMENT • New audio optimization before transcription • Reduces background noise for clearer results • Especially useful for recordings in noisy environments MEETING SUMMARIES • Enhanced meeting summary mode • Automatically extracts action items and agreements • Perfect for team meetings and project discussions IMPROVEMENTS • Faster session loading • Better error handling for translations • Improved stability throughout Privacy first: All processing remains 100% on-device.

TESTING REQUIREMENTS: This app requires iOS 26.1 or macOS 26.1 with Apple Intelligence enabled. Please ensure Apple Intelligence is activated in Settings > Apple Intelligence & Siri before testing. HOW TO TEST: 1. Open the app – you'll see the Session Library 2. Tap "+" to start a new session 3. Choose "Select File" for audio (MP3, M4A, WAV) or video (MP4, MOV, M4V) 4. Or choose "Record" to capture audio directly 5. Select transcription language 6. Optionally enable "Speaker Recognition" for multi-speaker recordings 7. Tap "Start Transcription" 8. After completion, the session opens with 4 tabs: - Transcript: View and edit the transcription - Translations: Translate into 34 languages - Summaries: Generate AI summaries - Subtitles: Preview and export video subtitles TRANSCRIPTION ENGINE: - Apple Intelligence handles all transcription (~20 languages) - FluidAudio provides speaker recognition/diarization only - Both work 100% on-device with no cloud uploads SPEAKER RECOGNITION: 1. Select an audio file with multiple speakers (interview, meeting, podcast) 2. Enable "Speaker Recognition" toggle 3. Select a preset: Interview (2-3 speakers), Meeting (4-6), or Conversation (2-3) 4. Start transcription 5. The transcript shows color-coded speaker labels (Speaker 1, Speaker 2, etc.) VOICE MEMOS INTEGRATION: 1. Open Apple's Voice Memos app 2. Record or select an existing memo 3. Tap Share and select "Transkript" 4. The audio opens directly in Transkript for transcription Note: On Mac, use drag-and-drop instead of Share SESSION LIBRARY FEATURES: - All transcriptions saved as sessions - Pull-to-refresh to update - Custom storage location (iCloud, Proton Drive, any folder) - Sessions persist between app launches VIDEO SUBTITLE WORKFLOW: 1. Select a video file (MP4, MOV, M4V) 2. Audio is extracted automatically 3. After transcription, go to Subtitles tab 4. Use "Optimize" to create readable subtitle segments 5. Preview subtitles overlaid on your video 6. Export as SRT or VTT TRANSLATION & SUMMARIES: - Translations tab: Translate transcript into 34 languages, preserving timestamps - Summaries tab: Generate AI summaries, export as PDF or DOCX SAMPLE FILES: Any spoken audio or video file will work. For Speaker Recognition testing, use recordings with 2+ distinct speakers. PRIVACY: - No network requests for transcription/translation/summarization - All processing uses on-device Apple Intelligence - FluidAudio speaker recognition also runs on-device - No user account or login required - No data collection or analytics PERMISSIONS REQUESTED: - Microphone: For recording audio - Speech Recognition: For on-device transcription

Speaker Recognition is here! • Automatically identify different speakers in your recordings • Perfect for meetings, interviews, and podcasts • Color-coded labels show who said what • Choose from presets: Interview, Meeting, or Conversation Voice Memos Integration: • Share recordings directly from Voice Memos to Transkript • Drag and drop audio files on Mac All processing remains 100% on-device for complete privacy.

Automatic Engine Selection The app now automatically chooses the best AI engine (Apple Intelligence or Whisper) based on your selected language. See availability with green bolt or orange checkmark icons. Word Export Export your summaries as Microsoft Word documents (.docx) in addition to PDF. Perfect for editing and sharing. Long Text Support Long transcripts are now automatically split into chunks, summarized individually, then combined into a final summary. Improved Progress Accurate progress indicator based on audio position with time remaining estimates.

What's New in Version 2.0 Whisper AI Integration Transkript now supports two powerful engines: Apple Intelligence and OpenAI Whisper. Choose Whisper for even more languages and higher accuracy – all 100% offline and private on your device. Video Subtitles Import MP4 and MOV videos and export perfectly timed subtitles in SRT or VTT format. Perfect for YouTube, social media, and professional video production. Translation Feature Translate your transcripts into 30+ languages – with preserved timestamps for synchronized subtitles. Subtitle Optimization Automatically split long segments into readable subtitles. Configure maximum characters and duration for perfect readability. Improved Design Completely redesigned interface with animated progress, cleaner buttons, and optimized iPhone layout. Quick Start Mode Enable Quick Start in settings to begin transcription immediately after dropping a file.

What's New in This Version VIDEO SUPPORT • Transcribe video files (MP4, MOV, M4V) directly • Preview subtitles overlaid on your video • Extract audio automatically for transcription SUBTITLE OPTIMIZATION • Split long segments into readable subtitle chunks • Customize max characters (80) and duration (5s) per segment • Perfect for SRT/VTT export TRANSLATION IMPROVEMENTS • Untranslated segments now highlighted in orange • Tap to edit individual segments inline • Filter to show only segments needing attention • Detects partially translated text automatically EXPORT FIXES • Improved export dialog layout • Fixed export for optimized subtitles • Better macOS compatibility Plus: New help pages, changelog, and 404 pages on our website.