• iPhone Duo: adaptive recording and live transcription layouts, plus side-by-side library navigation. • Label speakers on-device after transcription, then rename or correct their labels. • Reduce noise before re-transcribing, while keeping the original recording. • Remove quiet pauses from playback and exported audio; SRT timings adapt to trimmed audio. • Get model setup guidance based on device resources.

• Read the full transcript in the new reading view, or switch back to timestamped passages. • Mark important passages and copy text directly from each passage. • Follow the active passage during playback and skip forward or back by 10 seconds. • Open matching source passages from supported summary points to review the context.

• New recordings and saved notes now use the same detail view for playback, transcripts and summaries. • Saving an edit can now save a draft when automatic saving is off. • With automatic saving enabled, recordings without a transcript remain accessible in the library for later transcription.

Version 3.2 makes live recording easier to follow and control. • Added a focused full-screen live transcription view. • See recording time, audio activity, and recent transcript text in the Lock Screen Live Activity and Dynamic Island on supported devices. • Pause, resume, or stop recording directly from the Live Activity. • Improved real-time transcription behavior while the screen is locked.

• Added a searchable transcription-language picker with automatic detection or manual language selection. • Your chosen language now applies consistently to live transcription, imported audio, and long-audio processing, with automatic handling for English-only models. • Change the language from an audio or saved-note screen to re-transcribe the original recording. • Added guidance when automatic detection does not produce the expected result and fixed language-setting inconsistencies between transcription workflows. • Fixed crashes that could occur while processing empty or unreadable audio or recovering recordings with invalid segments.

• Added a searchable transcription-language picker with automatic detection or manual language selection. • Your chosen language now applies consistently to live transcription, imported audio, and long-audio processing, with automatic handling for English-only models. • Change the language from an audio or saved-note screen to re-transcribe the original recording. • Added guidance when automatic detection does not produce the expected result and fixed language-setting inconsistencies between transcription workflows.

• Long recordings are now saved automatically in 10-minute segments and can recover saved audio and transcription progress after an interruption. • Improved long-audio transcription with chunked processing for greater reliability. • Added note-title editing, transcript editing by timestamped segment, and full-text search across titles and content. • After several transcriptions with Tiny, the app can suggest a larger model and take you directly to model management. • Improved model-loading and error-handling stability, and fixed edited titles not refreshing promptly in the note list.

• Long recordings are now saved automatically in 10-minute segments. There is no fixed duration limit; actual recording time depends on device storage and system conditions. • Recover saved audio and transcription progress after an interruption. • Rename note titles and edit transcript text. • Edit long transcripts by timestamped segment and search across titles and content. • Fixed title changes not refreshing in the list and improved the note details screen.

• Added segmented saving and recovery for long recordings. • Added note title renaming and transcript editing, including timestamped segments. • Added full-text search across titles, transcripts, and summaries. • Improved storage checks and long-recording reliability.

Version 2.7 brings more flexible and transparent transcript summaries. • Summaries now adapt to available on-device capabilities, using Apple Intelligence when supported and local fallback methods when it is unavailable • New engine badges show how each summary was generated • Generate or regenerate summaries anytime from current and saved transcripts • Transcripts are saved first while summaries finish in the background • Copy a prepared prompt and transcript, then open ChatGPT to continue there • Refined transcript and summary views, with reliability improvements

This update makes recording and audio transcription faster to access across iPhone. • Share a user-selected audio file directly to Whisper Notes • Choose to import shared audio or begin transcription immediately • Start recording from Home Screen and Lock Screen widgets • Add a recording control to Control Center on supported devices • Start recording with Siri and App Shortcuts • Long-press the app icon to record, select audio for transcription, open notes, or choose a model • Improved audio import reliability and supported format handling

This update makes WhisperNotes faster, cleaner, and easier to use. • Record from iPhone, Apple Watch, widgets, and Control Center shortcuts • Transcribe audio offline with no cloud upload required • Turn recordings into Overview, Key Points, and Action Items • Import audio and video from Voice Memos, Files, WhatsApp, and videos • Export notes and transcripts as Markdown, SRT, OPML, and PDF • Improved recording, transcript, and Apple Watch experience • Privacy-focused improvements and stability fixes WhisperNotes is still a one-time purchase. No subscription required.

Added multilingual app language switching and improved recording, real-time transcription, summaries, text sharing, and Apple Watch recording.

• New Apple Watch companion experience • Record audio directly on Apple Watch • Play back watch recordings before sending • Send watch audio to iPhone for private offline transcription • View live captions, transcript progress, and summaries on your wrist • Improved pause/resume recording • Cleaner, more readable transcription display

Version 1.5 Added Pause & Resume Recording: Pause anytime during recording and continue seamlessly — never miss a word again! Optimized transcription display: Brand new clean layout, smart timestamps, and improved formatting for much better readability. Performance improvements and minor bug fixes. Continues to support 100% offline Whisper AI with privacy first.

Noise Reduction Reduce background noise before transcription for clearer speech and higher accuracy — even in cafés, meetings, or travel scenarios. Dark Mode Supports system appearance and manual switching for a comfortable, distraction-free experience day or night.

Big update! WhisperNote now lets you import local audio files and transform transcripts into powerful new formats: Import Audio: Transcribe any MP3, WAV, M4A, etc., from your device, offline. Mind Map Generation: Visualize your ideas! Automatically create and export mind maps from your text. SRT Subtitle Export: Perfect for creators—generate time-stamped SRT files for your videos. Markdown Export: Preview and export transcripts as structured Markdown notes. Enhanced Performance: Faster, more accurate on-device AI transcription.

What’s New Added real-time transcription — convert speech to text instantly as you speak, fully offline. Included a built-in basic model so you can start transcribing immediately after installation. New automatic segmentation — your transcriptions are now organized into clean, readable paragraphs. Improved stability, faster processing, and overall performance enhancements.