After many late nights, it’s finally ready. This update brings a more complete on-device recording and transcription experience: - Added Parakeet V3 Near-Realtime captions with on-device support for 25 European languages - Picture in Picture captions now support adjustable window proportions and text sizes, with bilingual previews - Dynamic Island transcripts now offer small, medium, and large text sizes - Nemotron can now detect the spoken language automatically - MOSS on-device speaker refinement now supports both Apple Speech and Nemotron - Added offline speaker recognition to separate speakers and identify people you’ve previously saved - Improved conversation playback by combining adjacent segments from the same speaker into continuous passages - The full transcript editor now links the cursor to the matching audio, so you can listen and edit without losing your place - Added timestamped recording chapters to help you find key moments faster - Added more font and app icon theme options This update also fixes several issues and continues to improve stability and the overall experience. Thank you to everyone for your continued support and patience. LiveTranscriber is still evolving, and some features remain in Beta. There may also be issues we haven’t discovered yet. If you experience problems with recognition, model downloads, recordings, or captions, please let me know through Settings > Feedback. If possible, include the steps to reproduce the issue and relevant screenshots to help me investigate it more quickly. I read every piece of feedback. Thank you for helping make LiveTranscriber better!After many late nights, it’s finally polished and ready. This update brings a more complete on-device recording and transcription experience: - Added Parakeet V3 Near-Realtime captions with on-device support for 25 European languages - Picture in Picture captions now support adjustable window proportions and text sizes, with bilingual previews - Dynamic Island transcripts now offer small, medium, and large text sizes - Nemotron can now detect the spoken language automatically - MOSS on-device speaker refinement now supports both Apple Speech and Nemotron - Added offline speaker recognition to separate speakers and identify people you’ve previously saved - Improved conversation playback by combining adjacent segments from the same speaker into continuous passages - The full transcript editor now links the cursor to the matching audio, so you can listen and edit without losing your place - Added timestamped recording chapters to help you find key moments faster - Added more font and app icon theme options This update also fixes several issues and continues to improve stability and the overall experience. Thank you to everyone for your continued support and patience. LiveTranscriber is still evolving, and some features remain in Beta. There may also be issues we haven’t discovered yet. If you experience problems with recognition, model downloads, recordings, or captions, please let me know through Settings > Feedback. If possible, include the steps to reproduce the issue and relevant screenshots to help me investigate it more quickly. I read every piece of feedback. Thank you for helping make LiveTranscriber better!

• Redesigned onboarding makes it easier to understand live and offline transcription, choose an on-device model, and download it • Smoother recording dashboard charts and animations, with improved ProMotion support • Clearer recording details for microphones, transcription models, and model providers • Improved localization, accessibility, interface polish, and overall transcription reliability • Fixed the transcription model crash issue. • Fixed the crash that occurred when importing audio recordings. • Improved overall app smoothness and responsiveness. • Hot fix for 1.2.1

• Redesigned onboarding makes it easier to understand live and offline transcription, choose an on-device model, and download it • Smoother recording dashboard charts and animations, with improved ProMotion support • Clearer recording details for microphones, transcription models, and model providers • Improved localization, accessibility, interface polish, and overall transcription reliability • Fixed the transcription model crash issue. • Fixed the crash that occurred when importing audio recordings. • Improved overall app smoothness and responsiveness.

LiveTranscriber 1.2 is a major update: • A new Apple Watch app lets you start, pause, resume, and stop recordings from your wrist, play recordings on the watch, and transfer them to your iPhone • New Apple Watch widgets and complications provide quick recording access and show recording and transfer status • Choose Voice, Balanced, or High Quality recording on Apple Watch, with optional recording location • Added Parakeet V3 for fast, high-accuracy Core ML transcription across supported European languages • Start offline background retranscription from the recording player, with progress preserved for long-running tasks • Added optional Sortformer live speaker diarization with stable speaker labels during recording • Added Qwen3-ASR Live Beta and improved streaming support for long recordings • Reworked Nemotron 3.5 Core ML live transcription with improved model loading, background handling, and timestamp alignment • Added optional automatic MOSS post-recording refinement for more accurate final transcripts and speaker-separated results • Added Picture in Picture captions so live transcription remains visible while using other apps • Improved live and saved-transcript translation, with a new settings page for checking and preparing Apple Translation language packs • Added Standard and Spatial Audio capture profiles, sample-rate and mono/stereo controls, wind-noise removal, high-quality Bluetooth recording, and microphone selection • Redesigned recording details and playback with clearer waveforms, transcript locating and following, audio effects, and spatial-audio master sharing • Improved recording editing for titles, key points, tags, summaries, languages, categories, and locations, including location search and current-location support • Added automatic recording details and intelligence output-language controls, with improved local summaries, recording chat, and translated-transcript analysis • Choose the app’s interface language independently from the system: English, Simplified Chinese, Traditional Chinese, Japanese, German, French, or Dutch • Language menus now remember frequently selected languages and prioritize them across the app • Added a redesigned step-by-step introduction covering languages, recording formats, local models, and privacy • Improved model download progress, deletion, and status reporting, with a complete third-party model and runtime license catalog • Fixed the Parakeet model permission error, Nemotron timestamp drift, and multiple background transcription, system-audio, and recording stability issues

Version 1.1 brings a major upgrade to live and offline transcription. Dutch, now live Transcribe Dutch speech in real time and translate it into another language while recording. The new streaming engine also adds automatic punctuation and capitalization. Faster, smarter on-device transcription A new on-device streaming engine supports more than 75 language locales. Automatic mode chooses Apple’s on-device transcription when available and the fast offline engine when needed. More ways to transcribe saved audio Choose Standard, Fast Offline, High Accuracy, or Separate Speakers, depending on the recording and the result you need. Translations are now saved Translations created during recording can be saved with the recording. Translations generated later are remembered too, including your selected translation language. Redesigned playback Review recordings with a new compact or expanded player, precise timeline scrubbing, Repeat One, clearer transcript timestamps, and improved transcript navigation. New recording insights See your recording activity over the past 12 months, explore time by language, and open recordings grouped by topic or language. Also includes a refreshed recording and detail experience, more reliable model delivery, performance improvements, and bug fixes.