Added Vocabulary Hints Support: - You can now add custom vocabulary, proper nouns, names, and industry-specific terminology hints. - Significantly reduces misrecognition of uncommon words and specific terms during speech recognition and subtitle extraction. - Perfect for technical videos, anime/movie character names, and specialized jargon. Interface & Experience Improvements: - Streamlined the mobile vocabulary management interface with quick editing and toggle options. - Improved background processing performance and recognition speed.

1. New Whisper Voice Recognition Mode Integrated the Whisper speech-to-text framework. When videos lack on-screen text or have highly cluttered backgrounds, users can select this mode to directly transcribe audio tracks into time-coded standard SRT files. Supports automatic audio language detection. 2. Refactored Functional Modes (Four Independent Options) To better accommodate varied post-production workflows, core features are now structured into four distinct, mutually exclusive modes: Manual ROI Mode: Users manually define the Region of Interest (ROI) for targeted visual OCR scanning. Auto ROI Mode: The system automatically detects and locks the subtitle area for visual OCR scanning. Voice Recognition Mode: A new mode that bypasses visual scanning entirely, performing voice-to-text transcription directly on the audio stream. Playback Only Mode: A new mode that invokes neither OCR nor voice recognition engines. It functions strictly as a standard video player, allowing users to preview media or overlay existing subtitle tracks. 3. Core Workflow Integration Subtitles generated via either OCR scanning or the new voice recognition mode integrate seamlessly with the pre-existing Seamless AI Translation Workflow and AI Video Copilot prompt templates. 4. Sandbox Privacy & Performance Optimization Strictly operates within the Apple Sandbox framework. Both audio and video streams are processed on-the-fly inside active memory with zero local copying, caching, or remote server exposure. Optimized dynamic memory release logic to improve stability when handling long-duration footage.

【Major Upgrade: Moving Towards the Era of AI-Powered Automation】 Intelligent Auto-Detection Workflow (With Manual Precision) Upon import, the system now automatically detects the subtitle region (ROI), locks text boxes, and identifies languages for an instant, zero-configuration scanning experience. Professional control is never compromised: switch to manual mode at any time to custom-adjust scanning areas for complex layouts. Seamless AI Subtitle Translation Workflow Smartly bundles extracted subtitles with tailored translation prompts. Use the iOS Share Sheet to send text straight to preferred AI assistants (such as ChatGPT or Claude), or leverage the automatic clipboard formatting on macOS for a frictionless paste-and-go multi-language workflow. AI Video Copilot (Instant Video Q&A) Productivity does not end with SRT generation! Utilize built-in high-frequency prompt templates to instantly bundle transcripts with your queries, letting AI handle advanced tasks like Fact-Checking, Instant Summaries, Copywriting/Titles, and Thumbnail Visual Inspiration. Built-in Standard Format Video Playback Solves the pain point of figuring out how to view generated SRT files. The newly integrated preview player natively supports standard compatible formats (MP4, MOV, M4V), overlaying your subtitle track right inside the app. (Note: Advanced formats like AV1 are fully supported for OCR scanning and extraction, but localized video playback may be restricted by system framework limitations.) 【Hardcore Privacy & Sandbox Security】 Strict Zero-Storage & Zero-Copy: Operating fully within the Apple Sandbox framework, the app processes video files entirely on-the-fly in memory. It never stores, duplicates, or caches your video files. Temporary Access Lifecycle Management: The application requests transient access tokens via system-secured URLs. Once the security session expires, file resources are automatically and completely released. 【Core Algorithm & Performance Enhancements】 5. Refined Auto-Detection Optimization: Addressed edge cases from previous versions where non-standard aspect ratios or highly complex backgrounds caused template extraction variances. 6. Re-Engineered 4K & Long Video Stability: Advanced memory management optimizations systematically prevent crashes and memory leaks, ensuring seamless processing for long-duration and Ultra-HD footage.

Seamless AI Subtitle Translation Workflow Unlock 60+ Languages Instantly: Optimized prompts tailored for natural, context-aware translations. Use the iOS Share Sheet to send your text straight to AI apps, or leverage the smart clipboard on macOS for a frictionless desktop experience. AI Video Copilot (Instant Video Q&A) Your workflow shouldn't end with just extracting an SRT file. Version 2.9 introduces preset "AI Insight Prompts" that perfectly bundle your subtitles with actionable questions. With a single tap, send them to your favorite AI to handle heavy lifting like 【Fact-Checking】, 【Instant Summary】, 【Title Generation】, and 【Thumbnail Inspiration】. Built-in Standard Format Video Playback Preview Instantly: Many users struggle with how to open and play their newly translated SRT subtitles. Version 2.9 adds an integrated player supporting standard system-compatible formats (such as MP4, MOV, M4V). You can now play your video and overlay the extracted/translated subtitles directly inside the app—delivering a smooth "Extract, Translate, and Preview" experience. 【Privacy & Sandbox Security】 Zero Storage, Zero Copies: We deeply respect your data privacy. Strictly operating within the Apple Sandbox framework, the app never stores, duplicates, or caches your video files. Temporary Access Lifecycle Management: The app requests only transient read-only permissions via system-secured tokens (Security-Scoped URLs) in memory. Once this temporary security token expires, the file is securely released. If you need to access it again, the app will safely prompt you to reconnect/re-import the file. Your media remains 100% under your control. 【Algorithm Fixes & Performance Enhancements】 4. Refined Auto-Detection Optimization (Bug Fixes) We addressed edge cases from the previous version where certain videos with unusual aspect ratios or complex backgrounds caused hiccups in our automatic template extraction (subtitle positioning and language auto-detection). The "Zero-Configuration" pipeline is now rock-solid.

In this major milestone update, we are introducing a revolutionary feature that completely redefines and simplifies your subtitle extraction workflow. Say goodbye to manual bounding boxes and guessing video languages—the app now handles everything intelligently for you. 【Key New Features】 Auto Subtitle Detection: Driven by an advanced layout-parsing algorithm, the app now automatically locates and locks onto the exact position of subtitles in your video. Smart Language Auto-Detection: No more manual language selection! The app instantly analyzes and detects the subtitle language with industry-leading accuracy for the vast majority of standard videos. Zero-Configuration, Peak Efficiency: We have completely removed the tedious pre-scanning setup. Just import your video and let the automation work its magic. Your productivity is about to soar. 【Seamless Import Workflows for iOS】 Context Menu: Long-press any video file inside the Files app, select "Open With..." and choose OCR Subtitle. Drag & Drop: Simply drag a video file from the Files app and drop it right onto the "+" target area within OCR Subtitle. In-App Picker: Tap the "+" button inside the app to flexibly choose videos from either your Files directory or your Photos library. 【Seamless Import Workflows for macOS】 Finder Open With: Right-click a video file in Finder, navigate to "Open With..." and select OCR Subtitle. Instant Drag & Drop: Drag a video file straight from Finder and drop it onto the "+" icon in the app window to kick off scanning instantly. Native Finder Selector: Click the "+" button inside the app to quickly browse and select your target files via the standard Finder sheet.

Special thanks to **at9**39@gmail.com** for the valuable feedback! New "Skip Intro & Skip Outro" Template Settings: Designed specifically for extracting subtitles from series. Automatically skip intros and outros to save time during batch processing. Enhanced Template Creation UI: Added "Close," "Scan Video," and "Advanced Template Settings" options to the creation interface. Streamlined Workflow: The default action is now set to "Scan Video," allowing you to start the recognition process instantly after setup.

Special thanks to bel***@gmail.com for the valuable feedback. OCR Subtitle Ultra v2.6 Update: Performance & Stability Boost Re-engineered memory management specifically optimized for 4K Ultra-HD and long-duration videos. Processing high-resolution footage is now significantly more stable, minimizing crash risks during export. New Decoding Engine Upgraded FFmpeg backend now natively supports H.265 (HEVC), AV1, and various professional video formats with improved decoding efficiency. Enhanced Smart ROI (Region of Interest) Supports more precise custom scanning areas with real-time zoom preview. This ensures the OCR engine focuses accurately on subtitles, reducing interference from backgrounds or logos. Professional Workflow Optimization Improved SRT timeline merging algorithm. Exported subtitle files are now fully compatible with major editing platforms like Final Cut Pro and Adobe Premiere. Brand New Visual Identity Updated with a fresh app icon. Featuring a dark-themed design with brushed metal elements, the new look aligns with the professional "Ultra" positioning and fits perfectly with Dark Mode. For support or feedback, please contact: hanmingjie@gmail.com

【Core Engine: A Massive Leap in Performance】 New FFmpeg Integration: Deeply integrated the industry-leading multimedia framework, bringing a quantum leap in video format compatibility. Enhanced 4K Decoding Suite: New AV1 Support: Built-in high-performance dav1d decoder for seamless playback of next-generation video formats. VP9 & WebM Support: Full optimization for WebM containers and VP9-encoded videos from major streaming platforms. Refined H.265 (HEVC) Experience: Specialized tuning for high-bitrate 4K H.265 videos, ensuring a buttery-smooth viewing experience. 【Evolution: Better Workflow & Localization】 Improved Template Selection Interface: A completely redesigned UI for previewing and switching templates. Finding and applying the right recognition preset is now faster and more intuitive. Traditional Chinese Support: Full localization for Traditional Chinese (zh-Hant). From menu settings to recognition results, providing a native and seamless experience for users worldwide. 【Efficiency: Optimized for Long Videos】 Advanced Memory Management: Redesigned memory scheduling for OCR tasks. Memory footprint is reduced by over 30% when processing long-form videos (2+ hours), keeping your system light and responsive. Boosted Recognition Speed: Optimized frame parsing and OCR queuing logic, significantly shortening the wait time for long-video processing.

Thanks again to yuj***@gmail.com for the helpful feedback. Improvement: Greatly improved English subtitle recognition accuracy. In our internal tests, about 92% of subtitle sentences are extracted correctly, with most remaining errors occurring at sentence boundaries.

Special thanks to the user yuj***@gmail.com for the patient feedback and repeated communication, which helped me finally identify the root cause of the issue. Fix: When scanning large video subtitles, the system entering sleep mode could lead to unpredictable results. This update adds a control mechanism to temporarily prevent the device from sleeping during the subtitle scanning and extraction process, ensuring the task completes reliably. If you encounter any issues while using the app, please feel free to use the in-app feedback feature and leave your email so I can follow up if needed.

Thanks to aaa***@yahoo.com.hk for the feedback! This version includes the following updates: • Set the exact area for subtitle extraction: define X and Y coordinates to scan only the selected region. • Choose the source on iOS: open videos from Photos or Files.

Thank you for the feedback from at****039@gmail.com, this update introduces Multi-Frame OCR Consensus. By aggregating OCR results across consecutive video frames and enforcing temporal consistency, the algorithm significantly reduces recognition errors caused by background changes, motion, and fade-in subtitles. Subtitle stability and accuracy have been improved for Chinese, English, and Vietnamese content.

Thank you for your feedback! New in this release: * Fixed the crash issue when scanning resolution exceeds 1920. * Fixed some program errors and improved program compatibility.

Thank you for your feedback! New in this release: Supports extracting videos with multiple lines of subtitles. Fixed some program bugs.

Thank you for your feedback! New in this release: Improvements Improved program stability. Fixed some program bugs.

Thank you for your feedback! New in this release: Improvements Improved program stability. Fixed some program bugs.

Thank you for your feedback! New in this release: * Added feedback module * Fixed collector for subtitle text, the trash can is ridiculous

Thank you for your feedback! New in this release: * Improved image similarity calculation to reduce title duplication errors. * Added subtitle centering check function. * Improved settings interface. * We've also fixed bugs and added various other enhancements.

Thank you for your feedback! New in this release: * Now you can extract the video subtitles that need to be rotated. * We've also fixed bugs and added various other enhancements.

Thank you for your feedback! New in this release: * Now you can set whether to enable the subtitle centering check. * We've also fixed bugs and added various other enhancements.