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.