What changed in Voice2Sub

Voice2Sub 1.1.4 improves startup reliability, media access, task cancellation, model and update downloads, subtitle export, and recovery of settings, history, and editing sessions across Windows, macOS, and Linux.

• Improved startup and second-launch reliability across Windows, macOS, and Linux.
• Improved access to media stored in OneDrive, network locations, and folders with special characters, with clearer error messages.
• Safer cancellation and shutdown handling reduces leftover background processes and temporary files.
• Improved detection of missing, damaged, or incomplete models, with safer resumable model and update downloads.
• Safer subtitle export and data recovery help prevent accidental overwrites and preserve settings, history, and editor sessions.
• Improved upgrade compatibility from Voice2Sub 1.1.2 and 1.1.3. macOS now requires version 15.6 or later.

Voice2Sub 1.1.3 improves the review step after subtitle generation: edit text and timing, reopen recent results, import existing subtitle files, preview audio, save drafts, and export edited subtitles as separate files.

• Added a subtitle editor for revising subtitle text and fine-tuning timing directly in Voice2Sub.
• Added subtitle generation history so you can review recent results, open output folders, or continue editing faster.
• Generated subtitles can be edited later, including original subtitles and English subtitles when a translation was created.
• Added support for importing existing subtitle files and editing them together with video or audio.
• Added an audio timeline and preview playback to make subtitle timing more visual and accurate.
• Added practical editing tools for adding, deleting, splitting, and merging subtitle lines, plus Undo/Redo and Find/Replace.
• Added edit draft saving and the ability to reopen recent editing sessions.
• Edited subtitles are exported as separate files to help avoid accidentally overwriting the original files.
• Added German language support.
• Improved the overall interface, user experience, and stability.

Voice2Sub 1.1.2 adds translation from source-language speech into English subtitle files, improves multilingual UI rendering, makes CUDA setup clearer, and updates the subtitle engine for better stability across Windows, Linux, and macOS.

• Translate speech from supported source languages into English subtitles with English only output, or create separate source-language and English subtitle files with Original + English.
• Improved display quality and smoother language switching for Chinese, Japanese, Korean, Thai, and Hindi.
• Clearer CUDA setup and repair flow with background runtime checks.
• Updated subtitle engine and media processing for better stability across Windows, Linux, and macOS.

Voice2Sub 1.1.1 improves subtitle creation reliability, especially on macOS Apple Silicon, and handles long file names, Vietnamese accents, and special characters more smoothly.

• Improved subtitle creation reliability on macOS Apple Silicon.
• Better handling for long file names, Vietnamese accents, and special characters in file paths.
• More reliable checks and recovery for the local processing components used to create subtitles.

Voice2Sub 1.1.0 lets you create subtitles for multiple files at once, follow progress more easily, and enjoy more reliable file handling and updates across Windows, macOS, and Linux.

• Create subtitles for multiple audio or video files in one run with the new batch workflow.
• Follow progress more easily with a new processing drawer and clearer status log.
• Improved file selection, drag-and-drop, internal processing reliability, and update reliability on Windows, macOS, and Linux.

Voice2Sub 1.0.5 adds Linux availability and optimizes overall performance and stability for a smoother, more reliable user experience.

• Voice2Sub is now available for Linux.
• Optimized overall performance and stability for a smoother, more reliable user experience.

Voice2Sub 1.0.4 improves license management reliability and the overall activation experience, while making updates more reliable, safer, and more stable on Windows and macOS.

• Improved license management reliability and overall activation experience.
• Improved update reliability, safety, and stability on Windows and macOS.

Voice2Sub 1.0.3 improves Windows runtime compatibility, adds clearer diagnostics for subtitle generation errors, and makes update paths safer for older app versions.

• Windows: Voice2Sub checks for a supported Microsoft Visual C++ Runtime and guides users to install the latest Microsoft runtime when their system is outdated.
• Audio processing and subtitle generation errors now include detailed native process logs, exit codes, and clearer messages.
• Update compatibility is improved for users moving from older app versions.

Voice2Sub 1.0.2 updates how CUDA is enabled on Windows and improves download speed and progress feedback.

• Windows: CUDA acceleration is managed inside the Windows app. The app detects compatible NVIDIA GPUs and lets users download required CUDA libraries from Settings.
• Download speed is now shown for app updates, CUDA libraries, and AI model downloads.

Voice2Sub 1.0.1 matches the app update notes: faster Audio Quality Enhancement processing and more stable stop/cancel behavior during audio processing.

• Optimized processing speed when using the "Audio Quality Enhancement" option.
• Improved stability when stopping or canceling audio processing.

The first public release introduced the desktop workflow for turning speech in video or audio into AI subtitles, transcripts and plain text output.

• Windows x64 and macOS Apple Silicon builds.
• Windows app later supports optional CUDA acceleration managed inside the app.
• Local speech recognition for offline transcription work.
• Support for up to 99 recognition languages and common media formats.
• Subtitle and plain-text output for creator, learning and documentation workflows.